System

Abstract

A system is provided.SOLUTION: A system comprising: means for acquiring vital data of a user; means for acquiring preference data of cooking; means for analyzing the acquired vital data and preference data to generate an optimal cooking menu; means for providing the generated cooking menu; means for providing a cooking method based on the provided cooking menu; and means for acquiring feedback information and reflecting the feedback information in improvement of the cooking menu.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern society, labor shortages due to a declining birthrate and aging population and the growing need for individual health promotion are making it increasingly difficult to easily prepare healthy and delicious meals at home. Furthermore, it is difficult to recreate memorable meals or to provide meals tailored to individual taste preferences. This invention aims to solve these problems by providing a system that generates healthy and delicious meal menus based on each user's vital data and preferences, allowing for easy cooking. [Means for solving the problem]

[0005] The present invention is a system including a means for acquiring a user's vital data, a means for acquiring food preference data, a means for generating an optimal cooking menu by analyzing the acquired vital data and preference data, a means for providing the generated cooking menu, a means for providing cooking methods based on the provided cooking menu, and a means for acquiring feedback information and reflecting the feedback information in improving the cooking menu. The system also includes a means for providing specific ingredient measurement information based on the generated cooking menu, a video generation means for visually providing cooking methods, a machine learning model for automatically improving the generated cooking menu based on the feedback information, and a means for interfacing with IoT-enabled cooking appliances to provide cooking methods. This not only enables the system to easily provide dishes tailored to individual health conditions and preferences, but also significantly reduces the effort required for cooking, enabling users to recreate dishes of top chef-quality at home.

[0006] "Vital data" refers to data that indicates the user's health condition, and includes biological information such as weight, blood pressure, and blood sugar level.

[0007] "Preference data" is data that includes information about the types of food a user likes, their seasoning preferences, and memorable dishes they have eaten in the past.

[0008] "Analysis" refers to the process of selecting a food menu based on the acquired vital data and preference data, taking into consideration the necessary nutrients and preferred seasonings.

[0009] A "cooking menu" includes a set of recipes and cooking instructions provided to the user.

[0010] "Generative AI model" refers to the artificial intelligence algorithm used to analyze vital data and preference data to generate optimal food menus.

[0011] "Specific measurement information" is information that indicates the amount of ingredients used in a dish in specific units such as grams, tablespoons, or teaspoons.

[0012] "Cooking method" refers to instructions that indicate the steps and processes for preparing a dish, including heating methods and timing for adding seasonings.

[0013] "Video generation means" refers to technology that generates explanatory videos to make cooking procedures visually easy to understand.

[0014] "Feedback information" is data that includes impressions and suggestions for improvement provided by users after they actually cook and eat the food.

[0015] "Machine learning model" refers to the artificial intelligence algorithm used to automatically improve a food menu based on obtained feedback information.

[0016] "IoT-compatible cooking appliances" refer to cooking appliances that are connected to the Internet and can be operated and their settings changed based on external instructions. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

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

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The system of the present invention acquires a user's vital data and food preference data, and based on that data, generates, provides, and improves healthy and delicious food menus. This system operates in cooperation with the user, terminal, and server.

[0039] First, the user launches the application and enters their vital data (e.g., weight, blood pressure, blood sugar level, etc.) into the app. Then, they also enter data about their favorite dishes, memorable dishes they have eaten in the past, and taste preferences. This allows the app to clarify the user's individual health condition and food preferences.

[0040] The terminal (smartphone, tablet, etc.) sends vital data and preference data entered by the user to a server on the cloud. The server generates the optimal meal menu for the user based on the received data. This process is carried out by an AI model, which selects a meal menu that matches the nutrients necessary for health promotion and the user's preferences.

[0041] The server then sends the generated cooking menu to the device. The cooking menu includes specific ingredient measurements (in grams or tablespoons / teaspoons) and cooking instructions. If necessary, the server can also generate a video of the cooking instructions and provide it to the device, helping users to understand the menu visually.

[0042] The device also has the ability to link with the user's IoT-enabled kitchen appliances, allowing them to automatically set their cooking appliances, for example, a smart oven to heat at the appropriate temperature and time.

[0043] After cooking is complete, the user tastes the dish and provides feedback to the app on their impressions and suggestions for improvement. Once the user enters their feedback, the information is sent back to the server. The server analyzes the collected feedback and improves the AI ​​model. This will enable the app to generate future meal menus that better suit the user's preferences and health.

[0044] As a concrete example, consider the case where a user inputs vital data such as weight 70 kg, blood pressure 130 / 85, and blood sugar level 100 mg / dL, and selects "spicy curry rice" as their favorite dish. The server generates a spicy curry rice recipe that suits the user's preferences while taking into account weight and blood pressure and selecting ingredients with the appropriate nutrients. For example, it provides specific ingredients such as 200 g of chicken, 50 g of carrots, 1 tablespoon of turmeric, and 1 teaspoon of cumin, along with cooking instructions. The server then receives feedback to adjust the spiciness and reflects this in the next recipe generation.

[0045] In this way, the system of the present invention provides healthy and delicious meal menus based on the user's vital data and preferences, promoting the user's health and improving the quality of the food they eat.

[0046] The processing flow will be explained below.

[0047] Step 1:

[0048] A user launches the application and inputs their personal vital data (e.g., weight, blood pressure, blood sugar level, etc.) The user also inputs data about their favorite dishes, memories of dishes they have eaten in the past, and taste preferences.

[0049] Step 2:

[0050] The device receives vital data and preference data entered by the user and sends it to a server on the cloud.

[0051] Step 3:

[0052] The server analyzes the received vital data and preference data and generates an optimal menu based on the user's health condition and preferences. The generative AI model takes into account the nutrients necessary for health promotion and the user's taste preferences.

[0053] Step 4:

[0054] The server generates a cooking menu and sends it to the device, which includes specific ingredient measurements (in grams, tablespoons, or teaspoons) and detailed cooking instructions.

[0055] Step 5:

[0056] The terminal displays the received menu and cooking instructions to the user, and also provides the cooking instructions generated by the server as a video to the terminal for easy visual understanding.

[0057] Step 6:

[0058] The device cooks food according to the menu provided by the user. When using IoT-enabled cooking appliances, the device will link with the appliance and automatically set the appropriate temperature and time.

[0059] Step 7:

[0060] Users taste the food and enter their feedback about the taste and health effects into the app, such as "I wish it was a little spicier."

[0061] Step 8:

[0062] The device sends the user's feedback to a server on the cloud.

[0063] Step 9:

[0064] The server analyzes the collected feedback and updates the generative AI model, which then reflects the feedback in the next menu suggestions, providing a menu that is more optimized in terms of both taste and health.

[0065] In this way, the user, terminal, and server work together at each step to create a system that provides healthy and delicious meals to users.

[0066] Example 1

[0067] 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."

[0068] In modern society, it is extremely important to provide meal menus tailored to each individual's health condition and food preferences. However, providing such menus generally requires specialized knowledge, and there are no systems that are easily accessible to many people. Furthermore, there is a lack of mechanisms for quickly responding to changes in the user's health condition and improving menus based on feedback. As a result, it is difficult to continuously provide meals that promote health and match preferences.

[0069] 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.

[0070] In this invention, the server includes a means for acquiring biometric data of the user, a means for acquiring food preference data, and a means for analyzing the acquired biometric data and preference data to generate an optimal meal menu, thereby providing an optimal meal menu based on the user's health condition and preferences, and making it possible to continuously improve the menu based on feedback.

[0071] "User Biometric Data" means objective medical measurements that indicate the user's health, such as weight, blood pressure, or blood sugar level.

[0072] "Food preference data" is information that indicates a user's personal food preferences, such as the type of food they like, the strength of the flavor, and the spiciness of the food.

[0073] "Means for analyzing acquired biometric data and preference data to generate an optimal meal menu" refers to a process or device that analyzes a user's biometric data and preference data and creates a nutritionally balanced meal menu appropriate for the user based on that data.

[0074] "Means for providing the generated meal menu" refers to a method or system for notifying and presenting the user with the meal menu generated through analysis.

[0075] "Means for providing cooking instructions" refers to a device or method that provides a user with specific cooking procedures and methods based on the provided meal menu.

[0076] "Means for obtaining feedback information and reflecting it in improving the meal menu" refers to a device or method for collecting user feedback and suggestions for improvement and improving the meal menu based on that feedback.

[0077] "Means for providing specific ingredient measurement information" refers to a system or method for indicating the exact amount of ingredients needed based on the generated meal menu.

[0078] "Video generation means" refers to a system or method for generating videos that visually show cooking methods and providing them to users.

[0079] The system of the present invention acquires a user's biometric data and food preference data, and then generates, provides, and improves an optimal meal menu based on that data. This system operates in cooperation with the user, terminal, and server.

[0080] First, the user launches the application using a device such as a smartphone or tablet. Within the application, the user enters their biometric data (weight, blood pressure, blood sugar level, etc.) and food preference data (favorite dishes, taste preferences, etc.). This clarifies the user's individual health condition and food preferences.

[0081] The device then sends the user's biometric and preference data to a cloud-based server, which then analyzes the received data using a generative AI model to generate a meal plan optimized for the user. This analysis includes algorithms that take into account the user's nutritional needs and preferences for better health.

[0082] As a concrete example, consider the case where a user inputs biometric data such as weight 70 kg, blood pressure 130 / 85, and blood sugar level 100 mg / dL, and selects "spicy curry rice" as their favorite dish. In this case, the server analyzes the user's data and generates a healthy spicy curry rice recipe. For example, it provides specific ingredients such as 200 g of chicken, 50 g of carrots, 1 tablespoon of turmeric, and 1 teaspoon of cumin, along with cooking instructions.

[0083] The server then sends the generated menu to the terminal. The terminal displays the received recipe information to the user. If necessary, it also generates a video of the cooking method to help the user visually understand the recipe. This video generation means is also executed on the server and provided to the terminal.

[0084] Furthermore, the device can also link with the user's IoT-enabled cooking appliances, enabling automated cooking, such as a smart oven heating food at the appropriate temperature and time.

[0085] After cooking is complete, users can taste the dish and provide feedback to the app on their impressions and suggestions for improvement. Once the user has entered their feedback, the information is sent back to the server, which analyzes the collected feedback and improves the generative AI model. This will enable the app to generate future meal menus that better suit the user's preferences and health.

[0086] Examples of prompts include:

[0087] "A user weighing 70 kg, with a blood pressure of 130 / 85 and a blood sugar level of 100 mg / dL has entered spicy curry rice as their favorite dish. Please generate a spicy curry rice recipe that suits the user's preferences while taking their health condition into consideration."

[0088] In this way, the system of the present invention provides a healthy and delicious meal menu based on the user's biometric data and preferences, promoting the user's health and improving the quality of their meals.

[0089] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0090] Step 1:

[0091] App launch

[0092] (Subject: User) The user launches an application on their smartphone or tablet. This action displays the login screen.

[0093] Input: User action (tap icon)

[0094] Output: Login screen displayed

[0095] Step 2:

[0096] Entering vital data

[0097] (Subject: User) The user enters their biometric data (weight, blood pressure, blood sugar level, etc.) into an input form within the application.

[0098] Input: Biometric data (e.g., weight 70 kg, blood pressure 130 / 85, blood sugar 100 mg / dL)

[0099] Output: Biometric data is stored within the application

[0100] Step 3:

[0101] Entering preference data

[0102] (Subject: User) The user enters their favorite dishes and taste preferences.

[0103] Input: Preference data (e.g., favorite dish "spicy curry rice")

[0104] Output: Preference data is saved in the application

[0105] Step 4:

[0106] Data transmission

[0107] (Subject: Device) The device sends the biometric and preference data entered by the user to a server in the cloud. The data is sent via Wi-Fi or mobile data.

[0108] Input: User-entered biometric and preference data

[0109] Output: Server receives data

[0110] Step 5:

[0111] Data reception

[0112] (Subject: Server) The server receives the biometric data and preference data sent from the terminal and stores them in a database.

[0113] Input: Submitted biometric and preference data

[0114] Output: User data stored in the database

[0115] Step 6:

[0116] Prompt generation

[0117] (Subject: Server) Based on the data received by the server, a prompt sentence is generated to be input into the generative AI model.

[0118] Input: Stored biometric and preference data

[0119] Output: Generated prompt text (e.g., "A user weighing 70 kg, with a blood pressure of 130 / 85 and a blood sugar level of 100 mg / dL has entered spicy curry rice as their favorite dish. Please generate a recipe for spicy curry rice that suits the user's preferences while taking their health condition into consideration.")

[0120] Step 7:

[0121] Input to AI model and analysis

[0122] (Subject: Server) The server inputs the prompt sentence into the generated AI model and performs analysis. As a result of the analysis, a meal menu that reflects the user's health condition and preferences is generated.

[0123] Input: Generated prompt text

[0124] Output: Meal menu as analysis result (e.g., 200g chicken, 50g carrots, 1 tablespoon turmeric, 1 teaspoon cumin)

[0125] Step 8:

[0126] Recipe Generation

[0127] (Subject: Server) The server converts the generated recipe into a concrete form (amount of ingredients, cooking steps).

[0128] Input: Meal menu as analysis result

[0129] Output: A specific recipe (e.g., 200g chicken, 50g carrots, 1 tablespoon turmeric, 1 teaspoon cumin, and cooking instructions)

[0130] Step 9:

[0131] Send recipe

[0132] (Subject: Server) The server sends the generated specific recipe to the terminal.

[0133] Input: A specific recipe

[0134] Output: Recipe data sent to the device

[0135] Step 10:

[0136] Recipe display

[0137] (Subject: Terminal) The terminal displays the received recipe to the user, allowing the user to check the recipe.

[0138] Input: Submitted recipe data

[0139] Output: The recipe displayed on the terminal screen

[0140] Step 11:

[0141] Cooking appliance linkage

[0142] (Subject: Device) The device sends instructions to IoT-enabled cooking appliances, such as setting a smart oven to the appropriate temperature and time.

[0143] Input: Cooking setting information based on recipe data

[0144] Output: Set cooking appliances

[0145] Step 12:

[0146] Feedback Input

[0147] (Subject: User) The user provides feedback to the app about their impressions and areas for improvement after cooking.

[0148] Input: Feedback information (e.g., "It was too spicy")

[0149] Output: Feedback information stored in the app

[0150] Step 13:

[0151] Send Feedback

[0152] (Subject: Terminal) The terminal sends the user's feedback to the server.

[0153] Input: Feedback information stored in the app

[0154] Output: Feedback information sent to the server

[0155] Step 14:

[0156] Feedback Analysis

[0157] (Subject: Server) The server analyzes the collected feedback and reflects it in improving the generative AI model.

[0158] Input: Submitted feedback information

[0159] Output: An updated generative AI model

[0160] In this way, the present invention provides a system that provides a healthy and delicious meal menu based on the user's biometric data and preferences, thereby promoting the user's health and improving the quality of their meals.

[0161] (Application example 1)

[0162] 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."

[0163] The present invention relates to a system that provides optimal food menus based on a user's individual health condition and taste preferences, and aims to provide an environment in which healthy and delicious food can be quickly enjoyed when ordering delivery of the food menu. Another objective is to improve user satisfaction by using feedback on the food menu.

[0164] 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.

[0165] In this invention, the server includes means for acquiring a user's vital data, means for acquiring food preference data, means for transmitting the acquired vital data and preference data to the cloud, means for analyzing the acquired data on the cloud server and generating an optimal food menu using a generative AI model, means for transmitting and providing the generated food menu to a terminal, means for placing a delivery order based on the generated food menu, means for providing cooking methods based on the provided food menu, and means for acquiring feedback information and reflecting it in improving the food menu. This makes it possible to order a food menu for delivery that matches the user's health condition and taste preferences, and to improve the menu based on subsequent feedback.

[0166] "Means for acquiring user's vital data" refers to a method or device for detecting, recording, and collecting data on the user's health status, such as weight, blood pressure, and blood sugar level.

[0167] "Means for acquiring food preference data" refers to a method or device for collecting information such as a user's preferred flavors and types of food, and records of food eaten in the past.

[0168] "Means for sending to the cloud" refers to a method or device for sending acquired data to a cloud server via the Internet.

[0169] A "server on the cloud" is a remote server on which computing resources are located that are accessible via the Internet.

[0170] "Means for analyzing acquired data and generating optimal dish menus using a generative AI model" refers to a method or device for analyzing collected user data using an algorithm or AI model to create optimal dish menus.

[0171] "Means for transmitting and providing to terminal" refers to a method or apparatus for transmitting the generated cooking menu to the end user's device and displaying it.

[0172] The "means for placing a delivery order" refers to a method or device for placing an order for food with a delivery company based on the created food menu.

[0173] The "means for providing cooking methods" refers to a method or device for presenting specific cooking procedures and methods to the user based on the generated cooking menu.

[0174] "Means for obtaining feedback information and reflecting it in improving the food menu" refers to a method or device for collecting user evaluations and suggestions for improvement, improving the generative AI model based on them, and using them to generate the next menu.

[0175] The system according to the present invention acquires and analyzes a user's vital data and food preference data, generates an optimal food menu based on the data, and places a delivery order. Specific embodiments will be described below.

[0176] First, the user launches the smartphone application and logs in to their account. Next, the user enters their vital data (e.g., weight, blood pressure, blood sugar level, etc.) and food preferences. This data is entered through the smartphone interface and sent to a server on the cloud.

[0177] Once the server receives this data, it analyzes it using a generative AI model built using machine learning libraries such as Python's TensorFlow and PyTorch to generate an optimal meal menu that matches the user's health status and preferences.

[0178] The generated menu includes specific ingredient measurements (e.g., 200g chicken, 50g carrots, 1 tablespoon turmeric, 1 teaspoon cumin) and cooking instructions. The server then sends the generated menu to the smartphone and serves it to the user.

[0179] When a user checks the menu and places a delivery order, the server manually or automatically places the order with the delivery company. For this purpose, an API is used to link the server and send the order information to the delivery system.

[0180] In addition, cooking instructions are provided in an easy-to-understand visual format and displayed as videos on a smartphone app, allowing users to easily and accurately follow the cooking steps.

[0181] After the food is delivered and the user samples it, they can provide feedback through the app. This feedback is then sent back to the cloud server and used to improve the AI ​​model. This allows the next time a menu is generated, it will be tailored to the user's preferences and health status.

[0182] As a concrete example, consider the case where a user inputs vital data such as weight 70 kg, blood pressure 130 / 85, and blood sugar level 100 mg / dL, and selects "spicy curry rice" as their favorite dish. The server generates a spicy curry rice recipe that suits the user's preferences, taking into account the user's weight and blood pressure and selecting ingredients with the appropriate nutrients. For example, it provides specific ingredients such as 200 g of chicken, 50 g of carrots, 1 tablespoon of turmeric, and 1 teaspoon of cumin, along with cooking instructions.

[0183] An example prompt is:

[0184] User weight: 70kg

[0185] Blood pressure: 130 / 85

[0186] Blood glucose level: 100 mg / dL

[0187] Favorite food: Spicy curry rice

[0188] Nutrients provided: High in protein, low in fat

[0189] Generate the appropriate food menu:

[0190] In this way, the system of the present invention can help users maintain their health and improve their satisfaction by generating and providing optimal meal menus based on the user's health condition and food preferences, and then delivering those meals.

[0191] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0192] Step 1:

[0193] The user starts the smartphone application and inputs their vital data (e.g., weight, blood pressure, blood sugar level, etc.) and food preference data. The vital data and preference data are input and recorded on the device.

[0194] Input: vital data, food preference data

[0195] Output: Dataset to send to cloud server

[0196] Step 2:

[0197] The device transmits the vital data and food preference data entered by the user to a cloud server via a secure communication protocol (e.g., HTTPS).

[0198] Input: Dataset obtained from user

[0199] Output: Data packets passed to the cloud server

[0200] Step 3:

[0201] The server analyzes the received data and uses a generative AI model (using TensorFlow or PyTorch, for example) to generate an optimal meal menu based on the user's health status and preferences.

[0202] Input: Dataset stored on a cloud server

[0203] Output: Optimal recipe (including specific ingredients and cooking methods)

[0204] Step 4:

[0205] The generated menu is sent from the server to the device, where it is displayed and provided to the user in a format that can be viewed on the device.

[0206] Input: Generated food menu

[0207] Output: A menu of dishes that the user can view on their device.

[0208] Step 5:

[0209] Users can check the menu and place a delivery order within the app. The order information is sent to the server, which then automatically sends it to the partner delivery company.

[0210] Input: User's order request

[0211] Output: A delivery order request is sent to the delivery company.

[0212] Step 6:

[0213] The user receives the food, samples it, and then provides feedback through the app.

[0214] Input: User feedback after tasting

[0215] Output: Feedback data sent to the cloud server

[0216] Step 7:

[0217] The server analyzes the feedback data and reflects it in the generative AI model, which improves the accuracy of future cooking menus.

[0218] Input: User feedback data

[0219] Output: An improved generative AI model

[0220] Thus, the present invention is a system that includes a series of steps to provide optimal food menus based on the user's health condition and food preference data, enable delivery orders, and improve the accuracy of the generative AI model based on feedback.

[0221] 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.

[0222] The system of the present invention acquires a user's vital data, food preference data, and user emotions, and generates, provides, and improves healthy and delicious food menus based on this data. This system operates in cooperation with the user, terminal, and server.

[0223] First, the user launches the application and inputs their personal vital data (e.g., weight, blood pressure, blood sugar level, etc.), their favorite dishes, memorable dishes they have eaten in the past, and taste preferences. In addition, an emotion engine is activated to obtain the user's emotional data. This emotion engine analyzes the user's facial expressions and voice to determine their current emotional state.

[0224] The device sends the vital data, preference data, and emotional data entered by the user to a server on the cloud. The server uses the received data to generate an optimal meal menu that matches the user's health condition and preferences. This process is performed using a generative AI model. By taking into account the nutrients necessary for health promotion and the user's taste preferences, and also reflecting the user's current emotional state, the system proposes a meal menu that is emotionally satisfying.

[0225] The server then sends the generated cooking menu to the device. The cooking menu includes specific ingredient measurements (grams, tablespoons, teaspoons) and detailed cooking instructions. If necessary, the server can also generate cooking instructions as videos and provide them to the device, making it easier for users to understand visually.

[0226] The device also has the ability to link with the user's IoT-enabled cooking appliances, allowing them to automatically set cooking appliances, such as a smart oven to heat at the appropriate temperature and time.

[0227] After cooking is complete, the user tastes the dish and provides feedback to the app on their impressions and suggestions for improvement. Once the user enters their feedback, the information is sent back to the server. The server analyzes the collected feedback and emotional data and updates the generative AI model, which is then reflected in future menu suggestions. By taking the user's emotional state into account, it is possible to provide a more fulfilling dining experience.

[0228] As a specific example, consider the case where a user inputs vital data such as weight 70 kg, blood pressure 130 / 85, and blood sugar level 100 mg / dL, and selects "spicy curry rice" as their favorite dish. Furthermore, suppose the user's emotion engine analyzes the user as "feeling stressed." The server generates a menu based on this vital data, preference data, and emotion data. In this case, the server may suggest relaxing herbal tea in addition to spicy curry rice to reduce the user's stress. For example, the server may provide specific ingredients such as 200 g of chicken, 50 g of carrots, 1 tablespoon of turmeric, and 1 teaspoon of cumin, along with cooking instructions. Additional feedback and emotion data is then collected and reflected in the next menu suggestion.

[0229] In this way, the system of the present invention promotes the user's health and improves the quality of the cooking experience by providing healthy and satisfying cooking menus based on the user's vital data, cooking preferences, and emotional data.

[0230] The processing flow will be explained below.

[0231] Step 1:

[0232] A user launches the application and inputs their personal vital data (e.g., weight, blood pressure, blood sugar level, etc.). The user also inputs data about their favorite dishes, dishes they have eaten in the past, and taste preferences.

[0233] Step 2:

[0234] The user uses a camera and microphone to provide facial expression and voice data to the emotion engine, which then analyzes this data to recognize the user's current emotional state (e.g., feeling stressed, relaxed, etc.).

[0235] Step 3:

[0236] The device transmits vital data, preference data, and emotional data input by the user to a server on the cloud.

[0237] Step 4:

[0238] The server analyzes the received data and generates an optimal meal menu based on the user's health condition, preferences, and emotional state. The generative AI model selects a meal menu that reflects the nutrients necessary for health promotion, the user's taste preferences, and emotional satisfaction.

[0239] Step 5:

[0240] The server generates a cooking menu and sends it to the device, which includes the specific ingredient measurements (in grams, tablespoons, or teaspoons) and detailed cooking instructions.

[0241] Step 6:

[0242] The terminal displays the received menu and cooking instructions to the user. The server also generates a video of the cooking instructions to make them easier to understand visually and provides it to the terminal.

[0243] Step 7:

[0244] The device cooks food according to the menu provided by the user. When using IoT-enabled cooking appliances, the device automatically connects to the appliance and sets the appropriate temperature and time.

[0245] Step 8:

[0246] Users taste the food and enter their feedback about its taste and health effects into the app, such as "I wish it was a little spicier" or "This dish helped me relax."

[0247] Step 9:

[0248] The device sends user feedback and emotional data to a server on the cloud.

[0249] Step 10:

[0250] The server analyzes the collected feedback and emotional data and updates the generative AI model, which then reflects the feedback and emotional data in the next menu suggestion, providing a more optimized menu.

[0251] In this way, the user, terminal, and server work together at each step to create a system that provides healthy, emotionally satisfying meals to the user.

[0252] Example 2

[0253] 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."

[0254] Conventional food recommendation systems have difficulty providing food menus that take into account the user's health condition and preferences, and do not provide food recommendations that reflect the user's emotional state. This makes it difficult for users to find healthy and satisfying food menus, and there is a lack of suggestions that meet individual needs. Furthermore, feedback information is not fully utilized, and system improvements are not being made effectively.

[0255] 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.

[0256] In this invention, the server includes a means for acquiring biometric data of the user, a means for acquiring preference data, and a means for acquiring emotional data of the user, thereby enabling the server to propose optimal cooking menus that reflect the user's health condition, preferences, and emotional state.

[0257] "User's biometric data" refers to numerical data that indicates the user's health condition, such as weight, blood pressure, and blood sugar level.

[0258] "Preference data" is information about the user's food preferences, such as favorite dishes, memorable dishes they have eaten in the past, and taste preferences.

[0259] "User emotional data" is data that indicates the user's current emotional state, obtained by analyzing the user's facial expressions and voice.

[0260] A "generative AI model" is an algorithm that generates optimal cooking menus based on a user's biometric data, preference data, and emotional data.

[0261] A "prompt sentence" is an input sentence that gives instructions to the generative AI model for generating a menu.

[0262] The "means for providing cooking instructions" is a method for presenting specific cooking steps to the user based on the generated cooking menu.

[0263] "Feedback information" refers to information about users' impressions of the food after tasting it and areas for improvement.

[0264] The "video generation means" is a method for creating a video that visually presents cooking methods based on the generated cooking menu.

[0265] The system of the present invention acquires a user's biometric data, preference data, and emotional data, and then generates, provides, and improves healthy and delicious food menus based on this data. This system operates in cooperation with the user, terminal, and server.

[0266] First, the user launches an application on a device such as a smartphone or tablet. This application runs on a mobile OS such as iOS or Android. The user then enters their personal biometric data (e.g., weight, blood pressure, blood sugar level, etc.). This data can be entered manually or automatically acquired from a Bluetooth-connected wearable device (e.g., a smartwatch). Next, the user enters preference data, such as their favorite dishes, dishes they have eaten in the past, and taste preferences.

[0267] Additionally, the emotion engine operates using the device's built-in camera and microphone. The emotion engine analyzes the user's emotional state from their facial expressions and voice, capturing this as emotion data. For example, it may determine that the user is "feeling stressed."

[0268] The device sends the acquired biometric data, preference data, and emotional data to a server on the cloud. Data is sent using the HTTPS protocol to ensure secure communication. The server analyzes the received data using a generative AI model (e.g., GPT-4). The generative AI model generates the optimal dish menu for the user based on the prompt text. An example of a prompt text is, "Please generate the optimal dish menu if the user is feeling stressed, has a weight of 70 kg, a blood pressure of 130 / 85, and a blood sugar level of 100 mg / dL, and prefers spicy curry rice."

[0269] The generative AI model considers the user's taste preferences and nutrients necessary for health promotion, and also reflects the user's current emotional state to suggest emotionally satisfying dishes. For example, it can suggest a relaxing herbal tea in addition to spicy curry rice. Specifically, it provides measurements of ingredients such as 200g of chicken, 50g of carrots, 1 tablespoon of turmeric, and 1 teaspoon of cumin, along with cooking instructions.

[0270] The server sends the generated menu to the device. The data includes specific ingredient measurements (e.g., grams, tablespoons, teaspoons) and detailed cooking instructions. If necessary, the server can also generate cooking instructions as videos and provide them to the device, making it easier for users to understand visually.

[0271] The device also has the ability to link with the user's IoT-enabled kitchen appliances, allowing them to automatically set their cooking appliances, for example, a smart oven to heat at the appropriate temperature and time.

[0272] After cooking is complete, the user tastes the dish and provides feedback to the app on their impressions and suggestions for improvement. Once the user enters their feedback, the information is sent back to the server. The server analyzes the collected feedback and emotional data and updates the generative AI model, which is then reflected in future menu suggestions. By taking the user's emotional state into account, it is possible to provide a more fulfilling dining experience.

[0273] In this way, the system of the present invention promotes the user's health and improves the quality of the cooking experience by providing healthy and satisfying cooking menus based on the user's biometric data, cooking preferences, and emotional data.

[0274] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0275] Step 1:

[0276] Data Entry

[0277] Users launch a dedicated application on their smartphone or tablet, which runs on a mobile operating system such as iOS or Android.

[0278] Users manually enter their personal biometric data (e.g., weight, blood pressure, blood glucose level, etc.) or it is automatically obtained from a Bluetooth-connected wearable device (e.g., a smartwatch).

[0279] The user also inputs preference data such as favorite dishes, memorable dishes they have eaten in the past, and taste preferences.

[0280] The emotion engine operates using the device's built-in camera and microphone to analyze the user's current emotional state from their facial expressions and voice.

[0281] How it works: The camera captures the user's facial expressions and the microphone records the user's voice. These data are processed in real time and output as emotional data, such as "I feel stressed."

[0282] Step 2:

[0283] Data transmission

[0284] The device collects biometric data, preference data, and emotional data and sends it to a cloud server. This data is generally sent in JSON format and is securely transmitted using the HTTPS protocol.

[0285] Specific operation: The device collects each piece of data, compiles it into a single JSON object, and sends an HTTPS request.

[0286] Step 3:

[0287] Data analysis and menu generation

[0288] The server analyzes the received biometric data, preference data, and emotion data.

[0289] A generative AI model (e.g., GPT-4) analyzes the prompt text based on the data and generates the optimal cooking menu.

[0290] Specific prompt: "Generate the best meal plan for the user if they are stressed, weigh 70 kg, have a blood pressure of 130 / 85, and have a blood sugar level of 100 mg / dL, and prefer spicy curry rice."

[0291] How it works: The generative AI model calculates necessary nutrients from biometric data, selects the type of food from preference data, and generates menus that take into account psychological effects from emotional data. For example, to reduce stress, it might suggest relaxing herbal tea in addition to spicy curry rice.

[0292] Step 4:

[0293] Menu offerings

[0294] The server sends the generated menu to the device, including the measurements of specific ingredients (e.g., 200g chicken, 50g carrots, 1 tablespoon turmeric, 1 teaspoon cumin) and detailed cooking instructions.

[0295] Specific operation: The server encodes the generated menu in JSON format and returns it to the device as an HTTP response.

[0296] Step 5:

[0297] IoT-enabled kitchen appliance integration

[0298] The device connects to the user's IoT-enabled cooking appliances (e.g., smart ovens), allowing the appliances to automatically cook food at the appropriate settings (e.g., temperature and time).

[0299] How it works: The device analyzes the cooking recipe and calls the API of the corresponding appliance to send the settings. For example, it sends a command to a smart oven to heat at 180 degrees for 30 minutes.

[0300] Step 6:

[0301] Feedback and Model Updates

[0302] Users can taste the food and provide feedback to the app on their impressions and suggestions for improvement, either as star ratings or text comments.

[0303] The device sends the feedback information to a server on the cloud.

[0304] The server analyzes the collected feedback and emotional data and updates the generative AI model, which is then reflected in future menu suggestions.

[0305] What it does: The server saves the new feedback data in a database and updates the learning algorithm of the generative AI model, which then uses the new data for the next proposal.

[0306] (Application example 2)

[0307] 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."

[0308] Conventional food menu suggestion systems generally rely on a user's vital data and preference data, but because they do not take emotional data into account, it is difficult to suggest optimal food menus based on the user's psychological state. Furthermore, they lack support for actually cooking the suggested dishes, resulting in low user convenience. Another problem is that suggested dishes cannot be tried immediately. To address these issues, a system is needed that can suggest food menus based on the user's psychological state and actually deliver them, providing a healthier and more satisfying dining experience.

[0309] 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.

[0310] In this invention, the server includes means for acquiring vital data of the user, means for acquiring preference data of the user, means for acquiring emotional data of the user, means for analyzing the acquired vital data, preference data, and emotional data to generate an optimal dish menu, means for providing the generated dish menu, means for providing cooking methods based on the provided dish menu, means for acquiring feedback information and reflecting it in improving the dish menu, and means for delivering cooked dishes. This makes it possible to propose an optimal dish menu that takes into consideration both the user's health and psychological state, and furthermore, by promptly delivering and providing the dish, a more satisfying dining experience can be realized.

[0311] "User vital data" refers to physiological data that indicates the user's health status, such as weight, blood pressure, and blood sugar level.

[0312] "Cooking preference data" refers to data about the user's favorite dishes, memorable dishes they have eaten in the past, and their taste preferences.

[0313] "User emotional data" is data that indicates the user's current emotional state, analyzed from their facial expressions and voice.

[0314] The "means for generating a cooking menu" refers to a technical means for analyzing a user's vital data, preference data, and emotional data to generate an optimal cooking menu.

[0315] "Means for providing a food menu" refers to means for displaying and notifying the user of the generated food menu.

[0316] The "means for providing cooking instructions" is a means for providing specific ingredient measurement information and detailed cooking instructions based on the generated cooking menu.

[0317] The "means for obtaining feedback information" refers to a means for obtaining feedback information such as user's impressions and suggestions for improvement regarding the provided food menu.

[0318] "Means for reflecting improvements to the food menu" refers to the means for improving and optimizing the food menu for future meals based on the obtained feedback information.

[0319] The "means for delivering cooked food" refers to a means for delivering food cooked based on the generated cooking menu to the user.

[0320] The system of the present invention acquires a user's vital data, food preference data, and emotional data, and uses this data to generate, provide, and improve healthy and satisfying food menus, and delivers the cooked meals. This system operates in cooperation with the user, terminal, and server.

[0321] First, the user launches the application using a device (e.g., a smartphone) and inputs their personal vital data (weight, blood pressure, blood sugar level, etc.). Next, they input data about the user's favorite dishes, memorable dishes they have eaten in the past, and taste preferences. Furthermore, to obtain emotional data, the emotion engine analyzes emotions from facial expressions and voice.

[0322] The device sends the vital data, preference data, and emotional data entered by the user to a server on the cloud. The server uses the acquired data to generate an optimal meal menu that matches the user's health condition and preferences. This generation process is carried out using a generative AI model (e.g., OpenAI GPT-4). By taking into account the nutrients necessary for health promotion and the user's taste preferences, and also reflecting the user's current emotional state, the system proposes a meal menu that is emotionally satisfying.

[0323] The server sends the generated cooking menu to the device. The cooking menu includes specific ingredient measurements (grams, tablespoons, teaspoons) and detailed cooking instructions. If necessary, the server can also generate cooking instructions as videos and provide them to the device, making it easier for users to understand visually.

[0324] The device also has the ability to link with the user's IoT-enabled cooking appliances, allowing the appliance to automatically set its temperature and time, for example, so that a smart oven can heat food at the appropriate temperature and time.

[0325] After cooking is complete, the user tastes the dish and provides feedback to the app on their impressions and areas for improvement. Once the user enters their feedback, the information is sent back to the server. The server analyzes the collected feedback and emotional data and updates the generative AI model. This will be reflected in future menu suggestions, enabling the app to provide a more satisfying dining experience.

[0326] Furthermore, the system also provides a means for delivering cooked dishes based on the generated menu, allowing users to immediately try the suggested dishes, improving convenience.

[0327] Specific examples

[0328] For example, consider a case where a user inputs vital data such as weight 70 kg, blood pressure 130 / 85 mmHg, and blood sugar level 100 mg / dL, and selects "spicy curry rice" as their favorite dish. If the emotion engine analyzes the user as "feeling stressed," the server will suggest relaxing herbal tea and spicy curry rice. The user selects this menu, and the cooked food is delivered through the ordering process.

[0329] Prompt Sentence Examples

[0330] "The user's weight is 70 kg, blood pressure is 130 / 85 mmHg, blood sugar level is 100 mg / dL, favorite food is spicy curry rice, and they are feeling stressed. Based on this information, please suggest a meal menu that will have a relaxing effect."

[0331] ---

[0332] The system aims to balance user health and food satisfaction, and by utilizing a variety of data, it provides a more personalized dining experience.

[0333] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0334] Step 1:

[0335] The user starts the application on the device and inputs vital data. Specifically, the user enters health data such as weight, blood pressure, and blood sugar level into the device through an input form. The input at this point is the user's vital data.

[0336] Step 2:

[0337] The user inputs data about their favorite dishes, dishes they have eaten in the past, and taste preferences into the terminal. For example, spicy curry rice is input as a favorite dish. This data is acquired as the user's food preference data.

[0338] Step 3:

[0339] The emotion engine operates and acquires emotion data from the user's facial expressions and voice. The device uses a camera and microphone to capture the user's facial expressions and voice, and the emotion engine analyzes them to acquire the user's current emotional state. This data is the user's emotion data.

[0340] Step 4:

[0341] The device sends the acquired vital data, food preference data, and emotional data to a server on the cloud. The input here is a collection of each data, and the device then sends it to the cloud.

[0342] Step 5:

[0343] The server analyzes the received data and generates an optimal cooking menu using a generative AI model. The server generates a cooking menu that takes into account the nutrients necessary for health promotion and the user's preferences based on the user's vital data, food preference data, and emotional data. This process uses a generative AI model.

[0344] Step 6:

[0345] The server sends the generated menu to the terminal, which then visually displays it to the user, including specific ingredient measurements and detailed cooking instructions.

[0346] Step 7:

[0347] The device generates a video of the cooking method sent from the server as needed and provides it to the user, making it easier for the user to visually understand the cooking procedure.

[0348] Step 8:

[0349] The device connects to IoT-enabled cooking appliances and automatically sets the appropriate cooking temperature and time, allowing users to cook easily.

[0350] Step 9:

[0351] After cooking is complete, the user tastes the dish and provides feedback on their impressions and suggestions for improvement to the device, which then records the feedback as user input.

[0352] Step 10:

[0353] The device then sends the collected feedback information and emotion data back to the server, which uses it to update the generative AI model and reflect it in future menu suggestions.

[0354] Step 11:

[0355] The server delivers cooked dishes based on the cooking menu it generates, allowing users to immediately try the suggested dishes. This operation provides convenience to users.

[0356] 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.

[0357] 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.

[0358] 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.

[0359] [Second embodiment]

[0360] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0361] 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.

[0362] 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).

[0363] 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.

[0364] 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.

[0365] 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).

[0366] 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.

[0367] 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.

[0368] 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.

[0369] 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.

[0370] 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.

[0371] 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."

[0372] The system of the present invention acquires a user's vital data and food preference data, and based on that data, generates, provides, and improves healthy and delicious food menus. This system operates in cooperation with the user, terminal, and server.

[0373] First, the user launches the application and enters their vital data (e.g., weight, blood pressure, blood sugar level, etc.) into the app. Then, they also enter data about their favorite dishes, memorable dishes they have eaten in the past, and taste preferences. This allows the app to clarify the user's individual health condition and food preferences.

[0374] The terminal (smartphone, tablet, etc.) sends vital data and preference data entered by the user to a server on the cloud. The server generates the optimal meal menu for the user based on the received data. This process is carried out by an AI model, which selects a meal menu that matches the nutrients necessary for health promotion and the user's preferences.

[0375] The server then sends the generated cooking menu to the device. The cooking menu includes specific ingredient measurements (in grams or tablespoons / teaspoons) and cooking instructions. If necessary, the server can also generate a video of the cooking instructions and provide it to the device, helping users to understand the menu visually.

[0376] The device also has the ability to link with the user's IoT-enabled kitchen appliances, allowing them to automatically set their cooking appliances, for example, a smart oven to heat at the appropriate temperature and time.

[0377] After cooking is complete, the user tastes the dish and provides feedback to the app on their impressions and suggestions for improvement. Once the user enters their feedback, the information is sent back to the server. The server analyzes the collected feedback and improves the AI ​​model. This will enable the app to generate future meal menus that better suit the user's preferences and health.

[0378] As a concrete example, consider the case where a user inputs vital data such as weight 70 kg, blood pressure 130 / 85, and blood sugar level 100 mg / dL, and selects "spicy curry rice" as their favorite dish. The server generates a spicy curry rice recipe that suits the user's preferences while taking into account weight and blood pressure and selecting ingredients with the appropriate nutrients. For example, it provides specific ingredients such as 200 g of chicken, 50 g of carrots, 1 tablespoon of turmeric, and 1 teaspoon of cumin, along with cooking instructions. The server then receives feedback to adjust the spiciness and reflects this in the next recipe generation.

[0379] In this way, the system of the present invention provides healthy and delicious meal menus based on the user's vital data and preferences, promoting the user's health and improving the quality of the food they eat.

[0380] The processing flow will be explained below.

[0381] Step 1:

[0382] A user launches the application and inputs their personal vital data (e.g., weight, blood pressure, blood sugar level, etc.) The user also inputs data about their favorite dishes, memories of dishes they have eaten in the past, and taste preferences.

[0383] Step 2:

[0384] The device receives vital data and preference data entered by the user and sends it to a server on the cloud.

[0385] Step 3:

[0386] The server analyzes the received vital data and preference data and generates an optimal menu based on the user's health condition and preferences. The generative AI model takes into account the nutrients necessary for health promotion and the user's taste preferences.

[0387] Step 4:

[0388] The server generates a cooking menu and sends it to the device, which includes specific ingredient measurements (in grams, tablespoons, or teaspoons) and detailed cooking instructions.

[0389] Step 5:

[0390] The terminal displays the received menu and cooking instructions to the user, and also provides the cooking instructions generated by the server as a video to the terminal for easy visual understanding.

[0391] Step 6:

[0392] The device cooks food according to the menu provided by the user. When using IoT-enabled cooking appliances, the device will link with the appliance and automatically set the appropriate temperature and time.

[0393] Step 7:

[0394] Users taste the food and enter their feedback about the taste and health effects into the app, such as "I wish it was a little spicier."

[0395] Step 8:

[0396] The device sends the user's feedback to a server on the cloud.

[0397] Step 9:

[0398] The server analyzes the collected feedback and updates the generative AI model, which then reflects the feedback in the next menu suggestions, providing a menu that is more optimized in terms of both taste and health.

[0399] In this way, the user, terminal, and server work together at each step to create a system that provides healthy and delicious meals to users.

[0400] Example 1

[0401] 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."

[0402] In modern society, it is extremely important to provide meal menus tailored to each individual's health condition and food preferences. However, providing such menus generally requires specialized knowledge, and there are no systems that are easily accessible to many people. Furthermore, there is a lack of mechanisms for quickly responding to changes in the user's health condition and improving menus based on feedback. As a result, it is difficult to continuously provide meals that promote health and match preferences.

[0403] 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.

[0404] In this invention, the server includes a means for acquiring biometric data of the user, a means for acquiring food preference data, and a means for analyzing the acquired biometric data and preference data to generate an optimal meal menu, thereby providing an optimal meal menu based on the user's health condition and preferences, and making it possible to continuously improve the menu based on feedback.

[0405] "User Biometric Data" means objective medical measurements that indicate the user's health, such as weight, blood pressure, or blood sugar level.

[0406] "Food preference data" is information that indicates a user's personal food preferences, such as the type of food they like, the strength of the flavor, and the spiciness of the food.

[0407] "Means for analyzing acquired biometric data and preference data to generate an optimal meal menu" refers to a process or device that analyzes a user's biometric data and preference data and creates a nutritionally balanced meal menu appropriate for the user based on that data.

[0408] "Means for providing the generated meal menu" refers to a method or system for notifying and presenting the user with the meal menu generated through analysis.

[0409] "Means for providing cooking instructions" refers to a device or method that provides a user with specific cooking procedures and methods based on the provided meal menu.

[0410] "Means for obtaining feedback information and reflecting it in improving the meal menu" refers to a device or method for collecting user feedback and suggestions for improvement and improving the meal menu based on that feedback.

[0411] "Means for providing specific ingredient measurement information" refers to a system or method for indicating the exact amount of ingredients needed based on the generated meal menu.

[0412] "Video generation means" refers to a system or method for generating videos that visually show cooking methods and providing them to users.

[0413] The system of the present invention acquires a user's biometric data and food preference data, and then generates, provides, and improves an optimal meal menu based on that data. This system operates in cooperation with the user, terminal, and server.

[0414] First, the user launches the application using a device such as a smartphone or tablet. Within the application, the user enters their biometric data (weight, blood pressure, blood sugar level, etc.) and food preference data (favorite dishes, taste preferences, etc.). This clarifies the user's individual health condition and food preferences.

[0415] The device then sends the user's biometric and preference data to a cloud-based server, which then analyzes the received data using a generative AI model to generate a meal plan optimized for the user. This analysis includes algorithms that take into account the user's nutritional needs and preferences for better health.

[0416] As a concrete example, consider the case where a user inputs biometric data such as weight 70 kg, blood pressure 130 / 85, and blood sugar level 100 mg / dL, and selects "spicy curry rice" as their favorite dish. In this case, the server analyzes the user's data and generates a healthy spicy curry rice recipe. For example, it provides specific ingredients such as 200 g of chicken, 50 g of carrots, 1 tablespoon of turmeric, and 1 teaspoon of cumin, along with cooking instructions.

[0417] The server then sends the generated menu to the terminal. The terminal displays the received recipe information to the user. If necessary, it also generates a video of the cooking method to help the user visually understand the recipe. This video generation means is also executed on the server and provided to the terminal.

[0418] Furthermore, the device can also link with the user's IoT-enabled cooking appliances, enabling automated cooking, such as a smart oven heating food at the appropriate temperature and time.

[0419] After cooking is complete, users can taste the dish and provide feedback to the app on their impressions and suggestions for improvement. Once the user has entered their feedback, the information is sent back to the server, which analyzes the collected feedback and improves the generative AI model. This will enable the app to generate future meal menus that better suit the user's preferences and health.

[0420] Examples of prompts include:

[0421] "A user weighing 70 kg, with a blood pressure of 130 / 85 and a blood sugar level of 100 mg / dL has entered spicy curry rice as their favorite dish. Please generate a spicy curry rice recipe that suits the user's preferences while taking their health condition into consideration."

[0422] In this way, the system of the present invention provides a healthy and delicious meal menu based on the user's biometric data and preferences, promoting the user's health and improving the quality of their meals.

[0423] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0424] Step 1:

[0425] App launch

[0426] (Subject: User) The user launches an application on their smartphone or tablet. This action displays the login screen.

[0427] Input: User action (tap icon)

[0428] Output: Login screen displayed

[0429] Step 2:

[0430] Entering vital data

[0431] (Subject: User) The user enters their biometric data (weight, blood pressure, blood sugar level, etc.) into an input form within the application.

[0432] Input: Biometric data (e.g., weight 70 kg, blood pressure 130 / 85, blood sugar 100 mg / dL)

[0433] Output: Biometric data is stored within the application

[0434] Step 3:

[0435] Entering preference data

[0436] (Subject: User) The user enters their favorite dishes and taste preferences.

[0437] Input: Preference data (e.g., favorite dish "spicy curry rice")

[0438] Output: Preference data is saved in the application

[0439] Step 4:

[0440] Data transmission

[0441] (Subject: Device) The device sends the biometric and preference data entered by the user to a server in the cloud. The data is sent via Wi-Fi or mobile data.

[0442] Input: User-entered biometric and preference data

[0443] Output: Server receives data

[0444] Step 5:

[0445] Data reception

[0446] (Subject: Server) The server receives the biometric data and preference data sent from the terminal and stores them in a database.

[0447] Input: Submitted biometric and preference data

[0448] Output: User data stored in the database

[0449] Step 6:

[0450] Prompt generation

[0451] (Subject: Server) Based on the data received by the server, a prompt sentence is generated to be input into the generative AI model.

[0452] Input: Stored biometric and preference data

[0453] Output: Generated prompt text (e.g., "A user weighing 70 kg, with a blood pressure of 130 / 85 and a blood sugar level of 100 mg / dL has entered spicy curry rice as their favorite dish. Please generate a recipe for spicy curry rice that suits the user's preferences while taking their health condition into consideration.")

[0454] Step 7:

[0455] Input to AI model and analysis

[0456] (Subject: Server) The server inputs the prompt sentence into the generated AI model and performs analysis. As a result of the analysis, a meal menu that reflects the user's health condition and preferences is generated.

[0457] Input: Generated prompt text

[0458] Output: Meal menu as analysis result (e.g., 200g chicken, 50g carrots, 1 tablespoon turmeric, 1 teaspoon cumin)

[0459] Step 8:

[0460] Recipe Generation

[0461] (Subject: Server) The server converts the generated recipe into a concrete form (amount of ingredients, cooking steps).

[0462] Input: Meal menu as analysis result

[0463] Output: A specific recipe (e.g., 200g chicken, 50g carrots, 1 tablespoon turmeric, 1 teaspoon cumin, and cooking instructions)

[0464] Step 9:

[0465] Send recipe

[0466] (Subject: Server) The server sends the generated specific recipe to the terminal.

[0467] Input: A specific recipe

[0468] Output: Recipe data sent to the device

[0469] Step 10:

[0470] Recipe display

[0471] (Subject: Terminal) The terminal displays the received recipe to the user, allowing the user to check the recipe.

[0472] Input: Submitted recipe data

[0473] Output: The recipe displayed on the terminal screen

[0474] Step 11:

[0475] Cooking appliance linkage

[0476] (Subject: Device) The device sends instructions to IoT-enabled cooking appliances, such as setting a smart oven to the appropriate temperature and time.

[0477] Input: Cooking setting information based on recipe data

[0478] Output: Set cooking appliances

[0479] Step 12:

[0480] Feedback Input

[0481] (Subject: User) The user provides feedback to the app about their impressions and areas for improvement after cooking.

[0482] Input: Feedback information (e.g., "It was too spicy")

[0483] Output: Feedback information stored in the app

[0484] Step 13:

[0485] Send Feedback

[0486] (Subject: Terminal) The terminal sends the user's feedback to the server.

[0487] Input: Feedback information stored in the app

[0488] Output: Feedback information sent to the server

[0489] Step 14:

[0490] Feedback Analysis

[0491] (Subject: Server) The server analyzes the collected feedback and reflects it in improving the generative AI model.

[0492] Input: Submitted feedback information

[0493] Output: An updated generative AI model

[0494] In this way, the present invention provides a system that provides a healthy and delicious meal menu based on the user's biometric data and preferences, thereby promoting the user's health and improving the quality of their meals.

[0495] (Application example 1)

[0496] 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."

[0497] The present invention relates to a system that provides optimal food menus based on a user's individual health condition and taste preferences, and aims to provide an environment in which healthy and delicious food can be quickly enjoyed when ordering delivery of the food menu. Another objective is to improve user satisfaction by using feedback on the food menu.

[0498] 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.

[0499] In this invention, the server includes means for acquiring a user's vital data, means for acquiring food preference data, means for transmitting the acquired vital data and preference data to the cloud, means for analyzing the acquired data on the cloud server and generating an optimal food menu using a generative AI model, means for transmitting and providing the generated food menu to a terminal, means for placing a delivery order based on the generated food menu, means for providing cooking methods based on the provided food menu, and means for acquiring feedback information and reflecting it in improving the food menu. This makes it possible to order a food menu for delivery that matches the user's health condition and taste preferences, and to improve the menu based on subsequent feedback.

[0500] "Means for acquiring user's vital data" refers to a method or device for detecting, recording, and collecting data on the user's health status, such as weight, blood pressure, and blood sugar level.

[0501] "Means for acquiring food preference data" refers to a method or device for collecting information such as a user's preferred flavors and types of food, and records of food eaten in the past.

[0502] "Means for sending to the cloud" refers to a method or device for sending acquired data to a cloud server via the Internet.

[0503] A "server on the cloud" is a remote server on which computing resources are located that are accessible via the Internet.

[0504] "Means for analyzing acquired data and generating optimal dish menus using a generative AI model" refers to a method or device for analyzing collected user data using an algorithm or AI model to create optimal dish menus.

[0505] "Means for transmitting and providing to terminal" refers to a method or apparatus for transmitting the generated cooking menu to the end user's device and displaying it.

[0506] The "means for placing a delivery order" refers to a method or device for placing an order for food with a delivery company based on the created food menu.

[0507] The "means for providing cooking methods" refers to a method or device for presenting specific cooking procedures and methods to the user based on the generated cooking menu.

[0508] "Means for obtaining feedback information and reflecting it in improving the food menu" refers to a method or device for collecting user evaluations and suggestions for improvement, improving the generative AI model based on them, and using them to generate the next menu.

[0509] The system according to the present invention acquires and analyzes a user's vital data and food preference data, generates an optimal food menu based on the data, and places a delivery order. Specific embodiments will be described below.

[0510] First, the user launches the smartphone application and logs in to their account. Next, the user enters their vital data (e.g., weight, blood pressure, blood sugar level, etc.) and food preferences. This data is entered through the smartphone interface and sent to a server on the cloud.

[0511] Once the server receives this data, it analyzes it using a generative AI model built using machine learning libraries such as Python's TensorFlow and PyTorch to generate an optimal meal menu that matches the user's health status and preferences.

[0512] The generated menu includes specific ingredient measurements (e.g., 200g chicken, 50g carrots, 1 tablespoon turmeric, 1 teaspoon cumin) and cooking instructions. The server then sends the generated menu to the smartphone and serves it to the user.

[0513] When a user checks the menu and places a delivery order, the server manually or automatically places the order with the delivery company. For this purpose, an API is used to link the server and send the order information to the delivery system.

[0514] In addition, cooking instructions are provided in an easy-to-understand visual format and displayed as videos on a smartphone app, allowing users to easily and accurately follow the cooking steps.

[0515] After the food is delivered and the user samples it, they can provide feedback through the app. This feedback is then sent back to the cloud server and used to improve the AI ​​model. This allows the next time a menu is generated, it will be tailored to the user's preferences and health status.

[0516] As a concrete example, consider the case where a user inputs vital data such as weight 70 kg, blood pressure 130 / 85, and blood sugar level 100 mg / dL, and selects "spicy curry rice" as their favorite dish. The server generates a spicy curry rice recipe that suits the user's preferences, taking into account the user's weight and blood pressure and selecting ingredients with the appropriate nutrients. For example, it provides specific ingredients such as 200 g of chicken, 50 g of carrots, 1 tablespoon of turmeric, and 1 teaspoon of cumin, along with cooking instructions.

[0517] An example prompt is:

[0518] User weight: 70kg

[0519] Blood pressure: 130 / 85

[0520] Blood glucose level: 100 mg / dL

[0521] Favorite food: Spicy curry rice

[0522] Nutrients provided: High in protein, low in fat

[0523] Generate the appropriate food menu:

[0524] In this way, the system of the present invention can help users maintain their health and improve their satisfaction by generating and providing optimal meal menus based on the user's health condition and food preferences, and then delivering those meals.

[0525] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0526] Step 1:

[0527] The user starts the smartphone application and inputs their vital data (e.g., weight, blood pressure, blood sugar level, etc.) and food preference data. The vital data and preference data are input and recorded on the device.

[0528] Input: vital data, food preference data

[0529] Output: Dataset to send to cloud server

[0530] Step 2:

[0531] The device transmits the vital data and food preference data entered by the user to a cloud server via a secure communication protocol (e.g., HTTPS).

[0532] Input: Dataset obtained from user

[0533] Output: Data packets passed to the cloud server

[0534] Step 3:

[0535] The server analyzes the received data and uses a generative AI model (using TensorFlow or PyTorch, for example) to generate an optimal meal menu based on the user's health status and preferences.

[0536] Input: Dataset stored on a cloud server

[0537] Output: Optimal recipe (including specific ingredients and cooking methods)

[0538] Step 4:

[0539] The generated menu is sent from the server to the device, where it is displayed and provided to the user in a format that can be viewed on the device.

[0540] Input: Generated food menu

[0541] Output: A menu of dishes that the user can view on their device.

[0542] Step 5:

[0543] Users can check the menu and place a delivery order within the app. The order information is sent to the server, which then automatically sends it to the partner delivery company.

[0544] Input: User's order request

[0545] Output: A delivery order request is sent to the delivery company.

[0546] Step 6:

[0547] The user receives the food, samples it, and then provides feedback through the app.

[0548] Input: User feedback after tasting

[0549] Output: Feedback data sent to the cloud server

[0550] Step 7:

[0551] The server analyzes the feedback data and reflects it in the generative AI model, which improves the accuracy of future cooking menus.

[0552] Input: User feedback data

[0553] Output: An improved generative AI model

[0554] Thus, the present invention is a system that includes a series of steps to provide optimal food menus based on the user's health condition and food preference data, enable delivery orders, and improve the accuracy of the generative AI model based on feedback.

[0555] 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.

[0556] The system of the present invention acquires a user's vital data, food preference data, and user emotions, and generates, provides, and improves healthy and delicious food menus based on this data. This system operates in cooperation with the user, terminal, and server.

[0557] First, the user launches the application and inputs their personal vital data (e.g., weight, blood pressure, blood sugar level, etc.), their favorite dishes, memorable dishes they have eaten in the past, and taste preferences. In addition, an emotion engine is activated to obtain the user's emotional data. This emotion engine analyzes the user's facial expressions and voice to determine their current emotional state.

[0558] The device sends the vital data, preference data, and emotional data entered by the user to a server on the cloud. The server uses the received data to generate an optimal meal menu that matches the user's health condition and preferences. This process is performed using a generative AI model. By taking into account the nutrients necessary for health promotion and the user's taste preferences, and also reflecting the user's current emotional state, the system proposes a meal menu that is emotionally satisfying.

[0559] The server then sends the generated cooking menu to the device. The cooking menu includes specific ingredient measurements (grams, tablespoons, teaspoons) and detailed cooking instructions. If necessary, the server can also generate cooking instructions as videos and provide them to the device, making it easier for users to understand visually.

[0560] The device also has the ability to link with the user's IoT-enabled cooking appliances, allowing them to automatically set cooking appliances, such as a smart oven to heat at the appropriate temperature and time.

[0561] After cooking is complete, the user tastes the dish and provides feedback to the app on their impressions and suggestions for improvement. Once the user enters their feedback, the information is sent back to the server. The server analyzes the collected feedback and emotional data and updates the generative AI model, which is then reflected in future menu suggestions. By taking the user's emotional state into account, it is possible to provide a more fulfilling dining experience.

[0562] As a specific example, consider the case where a user inputs vital data such as weight 70 kg, blood pressure 130 / 85, and blood sugar level 100 mg / dL, and selects "spicy curry rice" as their favorite dish. Furthermore, suppose the user's emotion engine analyzes the user as "feeling stressed." The server generates a menu based on this vital data, preference data, and emotion data. In this case, the server may suggest relaxing herbal tea in addition to spicy curry rice to reduce the user's stress. For example, the server may provide specific ingredients such as 200 g of chicken, 50 g of carrots, 1 tablespoon of turmeric, and 1 teaspoon of cumin, along with cooking instructions. Additional feedback and emotion data is then collected and reflected in the next menu suggestion.

[0563] In this way, the system of the present invention promotes the user's health and improves the quality of the cooking experience by providing healthy and satisfying cooking menus based on the user's vital data, cooking preferences, and emotional data.

[0564] The processing flow will be explained below.

[0565] Step 1:

[0566] A user launches the application and inputs their personal vital data (e.g., weight, blood pressure, blood sugar level, etc.). The user also inputs data about their favorite dishes, dishes they have eaten in the past, and taste preferences.

[0567] Step 2:

[0568] The user uses a camera and microphone to provide facial expression and voice data to the emotion engine, which then analyzes this data to recognize the user's current emotional state (e.g., feeling stressed, relaxed, etc.).

[0569] Step 3:

[0570] The device transmits vital data, preference data, and emotional data input by the user to a server on the cloud.

[0571] Step 4:

[0572] The server analyzes the received data and generates an optimal meal menu based on the user's health condition, preferences, and emotional state. The generative AI model selects a meal menu that reflects the nutrients necessary for health promotion, the user's taste preferences, and emotional satisfaction.

[0573] Step 5:

[0574] The server generates a cooking menu and sends it to the device, which includes the specific ingredient measurements (in grams, tablespoons, or teaspoons) and detailed cooking instructions.

[0575] Step 6:

[0576] The terminal displays the received menu and cooking instructions to the user. The server also generates a video of the cooking instructions to make them easier to understand visually and provides it to the terminal.

[0577] Step 7:

[0578] The device cooks food according to the menu provided by the user. When using IoT-enabled cooking appliances, the device automatically connects to the appliance and sets the appropriate temperature and time.

[0579] Step 8:

[0580] Users taste the food and enter their feedback about its taste and health effects into the app, such as "I wish it was a little spicier" or "This dish helped me relax."

[0581] Step 9:

[0582] The device sends user feedback and emotional data to a server on the cloud.

[0583] Step 10:

[0584] The server analyzes the collected feedback and emotional data and updates the generative AI model, which then reflects the feedback and emotional data in the next menu suggestion, providing a more optimized menu.

[0585] In this way, the user, terminal, and server work together at each step to create a system that provides healthy, emotionally satisfying meals to the user.

[0586] Example 2

[0587] 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."

[0588] Conventional food recommendation systems have difficulty providing food menus that take into account the user's health condition and preferences, and do not provide food recommendations that reflect the user's emotional state. This makes it difficult for users to find healthy and satisfying food menus, and there is a lack of suggestions that meet individual needs. Furthermore, feedback information is not fully utilized, and system improvements are not being made effectively.

[0589] 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.

[0590] In this invention, the server includes a means for acquiring biometric data of the user, a means for acquiring preference data, and a means for acquiring emotional data of the user, thereby enabling the server to propose optimal cooking menus that reflect the user's health condition, preferences, and emotional state.

[0591] "User's biometric data" refers to numerical data that indicates the user's health condition, such as weight, blood pressure, and blood sugar level.

[0592] "Preference data" is information about the user's food preferences, such as favorite dishes, memorable dishes they have eaten in the past, and taste preferences.

[0593] "User emotional data" is data that indicates the user's current emotional state, obtained by analyzing the user's facial expressions and voice.

[0594] A "generative AI model" is an algorithm that generates optimal cooking menus based on a user's biometric data, preference data, and emotional data.

[0595] A "prompt sentence" is an input sentence that gives instructions to the generative AI model for generating a menu.

[0596] The "means for providing cooking instructions" is a method for presenting specific cooking steps to the user based on the generated cooking menu.

[0597] "Feedback information" refers to information about users' impressions of the food after tasting it and areas for improvement.

[0598] The "video generation means" is a method for creating a video that visually presents cooking methods based on the generated cooking menu.

[0599] The system of the present invention acquires a user's biometric data, preference data, and emotional data, and then generates, provides, and improves healthy and delicious food menus based on this data. This system operates in cooperation with the user, terminal, and server.

[0600] First, the user launches an application on a device such as a smartphone or tablet. This application runs on a mobile OS such as iOS or Android. The user then enters their personal biometric data (e.g., weight, blood pressure, blood sugar level, etc.). This data can be entered manually or automatically acquired from a Bluetooth-connected wearable device (e.g., a smartwatch). Next, the user enters preference data, such as their favorite dishes, dishes they have eaten in the past, and taste preferences.

[0601] Additionally, the emotion engine operates using the device's built-in camera and microphone. The emotion engine analyzes the user's emotional state from their facial expressions and voice, capturing this as emotion data. For example, it may determine that the user is "feeling stressed."

[0602] The device sends the acquired biometric data, preference data, and emotional data to a server on the cloud. Data is sent using the HTTPS protocol to ensure secure communication. The server analyzes the received data using a generative AI model (e.g., GPT-4). The generative AI model generates the optimal dish menu for the user based on the prompt text. An example of a prompt text is, "Please generate the optimal dish menu if the user is feeling stressed, has a weight of 70 kg, a blood pressure of 130 / 85, and a blood sugar level of 100 mg / dL, and prefers spicy curry rice."

[0603] The generative AI model considers the user's taste preferences and nutrients necessary for health promotion, and also reflects the user's current emotional state to suggest emotionally satisfying dishes. For example, it can suggest a relaxing herbal tea in addition to spicy curry rice. Specifically, it provides measurements of ingredients such as 200g of chicken, 50g of carrots, 1 tablespoon of turmeric, and 1 teaspoon of cumin, along with cooking instructions.

[0604] The server sends the generated menu to the device. The data includes specific ingredient measurements (e.g., grams, tablespoons, teaspoons) and detailed cooking instructions. If necessary, the server can also generate cooking instructions as videos and provide them to the device, making it easier for users to understand visually.

[0605] The device also has the ability to link with the user's IoT-enabled kitchen appliances, allowing them to automatically set their cooking appliances, for example, a smart oven to heat at the appropriate temperature and time.

[0606] After cooking is complete, the user tastes the dish and provides feedback to the app on their impressions and suggestions for improvement. Once the user enters their feedback, the information is sent back to the server. The server analyzes the collected feedback and emotional data and updates the generative AI model, which is then reflected in future menu suggestions. By taking the user's emotional state into account, it is possible to provide a more fulfilling dining experience.

[0607] In this way, the system of the present invention promotes the user's health and improves the quality of the cooking experience by providing healthy and satisfying cooking menus based on the user's biometric data, cooking preferences, and emotional data.

[0608] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0609] Step 1:

[0610] Data Entry

[0611] Users launch a dedicated application on their smartphone or tablet, which runs on a mobile operating system such as iOS or Android.

[0612] Users manually enter their personal biometric data (e.g., weight, blood pressure, blood glucose level, etc.) or it is automatically obtained from a Bluetooth-connected wearable device (e.g., a smartwatch).

[0613] The user also inputs preference data such as favorite dishes, memorable dishes they have eaten in the past, and taste preferences.

[0614] The emotion engine operates using the device's built-in camera and microphone to analyze the user's current emotional state from their facial expressions and voice.

[0615] How it works: The camera captures the user's facial expressions and the microphone records the user's voice. These data are processed in real time and output as emotional data, such as "I feel stressed."

[0616] Step 2:

[0617] Data transmission

[0618] The device collects biometric data, preference data, and emotional data and sends it to a cloud server. This data is generally sent in JSON format and is securely transmitted using the HTTPS protocol.

[0619] Specific operation: The device collects each piece of data, compiles it into a single JSON object, and sends an HTTPS request.

[0620] Step 3:

[0621] Data analysis and menu generation

[0622] The server analyzes the received biometric data, preference data, and emotion data.

[0623] A generative AI model (e.g., GPT-4) analyzes the prompt text based on the data and generates the optimal cooking menu.

[0624] Specific prompt: "Generate the best meal plan for the user if they are stressed, weigh 70 kg, have a blood pressure of 130 / 85, and have a blood sugar level of 100 mg / dL, and prefer spicy curry rice."

[0625] How it works: The generative AI model calculates necessary nutrients from biometric data, selects the type of food from preference data, and generates menus that take into account psychological effects from emotional data. For example, to reduce stress, it might suggest relaxing herbal tea in addition to spicy curry rice.

[0626] Step 4:

[0627] Menu offerings

[0628] The server sends the generated menu to the device, including the measurements of specific ingredients (e.g., 200g chicken, 50g carrots, 1 tablespoon turmeric, 1 teaspoon cumin) and detailed cooking instructions.

[0629] Specific operation: The server encodes the generated menu in JSON format and returns it to the device as an HTTP response.

[0630] Step 5:

[0631] IoT-enabled kitchen appliance integration

[0632] The device connects to the user's IoT-enabled cooking appliances (e.g., smart ovens), allowing the appliances to automatically cook food at the appropriate settings (e.g., temperature and time).

[0633] How it works: The device analyzes the cooking recipe and calls the API of the corresponding appliance to send the settings. For example, it sends a command to a smart oven to heat at 180 degrees for 30 minutes.

[0634] Step 6:

[0635] Feedback and Model Updates

[0636] Users can taste the food and provide feedback to the app on their impressions and suggestions for improvement, either as star ratings or text comments.

[0637] The device sends the feedback information to a server on the cloud.

[0638] The server analyzes the collected feedback and emotional data and updates the generative AI model, which is then reflected in future menu suggestions.

[0639] What it does: The server saves the new feedback data in a database and updates the learning algorithm of the generative AI model, which then uses the new data for the next proposal.

[0640] (Application example 2)

[0641] 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."

[0642] Conventional food menu suggestion systems generally rely on a user's vital data and preference data, but because they do not take emotional data into account, it is difficult to suggest optimal food menus based on the user's psychological state. Furthermore, they lack support for actually cooking the suggested dishes, resulting in low user convenience. Another problem is that suggested dishes cannot be tried immediately. To address these issues, a system is needed that can suggest food menus based on the user's psychological state and actually deliver them, providing a healthier and more satisfying dining experience.

[0643] 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.

[0644] In this invention, the server includes means for acquiring vital data of the user, means for acquiring preference data of the user, means for acquiring emotional data of the user, means for analyzing the acquired vital data, preference data, and emotional data to generate an optimal dish menu, means for providing the generated dish menu, means for providing cooking methods based on the provided dish menu, means for acquiring feedback information and reflecting it in improving the dish menu, and means for delivering cooked dishes. This makes it possible to propose an optimal dish menu that takes into consideration both the user's health and psychological state, and furthermore, by promptly delivering and providing the dish, a more satisfying dining experience can be realized.

[0645] "User vital data" refers to physiological data that indicates the user's health status, such as weight, blood pressure, and blood sugar level.

[0646] "Cooking preference data" refers to data about the user's favorite dishes, memorable dishes they have eaten in the past, and their taste preferences.

[0647] "User emotional data" is data that indicates the user's current emotional state, analyzed from their facial expressions and voice.

[0648] The "means for generating a cooking menu" refers to a technical means for analyzing a user's vital data, preference data, and emotional data to generate an optimal cooking menu.

[0649] "Means for providing a food menu" refers to means for displaying and notifying the user of the generated food menu.

[0650] The "means for providing cooking instructions" is a means for providing specific ingredient measurement information and detailed cooking instructions based on the generated cooking menu.

[0651] The "means for obtaining feedback information" refers to a means for obtaining feedback information such as user's impressions and suggestions for improvement regarding the provided food menu.

[0652] "Means for reflecting improvements to the food menu" refers to the means for improving and optimizing the food menu for future meals based on the obtained feedback information.

[0653] The "means for delivering cooked food" refers to a means for delivering food cooked based on the generated cooking menu to the user.

[0654] The system of the present invention acquires a user's vital data, food preference data, and emotional data, and uses this data to generate, provide, and improve healthy and satisfying food menus, and delivers the cooked meals. This system operates in cooperation with the user, terminal, and server.

[0655] First, the user launches the application using a device (e.g., a smartphone) and inputs their personal vital data (weight, blood pressure, blood sugar level, etc.). Next, they input data about the user's favorite dishes, memorable dishes they have eaten in the past, and taste preferences. Furthermore, to obtain emotional data, the emotion engine analyzes emotions from facial expressions and voice.

[0656] The device sends the vital data, preference data, and emotional data entered by the user to a server on the cloud. The server uses the acquired data to generate an optimal meal menu that matches the user's health condition and preferences. This generation process is carried out using a generative AI model (e.g., OpenAI GPT-4). By taking into account the nutrients necessary for health promotion and the user's taste preferences, and also reflecting the user's current emotional state, the system proposes a meal menu that is emotionally satisfying.

[0657] The server sends the generated cooking menu to the device. The cooking menu includes specific ingredient measurements (grams, tablespoons, teaspoons) and detailed cooking instructions. If necessary, the server can also generate cooking instructions as videos and provide them to the device, making it easier for users to understand visually.

[0658] The device also has the ability to link with the user's IoT-enabled cooking appliances, allowing the appliance to automatically set its temperature and time, for example, so that a smart oven can heat food at the appropriate temperature and time.

[0659] After cooking is complete, the user tastes the dish and provides feedback to the app on their impressions and areas for improvement. Once the user enters their feedback, the information is sent back to the server. The server analyzes the collected feedback and emotional data and updates the generative AI model. This will be reflected in future menu suggestions, enabling the app to provide a more satisfying dining experience.

[0660] Furthermore, the system also provides a means for delivering cooked dishes based on the generated menu, allowing users to immediately try the suggested dishes, improving convenience.

[0661] Specific examples

[0662] For example, consider a case where a user inputs vital data such as weight 70 kg, blood pressure 130 / 85 mmHg, and blood sugar level 100 mg / dL, and selects "spicy curry rice" as their favorite dish. If the emotion engine analyzes the user as "feeling stressed," the server will suggest relaxing herbal tea and spicy curry rice. The user selects this menu, and the cooked food is delivered through the ordering process.

[0663] Prompt Sentence Examples

[0664] "The user's weight is 70 kg, blood pressure is 130 / 85 mmHg, blood sugar level is 100 mg / dL, favorite food is spicy curry rice, and they are feeling stressed. Based on this information, please suggest a meal menu that will have a relaxing effect."

[0665] ---

[0666] The system aims to balance user health and food satisfaction, and by utilizing a variety of data, it provides a more personalized dining experience.

[0667] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0668] Step 1:

[0669] The user starts the application on the device and inputs vital data. Specifically, the user enters health data such as weight, blood pressure, and blood sugar level into the device through an input form. The input at this point is the user's vital data.

[0670] Step 2:

[0671] The user inputs data about their favorite dishes, dishes they have eaten in the past, and taste preferences into the terminal. For example, spicy curry rice is input as a favorite dish. This data is acquired as the user's food preference data.

[0672] Step 3:

[0673] The emotion engine operates and acquires emotion data from the user's facial expressions and voice. The device uses a camera and microphone to capture the user's facial expressions and voice, and the emotion engine analyzes them to acquire the user's current emotional state. This data is the user's emotion data.

[0674] Step 4:

[0675] The device sends the acquired vital data, food preference data, and emotional data to a server on the cloud. The input here is a collection of each data, and the device then sends it to the cloud.

[0676] Step 5:

[0677] The server analyzes the received data and generates an optimal cooking menu using a generative AI model. The server generates a cooking menu that takes into account the nutrients necessary for health promotion and the user's preferences based on the user's vital data, food preference data, and emotional data. This process uses a generative AI model.

[0678] Step 6:

[0679] The server sends the generated menu to the terminal, which then visually displays it to the user, including specific ingredient measurements and detailed cooking instructions.

[0680] Step 7:

[0681] The device generates a video of the cooking method sent from the server as needed and provides it to the user, making it easier for the user to visually understand the cooking procedure.

[0682] Step 8:

[0683] The device connects to IoT-enabled cooking appliances and automatically sets the appropriate cooking temperature and time, allowing users to cook easily.

[0684] Step 9:

[0685] After cooking is complete, the user tastes the dish and provides feedback on their impressions and suggestions for improvement to the device, which then records the feedback as user input.

[0686] Step 10:

[0687] The device then sends the collected feedback information and emotion data back to the server, which uses it to update the generative AI model and reflect it in future menu suggestions.

[0688] Step 11:

[0689] The server delivers cooked dishes based on the cooking menu it generates, allowing users to immediately try the suggested dishes. This operation provides convenience to users.

[0690] 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.

[0691] 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.

[0692] 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.

[0693] [Third embodiment]

[0694] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0695] 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.

[0696] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0697] The 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.

[0698] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0699] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0700] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 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.

[0701] 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.

[0702] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0703] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0704] In the 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.

[0705] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0706] The system of the present invention acquires a user's vital data and food preference data, and based on that data, generates, provides, and improves healthy and delicious food menus. This system operates in cooperation with the user, terminal, and server.

[0707] First, the user launches the application and enters their vital data (e.g., weight, blood pressure, blood sugar level, etc.) into the app. Then, they also enter data about their favorite dishes, memorable dishes they have eaten in the past, and taste preferences. This allows the app to clarify the user's individual health condition and food preferences.

[0708] The terminal (smartphone, tablet, etc.) sends vital data and preference data entered by the user to a server on the cloud. The server generates the optimal meal menu for the user based on the received data. This process is carried out by an AI model, which selects a meal menu that matches the nutrients necessary for health promotion and the user's preferences.

[0709] The server then sends the generated cooking menu to the device. The cooking menu includes specific ingredient measurements (in grams or tablespoons / teaspoons) and cooking instructions. If necessary, the server can also generate a video of the cooking instructions and provide it to the device, helping users to understand the menu visually.

[0710] The device also has the ability to link with the user's IoT-enabled kitchen appliances, allowing them to automatically set their cooking appliances, for example, a smart oven to heat at the appropriate temperature and time.

[0711] After cooking is complete, the user tastes the dish and provides feedback to the app on their impressions and suggestions for improvement. Once the user enters their feedback, the information is sent back to the server. The server analyzes the collected feedback and improves the AI ​​model. This will enable the app to generate future meal menus that better suit the user's preferences and health.

[0712] As a concrete example, consider the case where a user inputs vital data such as weight 70 kg, blood pressure 130 / 85, and blood sugar level 100 mg / dL, and selects "spicy curry rice" as their favorite dish. The server generates a spicy curry rice recipe that suits the user's preferences while taking into account weight and blood pressure and selecting ingredients with the appropriate nutrients. For example, it provides specific ingredients such as 200 g of chicken, 50 g of carrots, 1 tablespoon of turmeric, and 1 teaspoon of cumin, along with cooking instructions. The server then receives feedback to adjust the spiciness and reflects this in the next recipe generation.

[0713] In this way, the system of the present invention provides healthy and delicious meal menus based on the user's vital data and preferences, promoting the user's health and improving the quality of the food they eat.

[0714] The processing flow will be explained below.

[0715] Step 1:

[0716] A user launches the application and inputs their personal vital data (e.g., weight, blood pressure, blood sugar level, etc.) The user also inputs data about their favorite dishes, memories of dishes they have eaten in the past, and taste preferences.

[0717] Step 2:

[0718] The device receives vital data and preference data entered by the user and sends it to a server on the cloud.

[0719] Step 3:

[0720] The server analyzes the received vital data and preference data and generates an optimal menu based on the user's health condition and preferences. The generative AI model takes into account the nutrients necessary for health promotion and the user's taste preferences.

[0721] Step 4:

[0722] The server generates a cooking menu and sends it to the device, which includes specific ingredient measurements (in grams, tablespoons, or teaspoons) and detailed cooking instructions.

[0723] Step 5:

[0724] The terminal displays the received menu and cooking instructions to the user, and also provides the cooking instructions generated by the server as a video to the terminal for easy visual understanding.

[0725] Step 6:

[0726] The device cooks food according to the menu provided by the user. When using IoT-enabled cooking appliances, the device will link with the appliance and automatically set the appropriate temperature and time.

[0727] Step 7:

[0728] Users taste the food and enter their feedback about the taste and health effects into the app, such as "I wish it was a little spicier."

[0729] Step 8:

[0730] The device sends the user's feedback to a server on the cloud.

[0731] Step 9:

[0732] The server analyzes the collected feedback and updates the generative AI model, which then reflects the feedback in the next menu suggestions, providing a menu that is more optimized in terms of both taste and health.

[0733] In this way, the user, terminal, and server work together at each step to create a system that provides healthy and delicious meals to users.

[0734] Example 1

[0735] 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."

[0736] In modern society, it is extremely important to provide meal menus tailored to each individual's health condition and food preferences. However, providing such menus generally requires specialized knowledge, and there are no systems that are easily accessible to many people. Furthermore, there is a lack of mechanisms for quickly responding to changes in the user's health condition and improving menus based on feedback. As a result, it is difficult to continuously provide meals that promote health and match preferences.

[0737] 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.

[0738] In this invention, the server includes a means for acquiring biometric data of the user, a means for acquiring food preference data, and a means for analyzing the acquired biometric data and preference data to generate an optimal meal menu, thereby providing an optimal meal menu based on the user's health condition and preferences, and making it possible to continuously improve the menu based on feedback.

[0739] "User Biometric Data" means objective medical measurements that indicate the user's health, such as weight, blood pressure, or blood sugar level.

[0740] "Food preference data" is information that indicates a user's personal food preferences, such as the type of food they like, the strength of the flavor, and the spiciness of the food.

[0741] "Means for analyzing acquired biometric data and preference data to generate an optimal meal menu" refers to a process or device that analyzes a user's biometric data and preference data and creates a nutritionally balanced meal menu appropriate for the user based on that data.

[0742] "Means for providing the generated meal menu" refers to a method or system for notifying and presenting the user with the meal menu generated through analysis.

[0743] "Means for providing cooking instructions" refers to a device or method that provides a user with specific cooking procedures and methods based on the provided meal menu.

[0744] "Means for obtaining feedback information and reflecting it in improving the meal menu" refers to a device or method for collecting user feedback and suggestions for improvement and improving the meal menu based on that feedback.

[0745] "Means for providing specific ingredient measurement information" refers to a system or method for indicating the exact amount of ingredients needed based on the generated meal menu.

[0746] "Video generation means" refers to a system or method for generating videos that visually show cooking methods and providing them to users.

[0747] The system of the present invention acquires a user's biometric data and food preference data, and then generates, provides, and improves an optimal meal menu based on that data. This system operates in cooperation with the user, terminal, and server.

[0748] First, the user launches the application using a device such as a smartphone or tablet. Within the application, the user enters their biometric data (weight, blood pressure, blood sugar level, etc.) and food preference data (favorite dishes, taste preferences, etc.). This clarifies the user's individual health condition and food preferences.

[0749] The device then sends the user's biometric and preference data to a cloud-based server, which then analyzes the received data using a generative AI model to generate a meal plan optimized for the user. This analysis includes algorithms that take into account the user's nutritional needs and preferences for better health.

[0750] As a concrete example, consider the case where a user inputs biometric data such as weight 70 kg, blood pressure 130 / 85, and blood sugar level 100 mg / dL, and selects "spicy curry rice" as their favorite dish. In this case, the server analyzes the user's data and generates a healthy spicy curry rice recipe. For example, it provides specific ingredients such as 200 g of chicken, 50 g of carrots, 1 tablespoon of turmeric, and 1 teaspoon of cumin, along with cooking instructions.

[0751] The server then sends the generated menu to the terminal. The terminal displays the received recipe information to the user. If necessary, it also generates a video of the cooking method to help the user visually understand the recipe. This video generation means is also executed on the server and provided to the terminal.

[0752] Furthermore, the device can also link with the user's IoT-enabled cooking appliances, enabling automated cooking, such as a smart oven heating food at the appropriate temperature and time.

[0753] After cooking is complete, users can taste the dish and provide feedback to the app on their impressions and suggestions for improvement. Once the user has entered their feedback, the information is sent back to the server, which analyzes the collected feedback and improves the generative AI model. This will enable the app to generate future meal menus that better suit the user's preferences and health.

[0754] Examples of prompts include:

[0755] "A user weighing 70 kg, with a blood pressure of 130 / 85 and a blood sugar level of 100 mg / dL has entered spicy curry rice as their favorite dish. Please generate a spicy curry rice recipe that suits the user's preferences while taking their health condition into consideration."

[0756] In this way, the system of the present invention provides a healthy and delicious meal menu based on the user's biometric data and preferences, promoting the user's health and improving the quality of their meals.

[0757] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0758] Step 1:

[0759] App launch

[0760] (Subject: User) The user launches an application on their smartphone or tablet. This action displays the login screen.

[0761] Input: User action (tap icon)

[0762] Output: Login screen displayed

[0763] Step 2:

[0764] Entering vital data

[0765] (Subject: User) The user enters their biometric data (weight, blood pressure, blood sugar level, etc.) into an input form within the application.

[0766] Input: Biometric data (e.g., weight 70 kg, blood pressure 130 / 85, blood sugar 100 mg / dL)

[0767] Output: Biometric data is stored within the application

[0768] Step 3:

[0769] Entering preference data

[0770] (Subject: User) The user enters their favorite dishes and taste preferences.

[0771] Input: Preference data (e.g., favorite dish "spicy curry rice")

[0772] Output: Preference data is saved in the application

[0773] Step 4:

[0774] Data transmission

[0775] (Subject: Device) The device sends the biometric and preference data entered by the user to a server in the cloud. The data is sent via Wi-Fi or mobile data.

[0776] Input: User-entered biometric and preference data

[0777] Output: Server receives data

[0778] Step 5:

[0779] Data reception

[0780] (Subject: Server) The server receives the biometric data and preference data sent from the terminal and stores them in a database.

[0781] Input: Submitted biometric and preference data

[0782] Output: User data stored in the database

[0783] Step 6:

[0784] Prompt generation

[0785] (Subject: Server) Based on the data received by the server, a prompt sentence is generated to be input into the generative AI model.

[0786] Input: Stored biometric and preference data

[0787] Output: Generated prompt text (e.g., "A user weighing 70 kg, with a blood pressure of 130 / 85 and a blood sugar level of 100 mg / dL has entered spicy curry rice as their favorite dish. Please generate a recipe for spicy curry rice that suits the user's preferences while taking their health condition into consideration.")

[0788] Step 7:

[0789] Input to AI model and analysis

[0790] (Subject: Server) The server inputs the prompt sentence into the generated AI model and performs analysis. As a result of the analysis, a meal menu that reflects the user's health condition and preferences is generated.

[0791] Input: Generated prompt text

[0792] Output: Meal menu as analysis result (e.g., 200g chicken, 50g carrots, 1 tablespoon turmeric, 1 teaspoon cumin)

[0793] Step 8:

[0794] Recipe Generation

[0795] (Subject: Server) The server converts the generated recipe into a concrete form (amount of ingredients, cooking steps).

[0796] Input: Meal menu as analysis result

[0797] Output: A specific recipe (e.g., 200g chicken, 50g carrots, 1 tablespoon turmeric, 1 teaspoon cumin, and cooking instructions)

[0798] Step 9:

[0799] Send recipe

[0800] (Subject: Server) The server sends the generated specific recipe to the terminal.

[0801] Input: A specific recipe

[0802] Output: Recipe data sent to the device

[0803] Step 10:

[0804] Recipe display

[0805] (Subject: Terminal) The terminal displays the received recipe to the user, allowing the user to check the recipe.

[0806] Input: Submitted recipe data

[0807] Output: The recipe displayed on the terminal screen

[0808] Step 11:

[0809] Cooking appliance linkage

[0810] (Subject: Device) The device sends instructions to IoT-enabled cooking appliances, such as setting a smart oven to the appropriate temperature and time.

[0811] Input: Cooking setting information based on recipe data

[0812] Output: Set cooking appliances

[0813] Step 12:

[0814] Feedback Input

[0815] (Subject: User) The user provides feedback to the app about their impressions and areas for improvement after cooking.

[0816] Input: Feedback information (e.g., "It was too spicy")

[0817] Output: Feedback information stored in the app

[0818] Step 13:

[0819] Send Feedback

[0820] (Subject: Terminal) The terminal sends the user's feedback to the server.

[0821] Input: Feedback information stored in the app

[0822] Output: Feedback information sent to the server

[0823] Step 14:

[0824] Feedback Analysis

[0825] (Subject: Server) The server analyzes the collected feedback and reflects it in improving the generative AI model.

[0826] Input: Submitted feedback information

[0827] Output: An updated generative AI model

[0828] In this way, the present invention provides a system that provides a healthy and delicious meal menu based on the user's biometric data and preferences, thereby promoting the user's health and improving the quality of their meals.

[0829] (Application example 1)

[0830] 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."

[0831] The present invention relates to a system that provides optimal food menus based on a user's individual health condition and taste preferences, and aims to provide an environment in which healthy and delicious food can be quickly enjoyed when ordering delivery of the food menu. Another objective is to improve user satisfaction by using feedback on the food menu.

[0832] 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.

[0833] In this invention, the server includes means for acquiring a user's vital data, means for acquiring food preference data, means for transmitting the acquired vital data and preference data to the cloud, means for analyzing the acquired data on the cloud server and generating an optimal food menu using a generative AI model, means for transmitting and providing the generated food menu to a terminal, means for placing a delivery order based on the generated food menu, means for providing cooking methods based on the provided food menu, and means for acquiring feedback information and reflecting it in improving the food menu. This makes it possible to order a food menu for delivery that matches the user's health condition and taste preferences, and to improve the menu based on subsequent feedback.

[0834] "Means for acquiring user's vital data" refers to a method or device for detecting, recording, and collecting data on the user's health status, such as weight, blood pressure, and blood sugar level.

[0835] "Means for acquiring food preference data" refers to a method or device for collecting information such as a user's preferred flavors and types of food, and records of food eaten in the past.

[0836] "Means for sending to the cloud" refers to a method or device for sending acquired data to a cloud server via the Internet.

[0837] A "server on the cloud" is a remote server on which computing resources are located that are accessible via the Internet.

[0838] "Means for analyzing acquired data and generating optimal dish menus using a generative AI model" refers to a method or device for analyzing collected user data using an algorithm or AI model to create optimal dish menus.

[0839] "Means for transmitting and providing to terminal" refers to a method or apparatus for transmitting the generated cooking menu to the end user's device and displaying it.

[0840] The "means for placing a delivery order" refers to a method or device for placing an order for food with a delivery company based on the created food menu.

[0841] The "means for providing cooking methods" refers to a method or device for presenting specific cooking procedures and methods to the user based on the generated cooking menu.

[0842] "Means for obtaining feedback information and reflecting it in improving the food menu" refers to a method or device for collecting user evaluations and suggestions for improvement, improving the generative AI model based on them, and using them to generate the next menu.

[0843] The system according to the present invention acquires and analyzes a user's vital data and food preference data, generates an optimal food menu based on the data, and places a delivery order. Specific embodiments will be described below.

[0844] First, the user launches the smartphone application and logs in to their account. Next, the user enters their vital data (e.g., weight, blood pressure, blood sugar level, etc.) and food preferences. This data is entered through the smartphone interface and sent to a server on the cloud.

[0845] Once the server receives this data, it analyzes it using a generative AI model built using machine learning libraries such as Python's TensorFlow and PyTorch to generate an optimal meal menu that matches the user's health status and preferences.

[0846] The generated menu includes specific ingredient measurements (e.g., 200g chicken, 50g carrots, 1 tablespoon turmeric, 1 teaspoon cumin) and cooking instructions. The server then sends the generated menu to the smartphone and serves it to the user.

[0847] When a user checks the menu and places a delivery order, the server manually or automatically places the order with the delivery company. For this purpose, an API is used to link the server and send the order information to the delivery system.

[0848] In addition, cooking instructions are provided in an easy-to-understand visual format and displayed as videos on a smartphone app, allowing users to easily and accurately follow the cooking steps.

[0849] After the food is delivered and the user samples it, they can provide feedback through the app. This feedback is then sent back to the cloud server and used to improve the AI ​​model. This allows the next time a menu is generated, it will be tailored to the user's preferences and health status.

[0850] As a concrete example, consider the case where a user inputs vital data such as weight 70 kg, blood pressure 130 / 85, and blood sugar level 100 mg / dL, and selects "spicy curry rice" as their favorite dish. The server generates a spicy curry rice recipe that suits the user's preferences, taking into account the user's weight and blood pressure and selecting ingredients with the appropriate nutrients. For example, it provides specific ingredients such as 200 g of chicken, 50 g of carrots, 1 tablespoon of turmeric, and 1 teaspoon of cumin, along with cooking instructions.

[0851] An example prompt is:

[0852] User weight: 70kg

[0853] Blood pressure: 130 / 85

[0854] Blood glucose level: 100 mg / dL

[0855] Favorite food: Spicy curry rice

[0856] Nutrients provided: High in protein, low in fat

[0857] Generate the appropriate food menu:

[0858] In this way, the system of the present invention can help users maintain their health and improve their satisfaction by generating and providing optimal meal menus based on the user's health condition and food preferences, and then delivering those meals.

[0859] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0860] Step 1:

[0861] The user starts the smartphone application and inputs their vital data (e.g., weight, blood pressure, blood sugar level, etc.) and food preference data. The vital data and preference data are input and recorded on the device.

[0862] Input: vital data, food preference data

[0863] Output: Dataset to send to cloud server

[0864] Step 2:

[0865] The device transmits the vital data and food preference data entered by the user to a cloud server via a secure communication protocol (e.g., HTTPS).

[0866] Input: Dataset obtained from user

[0867] Output: Data packets passed to the cloud server

[0868] Step 3:

[0869] The server analyzes the received data and uses a generative AI model (using TensorFlow or PyTorch, for example) to generate an optimal meal menu based on the user's health status and preferences.

[0870] Input: Dataset stored on a cloud server

[0871] Output: Optimal recipe (including specific ingredients and cooking methods)

[0872] Step 4:

[0873] The generated menu is sent from the server to the device, where it is displayed and provided to the user in a format that can be viewed on the device.

[0874] Input: Generated food menu

[0875] Output: A menu of dishes that the user can view on their device.

[0876] Step 5:

[0877] Users can check the menu and place a delivery order within the app. The order information is sent to the server, which then automatically sends it to the partner delivery company.

[0878] Input: User's order request

[0879] Output: A delivery order request is sent to the delivery company.

[0880] Step 6:

[0881] The user receives the food, samples it, and then provides feedback through the app.

[0882] Input: User feedback after tasting

[0883] Output: Feedback data sent to the cloud server

[0884] Step 7:

[0885] The server analyzes the feedback data and reflects it in the generative AI model, which improves the accuracy of future cooking menus.

[0886] Input: User feedback data

[0887] Output: An improved generative AI model

[0888] Thus, the present invention is a system that includes a series of steps to provide optimal food menus based on the user's health condition and food preference data, enable delivery orders, and improve the accuracy of the generative AI model based on feedback.

[0889] 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.

[0890] The system of the present invention acquires a user's vital data, food preference data, and user emotions, and generates, provides, and improves healthy and delicious food menus based on this data. This system operates in cooperation with the user, terminal, and server.

[0891] First, the user launches the application and inputs their personal vital data (e.g., weight, blood pressure, blood sugar level, etc.), their favorite dishes, memorable dishes they have eaten in the past, and taste preferences. In addition, an emotion engine is activated to obtain the user's emotional data. This emotion engine analyzes the user's facial expressions and voice to determine their current emotional state.

[0892] The device sends the vital data, preference data, and emotional data entered by the user to a server on the cloud. The server uses the received data to generate an optimal meal menu that matches the user's health condition and preferences. This process is performed using a generative AI model. By taking into account the nutrients necessary for health promotion and the user's taste preferences, and also reflecting the user's current emotional state, the system proposes a meal menu that is emotionally satisfying.

[0893] The server then sends the generated cooking menu to the device. The cooking menu includes specific ingredient measurements (grams, tablespoons, teaspoons) and detailed cooking instructions. If necessary, the server can also generate cooking instructions as videos and provide them to the device, making it easier for users to understand visually.

[0894] The device also has the ability to link with the user's IoT-enabled cooking appliances, allowing them to automatically set cooking appliances, such as a smart oven to heat at the appropriate temperature and time.

[0895] After cooking is complete, the user tastes the dish and provides feedback to the app on their impressions and suggestions for improvement. Once the user enters their feedback, the information is sent back to the server. The server analyzes the collected feedback and emotional data and updates the generative AI model, which is then reflected in future menu suggestions. By taking the user's emotional state into account, it is possible to provide a more fulfilling dining experience.

[0896] As a specific example, consider the case where a user inputs vital data such as weight 70 kg, blood pressure 130 / 85, and blood sugar level 100 mg / dL, and selects "spicy curry rice" as their favorite dish. Furthermore, suppose the user's emotion engine analyzes the user as "feeling stressed." The server generates a menu based on this vital data, preference data, and emotion data. In this case, the server may suggest relaxing herbal tea in addition to spicy curry rice to reduce the user's stress. For example, the server may provide specific ingredients such as 200 g of chicken, 50 g of carrots, 1 tablespoon of turmeric, and 1 teaspoon of cumin, along with cooking instructions. Additional feedback and emotion data is then collected and reflected in the next menu suggestion.

[0897] In this way, the system of the present invention promotes the user's health and improves the quality of the cooking experience by providing healthy and satisfying cooking menus based on the user's vital data, cooking preferences, and emotional data.

[0898] The processing flow will be explained below.

[0899] Step 1:

[0900] A user launches the application and inputs their personal vital data (e.g., weight, blood pressure, blood sugar level, etc.). The user also inputs data about their favorite dishes, dishes they have eaten in the past, and taste preferences.

[0901] Step 2:

[0902] The user uses a camera and microphone to provide facial expression and voice data to the emotion engine, which then analyzes this data to recognize the user's current emotional state (e.g., feeling stressed, relaxed, etc.).

[0903] Step 3:

[0904] The device transmits vital data, preference data, and emotional data input by the user to a server on the cloud.

[0905] Step 4:

[0906] The server analyzes the received data and generates an optimal meal menu based on the user's health condition, preferences, and emotional state. The generative AI model selects a meal menu that reflects the nutrients necessary for health promotion, the user's taste preferences, and emotional satisfaction.

[0907] Step 5:

[0908] The server generates a cooking menu and sends it to the device, which includes the specific ingredient measurements (in grams, tablespoons, or teaspoons) and detailed cooking instructions.

[0909] Step 6:

[0910] The terminal displays the received menu and cooking instructions to the user. The server also generates a video of the cooking instructions to make them easier to understand visually and provides it to the terminal.

[0911] Step 7:

[0912] The device cooks food according to the menu provided by the user. When using IoT-enabled cooking appliances, the device automatically connects to the appliance and sets the appropriate temperature and time.

[0913] Step 8:

[0914] Users taste the food and enter their feedback about its taste and health effects into the app, such as "I wish it was a little spicier" or "This dish helped me relax."

[0915] Step 9:

[0916] The device sends user feedback and emotional data to a server on the cloud.

[0917] Step 10:

[0918] The server analyzes the collected feedback and emotional data and updates the generative AI model, which then reflects the feedback and emotional data in the next menu suggestion, providing a more optimized menu.

[0919] In this way, the user, terminal, and server work together at each step to create a system that provides healthy, emotionally satisfying meals to the user.

[0920] Example 2

[0921] 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."

[0922] Conventional food recommendation systems have difficulty providing food menus that take into account the user's health condition and preferences, and do not provide food recommendations that reflect the user's emotional state. This makes it difficult for users to find healthy and satisfying food menus, and there is a lack of suggestions that meet individual needs. Furthermore, feedback information is not fully utilized, and system improvements are not being made effectively.

[0923] 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.

[0924] In this invention, the server includes a means for acquiring biometric data of the user, a means for acquiring preference data, and a means for acquiring emotional data of the user, thereby enabling the server to propose optimal cooking menus that reflect the user's health condition, preferences, and emotional state.

[0925] "User's biometric data" refers to numerical data that indicates the user's health condition, such as weight, blood pressure, and blood sugar level.

[0926] "Preference data" is information about the user's food preferences, such as favorite dishes, memorable dishes they have eaten in the past, and taste preferences.

[0927] "User emotional data" is data that indicates the user's current emotional state, obtained by analyzing the user's facial expressions and voice.

[0928] A "generative AI model" is an algorithm that generates optimal cooking menus based on a user's biometric data, preference data, and emotional data.

[0929] A "prompt sentence" is an input sentence that gives instructions to the generative AI model for generating a menu.

[0930] The "means for providing cooking instructions" is a method for presenting specific cooking steps to the user based on the generated cooking menu.

[0931] "Feedback information" refers to information about users' impressions of the food after tasting it and areas for improvement.

[0932] The "video generation means" is a method for creating a video that visually presents cooking methods based on the generated cooking menu.

[0933] The system of the present invention acquires a user's biometric data, preference data, and emotional data, and then generates, provides, and improves healthy and delicious food menus based on this data. This system operates in cooperation with the user, terminal, and server.

[0934] First, the user launches an application on a device such as a smartphone or tablet. This application runs on a mobile OS such as iOS or Android. The user then enters their personal biometric data (e.g., weight, blood pressure, blood sugar level, etc.). This data can be entered manually or automatically acquired from a Bluetooth-connected wearable device (e.g., a smartwatch). Next, the user enters preference data, such as their favorite dishes, dishes they have eaten in the past, and taste preferences.

[0935] Additionally, the emotion engine operates using the device's built-in camera and microphone. The emotion engine analyzes the user's emotional state from their facial expressions and voice, capturing this as emotion data. For example, it may determine that the user is "feeling stressed."

[0936] The device sends the acquired biometric data, preference data, and emotional data to a server on the cloud. Data is sent using the HTTPS protocol to ensure secure communication. The server analyzes the received data using a generative AI model (e.g., GPT-4). The generative AI model generates the optimal dish menu for the user based on the prompt text. An example of a prompt text is, "Please generate the optimal dish menu if the user is feeling stressed, has a weight of 70 kg, a blood pressure of 130 / 85, and a blood sugar level of 100 mg / dL, and prefers spicy curry rice."

[0937] The generative AI model considers the user's taste preferences and nutrients necessary for health promotion, and also reflects the user's current emotional state to suggest emotionally satisfying dishes. For example, it can suggest a relaxing herbal tea in addition to spicy curry rice. Specifically, it provides measurements of ingredients such as 200g of chicken, 50g of carrots, 1 tablespoon of turmeric, and 1 teaspoon of cumin, along with cooking instructions.

[0938] The server sends the generated menu to the device. The data includes specific ingredient measurements (e.g., grams, tablespoons, teaspoons) and detailed cooking instructions. If necessary, the server can also generate cooking instructions as videos and provide them to the device, making it easier for users to understand visually.

[0939] The device also has the ability to link with the user's IoT-enabled kitchen appliances, allowing them to automatically set their cooking appliances, for example, a smart oven to heat at the appropriate temperature and time.

[0940] After cooking is complete, the user tastes the dish and provides feedback to the app on their impressions and suggestions for improvement. Once the user enters their feedback, the information is sent back to the server. The server analyzes the collected feedback and emotional data and updates the generative AI model, which is then reflected in future menu suggestions. By taking the user's emotional state into account, it is possible to provide a more fulfilling dining experience.

[0941] In this way, the system of the present invention promotes the user's health and improves the quality of the cooking experience by providing healthy and satisfying cooking menus based on the user's biometric data, cooking preferences, and emotional data.

[0942] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0943] Step 1:

[0944] Data Entry

[0945] Users launch a dedicated application on their smartphone or tablet, which runs on a mobile operating system such as iOS or Android.

[0946] Users manually enter their personal biometric data (e.g., weight, blood pressure, blood glucose level, etc.) or it is automatically obtained from a Bluetooth-connected wearable device (e.g., a smartwatch).

[0947] The user also inputs preference data such as favorite dishes, memorable dishes they have eaten in the past, and taste preferences.

[0948] The emotion engine operates using the device's built-in camera and microphone to analyze the user's current emotional state from their facial expressions and voice.

[0949] How it works: The camera captures the user's facial expressions and the microphone records the user's voice. These data are processed in real time and output as emotional data, such as "I feel stressed."

[0950] Step 2:

[0951] Data transmission

[0952] The device collects biometric data, preference data, and emotional data and sends it to a cloud server. This data is generally sent in JSON format and is securely transmitted using the HTTPS protocol.

[0953] Specific operation: The device collects each piece of data, compiles it into a single JSON object, and sends an HTTPS request.

[0954] Step 3:

[0955] Data analysis and menu generation

[0956] The server analyzes the received biometric data, preference data, and emotion data.

[0957] A generative AI model (e.g., GPT-4) analyzes the prompt text based on the data and generates the optimal cooking menu.

[0958] Specific prompt: "Generate the best meal plan for the user if they are stressed, weigh 70 kg, have a blood pressure of 130 / 85, and have a blood sugar level of 100 mg / dL, and prefer spicy curry rice."

[0959] How it works: The generative AI model calculates necessary nutrients from biometric data, selects the type of food from preference data, and generates menus that take into account psychological effects from emotional data. For example, to reduce stress, it might suggest relaxing herbal tea in addition to spicy curry rice.

[0960] Step 4:

[0961] Menu offerings

[0962] The server sends the generated menu to the device, including the measurements of specific ingredients (e.g., 200g chicken, 50g carrots, 1 tablespoon turmeric, 1 teaspoon cumin) and detailed cooking instructions.

[0963] Specific operation: The server encodes the generated menu in JSON format and returns it to the device as an HTTP response.

[0964] Step 5:

[0965] IoT-enabled kitchen appliance integration

[0966] The device connects to the user's IoT-enabled cooking appliances (e.g., smart ovens), allowing the appliances to automatically cook food at the appropriate settings (e.g., temperature and time).

[0967] How it works: The device analyzes the cooking recipe and calls the API of the corresponding appliance to send the settings. For example, it sends a command to a smart oven to heat at 180 degrees for 30 minutes.

[0968] Step 6:

[0969] Feedback and Model Updates

[0970] Users can taste the food and provide feedback to the app on their impressions and suggestions for improvement, either as star ratings or text comments.

[0971] The device sends the feedback information to a server on the cloud.

[0972] The server analyzes the collected feedback and emotional data and updates the generative AI model, which is then reflected in future menu suggestions.

[0973] What it does: The server saves the new feedback data in a database and updates the learning algorithm of the generative AI model, which then uses the new data for the next proposal.

[0974] (Application example 2)

[0975] 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."

[0976] Conventional food menu suggestion systems generally rely on a user's vital data and preference data, but because they do not take emotional data into account, it is difficult to suggest optimal food menus based on the user's psychological state. Furthermore, they lack support for actually cooking the suggested dishes, resulting in low user convenience. Another problem is that suggested dishes cannot be tried immediately. To address these issues, a system is needed that can suggest food menus based on the user's psychological state and actually deliver them, providing a healthier and more satisfying dining experience.

[0977] 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.

[0978] In this invention, the server includes means for acquiring vital data of the user, means for acquiring preference data of the user, means for acquiring emotional data of the user, means for analyzing the acquired vital data, preference data, and emotional data to generate an optimal dish menu, means for providing the generated dish menu, means for providing cooking methods based on the provided dish menu, means for acquiring feedback information and reflecting it in improving the dish menu, and means for delivering cooked dishes. This makes it possible to propose an optimal dish menu that takes into consideration both the user's health and psychological state, and furthermore, by promptly delivering and providing the dish, a more satisfying dining experience can be realized.

[0979] "User vital data" refers to physiological data that indicates the user's health status, such as weight, blood pressure, and blood sugar level.

[0980] "Cooking preference data" refers to data about the user's favorite dishes, memorable dishes they have eaten in the past, and their taste preferences.

[0981] "User emotional data" is data that indicates the user's current emotional state, analyzed from their facial expressions and voice.

[0982] The "means for generating a cooking menu" refers to a technical means for analyzing a user's vital data, preference data, and emotional data to generate an optimal cooking menu.

[0983] "Means for providing a food menu" refers to means for displaying and notifying the user of the generated food menu.

[0984] The "means for providing cooking instructions" is a means for providing specific ingredient measurement information and detailed cooking instructions based on the generated cooking menu.

[0985] The "means for obtaining feedback information" refers to a means for obtaining feedback information such as user's impressions and suggestions for improvement regarding the provided food menu.

[0986] "Means for reflecting improvements to the food menu" refers to the means for improving and optimizing the food menu for future meals based on the obtained feedback information.

[0987] The "means for delivering cooked food" refers to a means for delivering food cooked based on the generated cooking menu to the user.

[0988] The system of the present invention acquires a user's vital data, food preference data, and emotional data, and uses this data to generate, provide, and improve healthy and satisfying food menus, and delivers the cooked meals. This system operates in cooperation with the user, terminal, and server.

[0989] First, the user launches the application using a device (e.g., a smartphone) and inputs their personal vital data (weight, blood pressure, blood sugar level, etc.). Next, they input data about the user's favorite dishes, memorable dishes they have eaten in the past, and taste preferences. Furthermore, to obtain emotional data, the emotion engine analyzes emotions from facial expressions and voice.

[0990] The device sends the vital data, preference data, and emotional data entered by the user to a server on the cloud. The server uses the acquired data to generate an optimal meal menu that matches the user's health condition and preferences. This generation process is carried out using a generative AI model (e.g., OpenAI GPT-4). By taking into account the nutrients necessary for health promotion and the user's taste preferences, and also reflecting the user's current emotional state, the system proposes a meal menu that is emotionally satisfying.

[0991] The server sends the generated cooking menu to the device. The cooking menu includes specific ingredient measurements (grams, tablespoons, teaspoons) and detailed cooking instructions. If necessary, the server can also generate cooking instructions as videos and provide them to the device, making it easier for users to understand visually.

[0992] The device also has the ability to link with the user's IoT-enabled cooking appliances, allowing the appliance to automatically set its temperature and time, for example, so that a smart oven can heat food at the appropriate temperature and time.

[0993] After cooking is complete, the user tastes the dish and provides feedback to the app on their impressions and areas for improvement. Once the user enters their feedback, the information is sent back to the server. The server analyzes the collected feedback and emotional data and updates the generative AI model. This will be reflected in future menu suggestions, enabling the app to provide a more satisfying dining experience.

[0994] Furthermore, the system also provides a means for delivering cooked dishes based on the generated menu, allowing users to immediately try the suggested dishes, improving convenience.

[0995] Specific examples

[0996] For example, consider a case where a user inputs vital data such as weight 70 kg, blood pressure 130 / 85 mmHg, and blood sugar level 100 mg / dL, and selects "spicy curry rice" as their favorite dish. If the emotion engine analyzes the user as "feeling stressed," the server will suggest relaxing herbal tea and spicy curry rice. The user selects this menu, and the cooked food is delivered through the ordering process.

[0997] Prompt Sentence Examples

[0998] "The user's weight is 70 kg, blood pressure is 130 / 85 mmHg, blood sugar level is 100 mg / dL, favorite food is spicy curry rice, and they are feeling stressed. Based on this information, please suggest a meal menu that will have a relaxing effect."

[0999] ---

[1000] The system aims to balance user health and food satisfaction, and by utilizing a variety of data, it provides a more personalized dining experience.

[1001] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1002] Step 1:

[1003] The user starts the application on the device and inputs vital data. Specifically, the user enters health data such as weight, blood pressure, and blood sugar level into the device through an input form. The input at this point is the user's vital data.

[1004] Step 2:

[1005] The user inputs data about their favorite dishes, dishes they have eaten in the past, and taste preferences into the terminal. For example, spicy curry rice is input as a favorite dish. This data is acquired as the user's food preference data.

[1006] Step 3:

[1007] The emotion engine operates and acquires emotion data from the user's facial expressions and voice. The device uses a camera and microphone to capture the user's facial expressions and voice, and the emotion engine analyzes them to acquire the user's current emotional state. This data is the user's emotion data.

[1008] Step 4:

[1009] The device sends the acquired vital data, food preference data, and emotional data to a server on the cloud. The input here is a collection of each data, and the device then sends it to the cloud.

[1010] Step 5:

[1011] The server analyzes the received data and generates an optimal cooking menu using a generative AI model. The server generates a cooking menu that takes into account the nutrients necessary for health promotion and the user's preferences based on the user's vital data, food preference data, and emotional data. This process uses a generative AI model.

[1012] Step 6:

[1013] The server sends the generated menu to the terminal, which then visually displays it to the user, including specific ingredient measurements and detailed cooking instructions.

[1014] Step 7:

[1015] The device generates a video of the cooking method sent from the server as needed and provides it to the user, making it easier for the user to visually understand the cooking procedure.

[1016] Step 8:

[1017] The device connects to IoT-enabled cooking appliances and automatically sets the appropriate cooking temperature and time, allowing users to cook easily.

[1018] Step 9:

[1019] After cooking is complete, the user tastes the dish and provides feedback on their impressions and suggestions for improvement to the device, which then records the feedback as user input.

[1020] Step 10:

[1021] The device then sends the collected feedback information and emotion data back to the server, which uses it to update the generative AI model and reflect it in future menu suggestions.

[1022] Step 11:

[1023] The server delivers cooked dishes based on the cooking menu it generates, allowing users to immediately try the suggested dishes. This operation provides convenience to users.

[1024] 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.

[1025] 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.

[1026] 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.

[1027] [Fourth embodiment]

[1028] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1029] 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.

[1030] 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).

[1031] 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.

[1032] 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.

[1033] 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).

[1034] 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.

[1035] 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.

[1036] 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.

[1037] 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.

[1038] 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.

[1039] 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.

[1040] 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."

[1041] The system of the present invention acquires a user's vital data and food preference data, and based on that data, generates, provides, and improves healthy and delicious food menus. This system operates in cooperation with the user, terminal, and server.

[1042] First, the user launches the application and enters their vital data (e.g., weight, blood pressure, blood sugar level, etc.) into the app. Then, they also enter data about their favorite dishes, memorable dishes they have eaten in the past, and taste preferences. This allows the app to clarify the user's individual health condition and food preferences.

[1043] The terminal (smartphone, tablet, etc.) sends vital data and preference data entered by the user to a server on the cloud. The server generates the optimal meal menu for the user based on the received data. This process is carried out by an AI model, which selects a meal menu that matches the nutrients necessary for health promotion and the user's preferences.

[1044] The server then sends the generated cooking menu to the device. The cooking menu includes specific ingredient measurements (in grams or tablespoons / teaspoons) and cooking instructions. If necessary, the server can also generate a video of the cooking instructions and provide it to the device, helping users to understand the menu visually.

[1045] The device also has the ability to link with the user's IoT-enabled kitchen appliances, allowing them to automatically set their cooking appliances, for example, a smart oven to heat at the appropriate temperature and time.

[1046] After cooking is complete, the user tastes the dish and provides feedback to the app on their impressions and suggestions for improvement. Once the user enters their feedback, the information is sent back to the server. The server analyzes the collected feedback and improves the AI ​​model. This will enable the app to generate future meal menus that better suit the user's preferences and health.

[1047] As a concrete example, consider the case where a user inputs vital data such as weight 70 kg, blood pressure 130 / 85, and blood sugar level 100 mg / dL, and selects "spicy curry rice" as their favorite dish. The server generates a spicy curry rice recipe that suits the user's preferences while taking into account weight and blood pressure and selecting ingredients with the appropriate nutrients. For example, it provides specific ingredients such as 200 g of chicken, 50 g of carrots, 1 tablespoon of turmeric, and 1 teaspoon of cumin, along with cooking instructions. The server then receives feedback to adjust the spiciness and reflects this in the next recipe generation.

[1048] In this way, the system of the present invention provides healthy and delicious meal menus based on the user's vital data and preferences, promoting the user's health and improving the quality of the food they eat.

[1049] The processing flow will be explained below.

[1050] Step 1:

[1051] A user launches the application and inputs their personal vital data (e.g., weight, blood pressure, blood sugar level, etc.) The user also inputs data about their favorite dishes, memories of dishes they have eaten in the past, and taste preferences.

[1052] Step 2:

[1053] The device receives vital data and preference data entered by the user and sends it to a server on the cloud.

[1054] Step 3:

[1055] The server analyzes the received vital data and preference data and generates an optimal menu based on the user's health condition and preferences. The generative AI model takes into account the nutrients necessary for health promotion and the user's taste preferences.

[1056] Step 4:

[1057] The server generates a cooking menu and sends it to the device, which includes specific ingredient measurements (in grams, tablespoons, or teaspoons) and detailed cooking instructions.

[1058] Step 5:

[1059] The terminal displays the received menu and cooking instructions to the user, and also provides the cooking instructions generated by the server as a video to the terminal for easy visual understanding.

[1060] Step 6:

[1061] The device cooks food according to the menu provided by the user. When using IoT-enabled cooking appliances, the device will link with the appliance and automatically set the appropriate temperature and time.

[1062] Step 7:

[1063] Users taste the food and enter their feedback about the taste and health effects into the app, such as "I wish it was a little spicier."

[1064] Step 8:

[1065] The device sends the user's feedback to a server on the cloud.

[1066] Step 9:

[1067] The server analyzes the collected feedback and updates the generative AI model, which then reflects the feedback in the next menu suggestions, providing a menu that is more optimized in terms of both taste and health.

[1068] In this way, the user, terminal, and server work together at each step to create a system that provides healthy and delicious meals to users.

[1069] Example 1

[1070] 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."

[1071] In modern society, it is extremely important to provide meal menus tailored to each individual's health condition and food preferences. However, providing such menus generally requires specialized knowledge, and there are no systems that are easily accessible to many people. Furthermore, there is a lack of mechanisms for quickly responding to changes in the user's health condition and improving menus based on feedback. As a result, it is difficult to continuously provide meals that promote health and match preferences.

[1072] 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.

[1073] In this invention, the server includes a means for acquiring biometric data of the user, a means for acquiring food preference data, and a means for analyzing the acquired biometric data and preference data to generate an optimal meal menu, thereby providing an optimal meal menu based on the user's health condition and preferences, and making it possible to continuously improve the menu based on feedback.

[1074] "User Biometric Data" means objective medical measurements that indicate the user's health, such as weight, blood pressure, or blood sugar level.

[1075] "Food preference data" is information that indicates a user's personal food preferences, such as the type of food they like, the strength of the flavor, and the spiciness of the food.

[1076] "Means for analyzing acquired biometric data and preference data to generate an optimal meal menu" refers to a process or device that analyzes a user's biometric data and preference data and creates a nutritionally balanced meal menu appropriate for the user based on that data.

[1077] "Means for providing the generated meal menu" refers to a method or system for notifying and presenting the user with the meal menu generated through analysis.

[1078] "Means for providing cooking instructions" refers to a device or method that provides a user with specific cooking procedures and methods based on the provided meal menu.

[1079] "Means for obtaining feedback information and reflecting it in improving the meal menu" refers to a device or method for collecting user feedback and suggestions for improvement and improving the meal menu based on that feedback.

[1080] "Means for providing specific ingredient measurement information" refers to a system or method for indicating the exact amount of ingredients needed based on the generated meal menu.

[1081] "Video generation means" refers to a system or method for generating videos that visually show cooking methods and providing them to users.

[1082] The system of the present invention acquires a user's biometric data and food preference data, and then generates, provides, and improves an optimal meal menu based on that data. This system operates in cooperation with the user, terminal, and server.

[1083] First, the user launches the application using a device such as a smartphone or tablet. Within the application, the user enters their biometric data (weight, blood pressure, blood sugar level, etc.) and food preference data (favorite dishes, taste preferences, etc.). This clarifies the user's individual health condition and food preferences.

[1084] The device then sends the user's biometric and preference data to a cloud-based server, which then analyzes the received data using a generative AI model to generate a meal plan optimized for the user. This analysis includes algorithms that take into account the user's nutritional needs and preferences for better health.

[1085] As a concrete example, consider the case where a user inputs biometric data such as weight 70 kg, blood pressure 130 / 85, and blood sugar level 100 mg / dL, and selects "spicy curry rice" as their favorite dish. In this case, the server analyzes the user's data and generates a healthy spicy curry rice recipe. For example, it provides specific ingredients such as 200 g of chicken, 50 g of carrots, 1 tablespoon of turmeric, and 1 teaspoon of cumin, along with cooking instructions.

[1086] The server then sends the generated menu to the terminal. The terminal displays the received recipe information to the user. If necessary, it also generates a video of the cooking method to help the user visually understand the recipe. This video generation means is also executed on the server and provided to the terminal.

[1087] Furthermore, the device can also link with the user's IoT-enabled cooking appliances, enabling automated cooking, such as a smart oven heating food at the appropriate temperature and time.

[1088] After cooking is complete, users can taste the dish and provide feedback to the app on their impressions and suggestions for improvement. Once the user has entered their feedback, the information is sent back to the server, which analyzes the collected feedback and improves the generative AI model. This will enable the app to generate future meal menus that better suit the user's preferences and health.

[1089] Examples of prompts include:

[1090] "A user weighing 70 kg, with a blood pressure of 130 / 85 and a blood sugar level of 100 mg / dL has entered spicy curry rice as their favorite dish. Please generate a spicy curry rice recipe that suits the user's preferences while taking their health condition into consideration."

[1091] In this way, the system of the present invention provides a healthy and delicious meal menu based on the user's biometric data and preferences, promoting the user's health and improving the quality of their meals.

[1092] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1093] Step 1:

[1094] App launch

[1095] (Subject: User) The user launches an application on their smartphone or tablet. This action displays the login screen.

[1096] Input: User action (tap icon)

[1097] Output: Login screen displayed

[1098] Step 2:

[1099] Entering vital data

[1100] (Subject: User) The user enters their biometric data (weight, blood pressure, blood sugar level, etc.) into an input form within the application.

[1101] Input: Biometric data (e.g., weight 70 kg, blood pressure 130 / 85, blood sugar 100 mg / dL)

[1102] Output: Biometric data is stored within the application

[1103] Step 3:

[1104] Entering preference data

[1105] (Subject: User) The user enters their favorite dishes and taste preferences.

[1106] Input: Preference data (e.g., favorite dish "spicy curry rice")

[1107] Output: Preference data is saved in the application

[1108] Step 4:

[1109] Data transmission

[1110] (Subject: Device) The device sends the biometric and preference data entered by the user to a server in the cloud. The data is sent via Wi-Fi or mobile data.

[1111] Input: User-entered biometric and preference data

[1112] Output: Server receives data

[1113] Step 5:

[1114] Data reception

[1115] (Subject: Server) The server receives the biometric data and preference data sent from the terminal and stores them in a database.

[1116] Input: Submitted biometric and preference data

[1117] Output: User data stored in the database

[1118] Step 6:

[1119] Prompt generation

[1120] (Subject: Server) Based on the data received by the server, a prompt sentence is generated to be input into the generative AI model.

[1121] Input: Stored biometric and preference data

[1122] Output: Generated prompt text (e.g., "A user weighing 70 kg, with a blood pressure of 130 / 85 and a blood sugar level of 100 mg / dL has entered spicy curry rice as their favorite dish. Please generate a recipe for spicy curry rice that suits the user's preferences while taking their health condition into consideration.")

[1123] Step 7:

[1124] Input to AI model and analysis

[1125] (Subject: Server) The server inputs the prompt sentence into the generated AI model and performs analysis. As a result of the analysis, a meal menu that reflects the user's health condition and preferences is generated.

[1126] Input: Generated prompt text

[1127] Output: Meal menu as analysis result (e.g., 200g chicken, 50g carrots, 1 tablespoon turmeric, 1 teaspoon cumin)

[1128] Step 8:

[1129] Recipe Generation

[1130] (Subject: Server) The server converts the generated recipe into a concrete form (amount of ingredients, cooking steps).

[1131] Input: Meal menu as analysis result

[1132] Output: A specific recipe (e.g., 200g chicken, 50g carrots, 1 tablespoon turmeric, 1 teaspoon cumin, and cooking instructions)

[1133] Step 9:

[1134] Send recipe

[1135] (Subject: Server) The server sends the generated specific recipe to the terminal.

[1136] Input: A specific recipe

[1137] Output: Recipe data sent to the device

[1138] Step 10:

[1139] Recipe display

[1140] (Subject: Terminal) The terminal displays the received recipe to the user, allowing the user to check the recipe.

[1141] Input: Submitted recipe data

[1142] Output: The recipe displayed on the terminal screen

[1143] Step 11:

[1144] Cooking appliance linkage

[1145] (Subject: Device) The device sends instructions to IoT-enabled cooking appliances, such as setting a smart oven to the appropriate temperature and time.

[1146] Input: Cooking setting information based on recipe data

[1147] Output: Set cooking appliances

[1148] Step 12:

[1149] Feedback Input

[1150] (Subject: User) The user provides feedback to the app about their impressions and areas for improvement after cooking.

[1151] Input: Feedback information (e.g., "It was too spicy")

[1152] Output: Feedback information stored in the app

[1153] Step 13:

[1154] Send Feedback

[1155] (Subject: Terminal) The terminal sends the user's feedback to the server.

[1156] Input: Feedback information stored in the app

[1157] Output: Feedback information sent to the server

[1158] Step 14:

[1159] Feedback Analysis

[1160] (Subject: Server) The server analyzes the collected feedback and reflects it in improving the generative AI model.

[1161] Input: Submitted feedback information

[1162] Output: An updated generative AI model

[1163] In this way, the present invention provides a system that provides a healthy and delicious meal menu based on the user's biometric data and preferences, thereby promoting the user's health and improving the quality of their meals.

[1164] (Application example 1)

[1165] 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."

[1166] The present invention relates to a system that provides optimal food menus based on a user's individual health condition and taste preferences, and aims to provide an environment in which healthy and delicious food can be quickly enjoyed when ordering delivery of the food menu. Another objective is to improve user satisfaction by using feedback on the food menu.

[1167] 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.

[1168] In this invention, the server includes means for acquiring a user's vital data, means for acquiring food preference data, means for transmitting the acquired vital data and preference data to the cloud, means for analyzing the acquired data on the cloud server and generating an optimal food menu using a generative AI model, means for transmitting and providing the generated food menu to a terminal, means for placing a delivery order based on the generated food menu, means for providing cooking methods based on the provided food menu, and means for acquiring feedback information and reflecting it in improving the food menu. This makes it possible to order a food menu for delivery that matches the user's health condition and taste preferences, and to improve the menu based on subsequent feedback.

[1169] "Means for acquiring user's vital data" refers to a method or device for detecting, recording, and collecting data on the user's health status, such as weight, blood pressure, and blood sugar level.

[1170] "Means for acquiring food preference data" refers to a method or device for collecting information such as a user's preferred flavors and types of food, and records of food eaten in the past.

[1171] "Means for sending to the cloud" refers to a method or device for sending acquired data to a cloud server via the Internet.

[1172] A "server on the cloud" is a remote server on which computing resources are located that are accessible via the Internet.

[1173] "Means for analyzing acquired data and generating optimal dish menus using a generative AI model" refers to a method or device for analyzing collected user data using an algorithm or AI model to create optimal dish menus.

[1174] "Means for transmitting and providing to terminal" refers to a method or apparatus for transmitting the generated cooking menu to the end user's device and displaying it.

[1175] The "means for placing a delivery order" refers to a method or device for placing an order for food with a delivery company based on the created food menu.

[1176] The "means for providing cooking methods" refers to a method or device for presenting specific cooking procedures and methods to the user based on the generated cooking menu.

[1177] "Means for obtaining feedback information and reflecting it in improving the food menu" refers to a method or device for collecting user evaluations and suggestions for improvement, improving the generative AI model based on them, and using them to generate the next menu.

[1178] The system according to the present invention acquires and analyzes a user's vital data and food preference data, generates an optimal food menu based on the data, and places a delivery order. Specific embodiments will be described below.

[1179] First, the user launches the smartphone application and logs in to their account. Next, the user enters their vital data (e.g., weight, blood pressure, blood sugar level, etc.) and food preferences. This data is entered through the smartphone interface and sent to a server on the cloud.

[1180] Once the server receives this data, it analyzes it using a generative AI model built using machine learning libraries such as Python's TensorFlow and PyTorch to generate an optimal meal menu that matches the user's health status and preferences.

[1181] The generated menu includes specific ingredient measurements (e.g., 200g chicken, 50g carrots, 1 tablespoon turmeric, 1 teaspoon cumin) and cooking instructions. The server then sends the generated menu to the smartphone and serves it to the user.

[1182] When a user checks the menu and places a delivery order, the server manually or automatically places the order with the delivery company. For this purpose, an API is used to link the server and send the order information to the delivery system.

[1183] In addition, cooking instructions are provided in an easy-to-understand visual format and displayed as videos on a smartphone app, allowing users to easily and accurately follow the cooking steps.

[1184] After the food is delivered and the user samples it, they can provide feedback through the app. This feedback is then sent back to the cloud server and used to improve the AI ​​model. This allows the next time a menu is generated, it will be tailored to the user's preferences and health status.

[1185] As a concrete example, consider the case where a user inputs vital data such as weight 70 kg, blood pressure 130 / 85, and blood sugar level 100 mg / dL, and selects "spicy curry rice" as their favorite dish. The server generates a spicy curry rice recipe that suits the user's preferences, taking into account the user's weight and blood pressure and selecting ingredients with the appropriate nutrients. For example, it provides specific ingredients such as 200 g of chicken, 50 g of carrots, 1 tablespoon of turmeric, and 1 teaspoon of cumin, along with cooking instructions.

[1186] An example prompt is:

[1187] User weight: 70kg

[1188] Blood pressure: 130 / 85

[1189] Blood glucose level: 100 mg / dL

[1190] Favorite food: Spicy curry rice

[1191] Nutrients provided: High in protein, low in fat

[1192] Generate the appropriate food menu:

[1193] In this way, the system of the present invention can help users maintain their health and improve their satisfaction by generating and providing optimal meal menus based on the user's health condition and food preferences, and then delivering those meals.

[1194] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1195] Step 1:

[1196] The user starts the smartphone application and inputs their vital data (e.g., weight, blood pressure, blood sugar level, etc.) and food preference data. The vital data and preference data are input and recorded on the device.

[1197] Input: vital data, food preference data

[1198] Output: Dataset to send to cloud server

[1199] Step 2:

[1200] The device transmits the vital data and food preference data entered by the user to a cloud server via a secure communication protocol (e.g., HTTPS).

[1201] Input: Dataset obtained from user

[1202] Output: Data packets passed to the cloud server

[1203] Step 3:

[1204] The server analyzes the received data and uses a generative AI model (using TensorFlow or PyTorch, for example) to generate an optimal meal menu based on the user's health status and preferences.

[1205] Input: Dataset stored on a cloud server

[1206] Output: Optimal recipe (including specific ingredients and cooking methods)

[1207] Step 4:

[1208] The generated menu is sent from the server to the device, where it is displayed and provided to the user in a format that can be viewed on the device.

[1209] Input: Generated food menu

[1210] Output: A menu of dishes that the user can view on their device.

[1211] Step 5:

[1212] Users can check the menu and place a delivery order within the app. The order information is sent to the server, which then automatically sends it to the partner delivery company.

[1213] Input: User's order request

[1214] Output: A delivery order request is sent to the delivery company.

[1215] Step 6:

[1216] The user receives the food, samples it, and then provides feedback through the app.

[1217] Input: User feedback after tasting

[1218] Output: Feedback data sent to the cloud server

[1219] Step 7:

[1220] The server analyzes the feedback data and reflects it in the generative AI model, which improves the accuracy of future cooking menus.

[1221] Input: User feedback data

[1222] Output: An improved generative AI model

[1223] Thus, the present invention is a system that includes a series of steps to provide optimal food menus based on the user's health condition and food preference data, enable delivery orders, and improve the accuracy of the generative AI model based on feedback.

[1224] 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.

[1225] The system of the present invention acquires a user's vital data, food preference data, and user emotions, and generates, provides, and improves healthy and delicious food menus based on this data. This system operates in cooperation with the user, terminal, and server.

[1226] First, the user launches the application and inputs their personal vital data (e.g., weight, blood pressure, blood sugar level, etc.), their favorite dishes, memorable dishes they have eaten in the past, and taste preferences. In addition, an emotion engine is activated to obtain the user's emotional data. This emotion engine analyzes the user's facial expressions and voice to determine their current emotional state.

[1227] The device sends the vital data, preference data, and emotional data entered by the user to a server on the cloud. The server uses the received data to generate an optimal meal menu that matches the user's health condition and preferences. This process is performed using a generative AI model. By taking into account the nutrients necessary for health promotion and the user's taste preferences, and also reflecting the user's current emotional state, the system proposes a meal menu that is emotionally satisfying.

[1228] The server then sends the generated cooking menu to the device. The cooking menu includes specific ingredient measurements (grams, tablespoons, teaspoons) and detailed cooking instructions. If necessary, the server can also generate cooking instructions as videos and provide them to the device, making it easier for users to understand visually.

[1229] The device also has the ability to link with the user's IoT-enabled cooking appliances, allowing them to automatically set cooking appliances, such as a smart oven to heat at the appropriate temperature and time.

[1230] After cooking is complete, the user tastes the dish and provides feedback to the app on their impressions and suggestions for improvement. Once the user enters their feedback, the information is sent back to the server. The server analyzes the collected feedback and emotional data and updates the generative AI model, which is then reflected in future menu suggestions. By taking the user's emotional state into account, it is possible to provide a more fulfilling dining experience.

[1231] As a specific example, consider the case where a user inputs vital data such as weight 70 kg, blood pressure 130 / 85, and blood sugar level 100 mg / dL, and selects "spicy curry rice" as their favorite dish. Furthermore, suppose the user's emotion engine analyzes the user as "feeling stressed." The server generates a menu based on this vital data, preference data, and emotion data. In this case, the server may suggest relaxing herbal tea in addition to spicy curry rice to reduce the user's stress. For example, the server may provide specific ingredients such as 200 g of chicken, 50 g of carrots, 1 tablespoon of turmeric, and 1 teaspoon of cumin, along with cooking instructions. Additional feedback and emotion data is then collected and reflected in the next menu suggestion.

[1232] In this way, the system of the present invention promotes the user's health and improves the quality of the cooking experience by providing healthy and satisfying cooking menus based on the user's vital data, cooking preferences, and emotional data.

[1233] The processing flow will be explained below.

[1234] Step 1:

[1235] A user launches the application and inputs their personal vital data (e.g., weight, blood pressure, blood sugar level, etc.). The user also inputs data about their favorite dishes, dishes they have eaten in the past, and taste preferences.

[1236] Step 2:

[1237] The user uses a camera and microphone to provide facial expression and voice data to the emotion engine, which then analyzes this data to recognize the user's current emotional state (e.g., feeling stressed, relaxed, etc.).

[1238] Step 3:

[1239] The device transmits vital data, preference data, and emotional data input by the user to a server on the cloud.

[1240] Step 4:

[1241] The server analyzes the received data and generates an optimal meal menu based on the user's health condition, preferences, and emotional state. The generative AI model selects a meal menu that reflects the nutrients necessary for health promotion, the user's taste preferences, and emotional satisfaction.

[1242] Step 5:

[1243] The server generates a cooking menu and sends it to the device, which includes the specific ingredient measurements (in grams, tablespoons, or teaspoons) and detailed cooking instructions.

[1244] Step 6:

[1245] The terminal displays the received menu and cooking instructions to the user. The server also generates a video of the cooking instructions to make them easier to understand visually and provides it to the terminal.

[1246] Step 7:

[1247] The device cooks food according to the menu provided by the user. When using IoT-enabled cooking appliances, the device automatically connects to the appliance and sets the appropriate temperature and time.

[1248] Step 8:

[1249] Users taste the food and enter their feedback about its taste and health effects into the app, such as "I wish it was a little spicier" or "This dish helped me relax."

[1250] Step 9:

[1251] The device sends user feedback and emotional data to a server on the cloud.

[1252] Step 10:

[1253] The server analyzes the collected feedback and emotional data and updates the generative AI model, which then reflects the feedback and emotional data in the next menu suggestion, providing a more optimized menu.

[1254] In this way, the user, terminal, and server work together at each step to create a system that provides healthy, emotionally satisfying meals to the user.

[1255] Example 2

[1256] 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."

[1257] Conventional food recommendation systems have difficulty providing food menus that take into account the user's health condition and preferences, and do not provide food recommendations that reflect the user's emotional state. This makes it difficult for users to find healthy and satisfying food menus, and there is a lack of suggestions that meet individual needs. Furthermore, feedback information is not fully utilized, and system improvements are not being made effectively.

[1258] 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.

[1259] In this invention, the server includes a means for acquiring biometric data of the user, a means for acquiring preference data, and a means for acquiring emotional data of the user, thereby enabling the server to propose optimal cooking menus that reflect the user's health condition, preferences, and emotional state.

[1260] "User's biometric data" refers to numerical data that indicates the user's health condition, such as weight, blood pressure, and blood sugar level.

[1261] "Preference data" is information about the user's food preferences, such as favorite dishes, memorable dishes they have eaten in the past, and taste preferences.

[1262] "User emotional data" is data that indicates the user's current emotional state, obtained by analyzing the user's facial expressions and voice.

[1263] A "generative AI model" is an algorithm that generates optimal cooking menus based on a user's biometric data, preference data, and emotional data.

[1264] A "prompt sentence" is an input sentence that gives instructions to the generative AI model for generating a menu.

[1265] The "means for providing cooking instructions" is a method for presenting specific cooking steps to the user based on the generated cooking menu.

[1266] "Feedback information" refers to information about users' impressions of the food after tasting it and areas for improvement.

[1267] The "video generation means" is a method for creating a video that visually presents cooking methods based on the generated cooking menu.

[1268] The system of the present invention acquires a user's biometric data, preference data, and emotional data, and then generates, provides, and improves healthy and delicious food menus based on this data. This system operates in cooperation with the user, terminal, and server.

[1269] First, the user launches an application on a device such as a smartphone or tablet. This application runs on a mobile OS such as iOS or Android. The user then enters their personal biometric data (e.g., weight, blood pressure, blood sugar level, etc.). This data can be entered manually or automatically acquired from a Bluetooth-connected wearable device (e.g., a smartwatch). Next, the user enters preference data, such as their favorite dishes, dishes they have eaten in the past, and taste preferences.

[1270] Additionally, the emotion engine operates using the device's built-in camera and microphone. The emotion engine analyzes the user's emotional state from their facial expressions and voice, capturing this as emotion data. For example, it may determine that the user is "feeling stressed."

[1271] The device sends the acquired biometric data, preference data, and emotional data to a server on the cloud. Data is sent using the HTTPS protocol to ensure secure communication. The server analyzes the received data using a generative AI model (e.g., GPT-4). The generative AI model generates the optimal dish menu for the user based on the prompt text. An example of a prompt text is, "Please generate the optimal dish menu if the user is feeling stressed, has a weight of 70 kg, a blood pressure of 130 / 85, and a blood sugar level of 100 mg / dL, and prefers spicy curry rice."

[1272] The generative AI model considers the user's taste preferences and nutrients necessary for health promotion, and also reflects the user's current emotional state to suggest emotionally satisfying dishes. For example, it can suggest a relaxing herbal tea in addition to spicy curry rice. Specifically, it provides measurements of ingredients such as 200g of chicken, 50g of carrots, 1 tablespoon of turmeric, and 1 teaspoon of cumin, along with cooking instructions.

[1273] The server sends the generated menu to the device. The data includes specific ingredient measurements (e.g., grams, tablespoons, teaspoons) and detailed cooking instructions. If necessary, the server can also generate cooking instructions as videos and provide them to the device, making it easier for users to understand visually.

[1274] The device also has the ability to link with the user's IoT-enabled kitchen appliances, allowing them to automatically set their cooking appliances, for example, a smart oven to heat at the appropriate temperature and time.

[1275] After cooking is complete, the user tastes the dish and provides feedback to the app on their impressions and suggestions for improvement. Once the user enters their feedback, the information is sent back to the server. The server analyzes the collected feedback and emotional data and updates the generative AI model, which is then reflected in future menu suggestions. By taking the user's emotional state into account, it is possible to provide a more fulfilling dining experience.

[1276] In this way, the system of the present invention promotes the user's health and improves the quality of the cooking experience by providing healthy and satisfying cooking menus based on the user's biometric data, cooking preferences, and emotional data.

[1277] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1278] Step 1:

[1279] Data Entry

[1280] Users launch a dedicated application on their smartphone or tablet, which runs on a mobile operating system such as iOS or Android.

[1281] Users manually enter their personal biometric data (e.g., weight, blood pressure, blood glucose level, etc.) or it is automatically obtained from a Bluetooth-connected wearable device (e.g., a smartwatch).

[1282] The user also inputs preference data such as favorite dishes, memorable dishes they have eaten in the past, and taste preferences.

[1283] The emotion engine operates using the device's built-in camera and microphone to analyze the user's current emotional state from their facial expressions and voice.

[1284] How it works: The camera captures the user's facial expressions and the microphone records the user's voice. These data are processed in real time and output as emotional data, such as "I feel stressed."

[1285] Step 2:

[1286] Data transmission

[1287] The device collects biometric data, preference data, and emotional data and sends it to a cloud server. This data is generally sent in JSON format and is securely transmitted using the HTTPS protocol.

[1288] Specific operation: The device collects each piece of data, compiles it into a single JSON object, and sends an HTTPS request.

[1289] Step 3:

[1290] Data analysis and menu generation

[1291] The server analyzes the received biometric data, preference data, and emotion data.

[1292] A generative AI model (e.g., GPT-4) analyzes the prompt text based on the data and generates the optimal cooking menu.

[1293] Specific prompt: "Generate the best meal plan for the user if they are stressed, weigh 70 kg, have a blood pressure of 130 / 85, and have a blood sugar level of 100 mg / dL, and prefer spicy curry rice."

[1294] How it works: The generative AI model calculates necessary nutrients from biometric data, selects the type of food from preference data, and generates menus that take into account psychological effects from emotional data. For example, to reduce stress, it might suggest relaxing herbal tea in addition to spicy curry rice.

[1295] Step 4:

[1296] Menu offerings

[1297] The server sends the generated menu to the device, including the measurements of specific ingredients (e.g., 200g chicken, 50g carrots, 1 tablespoon turmeric, 1 teaspoon cumin) and detailed cooking instructions.

[1298] Specific operation: The server encodes the generated menu in JSON format and returns it to the device as an HTTP response.

[1299] Step 5:

[1300] IoT-enabled kitchen appliance integration

[1301] The device connects to the user's IoT-enabled cooking appliances (e.g., smart ovens), allowing the appliances to automatically cook food at the appropriate settings (e.g., temperature and time).

[1302] How it works: The device analyzes the cooking recipe and calls the API of the corresponding appliance to send the settings. For example, it sends a command to a smart oven to heat at 180 degrees for 30 minutes.

[1303] Step 6:

[1304] Feedback and Model Updates

[1305] Users can taste the food and provide feedback to the app on their impressions and suggestions for improvement, either as star ratings or text comments.

[1306] The device sends the feedback information to a server on the cloud.

[1307] The server analyzes the collected feedback and emotional data and updates the generative AI model, which is then reflected in future menu suggestions.

[1308] What it does: The server saves the new feedback data in a database and updates the learning algorithm of the generative AI model, which then uses the new data for the next proposal.

[1309] (Application example 2)

[1310] 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."

[1311] Conventional food menu suggestion systems generally rely on a user's vital data and preference data, but because they do not take emotional data into account, it is difficult to suggest optimal food menus based on the user's psychological state. Furthermore, they lack support for actually cooking the suggested dishes, resulting in low user convenience. Another problem is that suggested dishes cannot be tried immediately. To address these issues, a system is needed that can suggest food menus based on the user's psychological state and actually deliver them, providing a healthier and more satisfying dining experience.

[1312] 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.

[1313] In this invention, the server includes means for acquiring vital data of the user, means for acquiring preference data of the user, means for acquiring emotional data of the user, means for analyzing the acquired vital data, preference data, and emotional data to generate an optimal dish menu, means for providing the generated dish menu, means for providing cooking methods based on the provided dish menu, means for acquiring feedback information and reflecting it in improving the dish menu, and means for delivering cooked dishes. This makes it possible to propose an optimal dish menu that takes into consideration both the user's health and psychological state, and furthermore, by promptly delivering and providing the dish, a more satisfying dining experience can be realized.

[1314] "User vital data" refers to physiological data that indicates the user's health status, such as weight, blood pressure, and blood sugar level.

[1315] "Cooking preference data" refers to data about the user's favorite dishes, memorable dishes they have eaten in the past, and their taste preferences.

[1316] "User emotional data" is data that indicates the user's current emotional state, analyzed from their facial expressions and voice.

[1317] The "means for generating a cooking menu" refers to a technical means for analyzing a user's vital data, preference data, and emotional data to generate an optimal cooking menu.

[1318] "Means for providing a food menu" refers to means for displaying and notifying the user of the generated food menu.

[1319] The "means for providing cooking instructions" is a means for providing specific ingredient measurement information and detailed cooking instructions based on the generated cooking menu.

[1320] The "means for obtaining feedback information" refers to a means for obtaining feedback information such as user's impressions and suggestions for improvement regarding the provided food menu.

[1321] "Means for reflecting improvements to the food menu" refers to the means for improving and optimizing the food menu for future meals based on the obtained feedback information.

[1322] The "means for delivering cooked food" refers to a means for delivering food cooked based on the generated cooking menu to the user.

[1323] The system of the present invention acquires a user's vital data, food preference data, and emotional data, and uses this data to generate, provide, and improve healthy and satisfying food menus, and delivers the cooked meals. This system operates in cooperation with the user, terminal, and server.

[1324] First, the user launches the application using a device (e.g., a smartphone) and inputs their personal vital data (weight, blood pressure, blood sugar level, etc.). Next, they input data about the user's favorite dishes, memorable dishes they have eaten in the past, and taste preferences. Furthermore, to obtain emotional data, the emotion engine analyzes emotions from facial expressions and voice.

[1325] The device sends the vital data, preference data, and emotional data entered by the user to a server on the cloud. The server uses the acquired data to generate an optimal meal menu that matches the user's health condition and preferences. This generation process is carried out using a generative AI model (e.g., OpenAI GPT-4). By taking into account the nutrients necessary for health promotion and the user's taste preferences, and also reflecting the user's current emotional state, the system proposes a meal menu that is emotionally satisfying.

[1326] The server sends the generated cooking menu to the device. The cooking menu includes specific ingredient measurements (grams, tablespoons, teaspoons) and detailed cooking instructions. If necessary, the server can also generate cooking instructions as videos and provide them to the device, making it easier for users to understand visually.

[1327] The device also has the ability to link with the user's IoT-enabled cooking appliances, allowing the appliance to automatically set its temperature and time, for example, so that a smart oven can heat food at the appropriate temperature and time.

[1328] After cooking is complete, the user tastes the dish and provides feedback to the app on their impressions and areas for improvement. Once the user enters their feedback, the information is sent back to the server. The server analyzes the collected feedback and emotional data and updates the generative AI model. This will be reflected in future menu suggestions, enabling the app to provide a more satisfying dining experience.

[1329] Furthermore, the system also provides a means for delivering cooked dishes based on the generated menu, allowing users to immediately try the suggested dishes, improving convenience.

[1330] Specific examples

[1331] For example, consider a case where a user inputs vital data such as weight 70 kg, blood pressure 130 / 85 mmHg, and blood sugar level 100 mg / dL, and selects "spicy curry rice" as their favorite dish. If the emotion engine analyzes the user as "feeling stressed," the server will suggest relaxing herbal tea and spicy curry rice. The user selects this menu, and the cooked food is delivered through the ordering process.

[1332] Prompt Sentence Examples

[1333] "The user's weight is 70 kg, blood pressure is 130 / 85 mmHg, blood sugar level is 100 mg / dL, favorite food is spicy curry rice, and they are feeling stressed. Based on this information, please suggest a meal menu that will have a relaxing effect."

[1334] ---

[1335] The system aims to balance user health and food satisfaction, and by utilizing a variety of data, it provides a more personalized dining experience.

[1336] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1337] Step 1:

[1338] The user starts the application on the device and inputs vital data. Specifically, the user enters health data such as weight, blood pressure, and blood sugar level into the device through an input form. The input at this point is the user's vital data.

[1339] Step 2:

[1340] The user inputs data about their favorite dishes, dishes they have eaten in the past, and taste preferences into the terminal. For example, spicy curry rice is input as a favorite dish. This data is acquired as the user's food preference data.

[1341] Step 3:

[1342] The emotion engine operates and acquires emotion data from the user's facial expressions and voice. The device uses a camera and microphone to capture the user's facial expressions and voice, and the emotion engine analyzes them to acquire the user's current emotional state. This data is the user's emotion data.

[1343] Step 4:

[1344] The device sends the acquired vital data, food preference data, and emotional data to a server on the cloud. The input here is a collection of each data, and the device then sends it to the cloud.

[1345] Step 5:

[1346] The server analyzes the received data and generates an optimal cooking menu using a generative AI model. The server generates a cooking menu that takes into account the nutrients necessary for health promotion and the user's preferences based on the user's vital data, food preference data, and emotional data. This process uses a generative AI model.

[1347] Step 6:

[1348] The server sends the generated menu to the terminal, which then visually displays it to the user, including specific ingredient measurements and detailed cooking instructions.

[1349] Step 7:

[1350] The device generates a video of the cooking method sent from the server as needed and provides it to the user, making it easier for the user to visually understand the cooking procedure.

[1351] Step 8:

[1352] The device connects to IoT-enabled cooking appliances and automatically sets the appropriate cooking temperature and time, allowing users to cook easily.

[1353] Step 9:

[1354] After cooking is complete, the user tastes the dish and provides feedback on their impressions and suggestions for improvement to the device, which then records the feedback as user input.

[1355] Step 10:

[1356] The device then sends the collected feedback information and emotion data back to the server, which uses it to update the generative AI model and reflect it in future menu suggestions.

[1357] Step 11:

[1358] The server delivers cooked dishes based on the cooking menu it generates, allowing users to immediately try the suggested dishes. This operation provides convenience to users.

[1359] 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.

[1360] 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.

[1361] 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.

[1362] 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.

[1363] 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.

[1364] 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.

[1365] 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).

[1366] 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.

[1367] 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."

[1368] 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.

[1369] 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).

[1370] 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.

[1371] 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.

[1372] 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.

[1373] 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.

[1374] 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.

[1375] 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.

[1376] 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.

[1377] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1378] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1379] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1380] The following is further disclosed regarding the above embodiment.

[1381] (Claim 1)

[1382] a means for obtaining vital data of the user;

[1383] A means for acquiring food preference data;

[1384] A means for analyzing the acquired vital data and preference data to generate an optimal cooking menu;

[1385] a means for providing the generated food menu;

[1386] A means for providing a cooking method based on a provided food menu;

[1387] A means of obtaining feedback information and reflecting it in improving the food menu;

[1388] A system including:

[1389] (Claim 2)

[1390] 10. The system of claim 1, further comprising means for providing specific measurement information for ingredients based on the generated cooking menu.

[1391] (Claim 3)

[1392] The system according to claim 1, further comprising video generation means for visually presenting cooking methods based on the generated cooking menu.

[1393] (Claim 4)

[1394] The system of claim 1, further comprising a machine learning model for automatically improving the generated cooking menu based on the feedback information.

[1395] (Claim 5)

[1396] The system according to claim 1, further comprising means for linking with an IoT-enabled cooking appliance in providing the cooking method.

[1397] "Example 1"

[1398] (Claim 1)

[1399] a means for acquiring biometric data of a user;

[1400] a means for acquiring dietary preference data;

[1401] A means for analyzing the acquired biometric data and preference data to generate an optimal meal menu;

[1402] A means for providing the generated meal menu;

[1403] A means for providing a cooking method based on the provided meal menu;

[1404] A means of obtaining feedback information and reflecting it in improving the meal menu;

[1405] A system including:

[1406] (Claim 2)

[1407] 10. The system of claim 1, further comprising means for providing specific measurement information for ingredients based on the generated meal menu.

[1408] (Claim 3)

[1409] The system according to claim 1, further comprising an animation generating means for visually presenting cooking methods based on the generated meal menu.

[1410] "Application Example 1"

[1411] (Claim 1)

[1412] a means for obtaining vital data of the user;

[1413] A means for acquiring food preference data;

[1414] means for transmitting the acquired vital data and preference data to a cloud;

[1415] A method for analyzing the acquired data on a cloud server and generating the optimal cooking menu using a generative AI model;

[1416] means for transmitting and providing the generated menu to a terminal;

[1417] A means for placing a delivery order based on the generated food menu;

[1418] A means for providing a cooking method based on a provided food menu;

[1419] A means of obtaining feedback information and reflecting it in improving the food menu;

[1420] A system including:

[1421] (Claim 2)

[1422] 10. The system of claim 1, further comprising means for providing specific measurement information for ingredients based on the generated cooking menu.

[1423] (Claim 3)

[1424] 2. The system according to claim 1, further comprising video generation means for visually presenting cooking methods based on the generated cooking menu.

[1425] "Example 2: Combining Emotion Engines"

[1426] (Claim 1)

[1427] a means for acquiring biometric data of a user;

[1428] a means for obtaining preference data;

[1429] A means for acquiring user emotion data;

[1430] A means for analyzing the acquired biometric data, preference data, and emotion data to generate an optimal cooking menu;

[1431] a means for providing the generated food menu;

[1432] A means for providing a cooking method based on a provided food menu;

[1433] A means of obtaining feedback information and reflecting it in improving the food menu;

[1434] A system including:

[1435] (Claim 2)

[1436] 10. The system of claim 1, further comprising means for providing specific measurement information for ingredients based on the generated cooking menu.

[1437] (Claim 3)

[1438] The system according to claim 1, further comprising video generation means for visually presenting cooking methods based on the generated cooking menu.

[1439] "Application example 2 when combining emotion engines"

[1440] (Claim 1)

[1441] a means for obtaining vital data of the user;

[1442] A means for acquiring food preference data;

[1443] A means for acquiring user emotion data;

[1444] A means for analyzing the acquired vital data, preference data, and emotion data to generate an optimal cooking menu;

[1445] a means for providing the generated food menu;

[1446] A means for providing a cooking method based on a provided food menu;

[1447] A means of obtaining feedback information and reflecting it in improving the food menu;

[1448] a means of delivering cooked meals;

[1449] A system including:

[1450] (Claim 2)

[1451] 10. The system of claim 1, further comprising means for providing specific measurement information for ingredients based on the generated cooking menu.

[1452] (Claim 3)

[1453] The system according to claim 1, further comprising video generation means for visually presenting cooking methods based on the generated cooking menu. [Explanation of symbols]

[1454] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for obtaining vital data of the user; A means for acquiring food preference data; A means for analyzing the acquired vital data and preference data to generate an optimal cooking menu; a means for providing the generated food menu; A means for providing a cooking method based on a provided food menu; A means of obtaining feedback information and reflecting it in improving the food menu; A system including:

2. 10. The system of claim 1, further comprising means for providing specific measurement information for ingredients based on the generated cooking menu.

3. The system according to claim 1, further comprising an animation generating means for visually presenting cooking methods based on the generated cooking menu.

4. The system of claim 1 , further comprising a machine learning model for automatically improving the generated cooking menu based on the feedback information.

5. The system according to claim 1 , further comprising means for linking with an IoT-enabled cooking appliance in providing the cooking method.

Images