System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting preferences, dietary history, and allergy information of a user; means for training a generative AI model based on a profile of the user; means for generating a recipe that meets conditions desired by the user using the trained generative AI model; means for providing the generated recipe to the user; and means for collecting feedback from the user to improve accuracy of the generative AI model.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] Conventional recipe provision methods lack personalization that takes into account individual users' preferences, dietary history, and allergy information. Additionally, dual-income households and single people face challenges such as a lack of cooking ideas, monotony in meals, and difficulty finding recipes that accommodate individual dietary restrictions. The present invention aims to solve these problems and provide original recipes tailored to individual users. [Means for solving the problem]

[0005] The present invention relates to a system that includes a means for collecting user preferences, dietary history, and allergy information, a means for training a generative AI model based on the user's profile, a means for generating recipes that meet the user's desired conditions using the trained generative AI model, a means for providing the generated recipes to the user, and a means for collecting user feedback and improving the accuracy of the generative AI model. This system provides recipes optimized for each user, enabling meal preparation tailored to individual needs. Furthermore, by including a means for generating recipes that take into account the time required and the ease of obtaining ingredients, the system can provide recipes that users can easily try. Furthermore, by utilizing a database that stores user profiles and feedback, data can be acquired and reflected in the generative AI model, enabling continuous improvement and providing more accurate recipes.

[0006] A "user" is an individual or group who utilizes the system to provide preference, dietary history, and allergy information and receive original recipes.

[0007] "Preferences" refers to information that indicates the user's preferences, such as ingredients, types of dishes, and taste tendencies that they particularly like.

[0008] "Dietary history" refers to records of meals the user has eaten in the past, as well as information about meal frequency and patterns.

[0009] "Allergy information" is information that indicates whether the user has an allergic reaction to a particular food ingredient.

[0010] A "generative AI model" is an artificial intelligence model that learns profile information collected from users and generates optimal recipes based on that data.

[0011] A "database" is an information organization system for storing and managing user preferences, dietary history, allergy information, and feedback.

[0012] A "recipe" is information that provides specific instructions for a user to prepare a dish, including specific ingredients and cooking procedures.

[0013] "Feedback" is information about user feedback and suggestions for improvement regarding the generated recipe.

[0014] "Time required" is information that indicates the time required to complete a particular recipe.

[0015] "Difficulty of obtaining ingredients" is a criterion for evaluating the ease or difficulty of obtaining ingredients required for a recipe.

[0016] "Personalization" refers to customizing to suit the preferences and needs of individual users. [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 present invention relates to a system that collects and analyzes user preferences, dietary history, and allergy information, and provides recipes optimized for each individual user.

[0039] Server embodiment

[0040] The server has the following main functions:

[0041] 1. Collecting and storing user profiles

[0042] The server receives the user's preferences, dietary history, and allergy information sent from the terminal.

[0043] The received information is stored in a database.

[0044] Example: If a user provides information such as "I'm a vegetarian and I have a peanut allergy," the server stores that information in a database.

[0045] 2. Training the generative AI model

[0046] The server trains a generative AI model based on the collected user profiles.

[0047] Example: Based on a user's preference information such as "I like spicy food," the model learns patterns of spicy ingredients and recipes.

[0048] 3. Recipe Generation

[0049] The server uses the learned generative AI model to generate recipes that meet the user's desired conditions (time required, type of ingredients, etc.).

[0050] Example: If a user requests a vegetarian meal that can be prepared in under 30 minutes, the server generates a recipe that reflects that request.

[0051] 4. Providing recipes

[0052] The server sends the generated original recipe to the terminal.

[0053] Example: Send a server-generated recipe for "vegetarian pasta that can be made in under 30 minutes."

[0054] 5. Collect and use feedback

[0055] The server receives feedback from users and uses it to retrain the generative AI model to improve its accuracy.

[0056] Example: If a user provides feedback such as "The vegetarian pasta was bland," that feedback is reflected as training data.

[0057] Terminal embodiment

[0058] The terminal acts as an interface with the user:

[0059] 1. Enter your user profile

[0060] The terminal provides a form for the user to input preferences, dietary history, and allergy information.

[0061] The entered profile information is sent to the server.

[0062] Example: A user enters the information "I am a vegetarian" into a terminal and presses the send button.

[0063] 2. Enter your recipe request

[0064] The terminal provides a form for the user to input desired recipe conditions (required time, type of ingredients, etc.).

[0065] The input request is sent to the server.

[0066] Example: A user enters information about a "vegetarian meal that can be prepared in under 30 minutes" and presses the submit button.

[0067] 3. View recipes

[0068] The terminal receives the original recipe sent from the server and displays it to the user.

[0069] Example: Display a recipe sent from the server for "vegetarian pasta that can be made in under 30 minutes."

[0070] 4. Enter your feedback

[0071] The terminal provides a form for users to enter feedback on the recipes they have created.

[0072] The input feedback information is sent to the server.

[0073] Example: A user enters feedback such as "The pasta was bland" and presses the submit button.

[0074] User's embodiment

[0075] Users use the system to receive recipes tailored to their personal tastes and requirements:

[0076] 1. Providing Profile Information

[0077] The user enters their preferences, dietary history, and allergy information into a form on the terminal.

[0078] Example: A user enters that they "follow a gluten-free diet."

[0079] 2. Specify recipe conditions

[0080] The user inputs the conditions of the desired recipe into a form on the terminal.

[0081] Example: A user requests a "gluten-free snack that can be made in under 10 minutes."

[0082] 3. Check the recipe and cook

[0083] The user checks the recipe displayed on the terminal and prepares the dish based on it.

[0084] Example: A user makes cookies based on the recipe for "10-Minute Gluten-Free Cookies" displayed on their device.

[0085] 4. Providing Feedback

[0086] Users enter their thoughts and suggestions for improvement about the recipe they have cooked into a form on their device and send the feedback to the server.

[0087] Example: A user provides feedback such as "I would prefer the cookies to be a little softer."

[0088] The processing flow will be explained below.

[0089] Server Processing

[0090] Step 1:

[0091] The server receives the user's preferences, dietary history, and allergy information sent from the terminal.

[0092] Step 2:

[0093] The server stores the received user profile information in a database.

[0094] Step 3:

[0095] The server retrieves the user profile from the database and inputs it into the generative AI model for learning.

[0096] Step 4:

[0097] The server receives the recipe conditions (required time, type of ingredients, etc.) sent from the terminal.

[0098] Step 5:

[0099] The server uses a generative AI model to generate recipes that fit the user's requirements, taking into account the difficulty of obtaining ingredients and the time required.

[0100] Step 6:

[0101] The server sends the generated recipe to the terminal.

[0102] Step 7:

[0103] The server receives the user feedback sent from the terminal.

[0104] Step 8:

[0105] The server stores the received feedback in a database and uses it to retrain the generative AI model to improve its accuracy.

[0106] Terminal handling

[0107] Step 1:

[0108] The terminal provides the user with a form to enter information about preferences, dietary history, and allergies.

[0109] Step 2:

[0110] The profile information entered by the user is sent to the server.

[0111] Step 3:

[0112] The terminal provides the user with a form for inputting the desired recipe conditions (required time, type of ingredients, etc.).

[0113] Step 4:

[0114] A recipe request entered by the user is sent to the server.

[0115] Step 5:

[0116] The terminal receives the original recipe sent from the server.

[0117] Step 6:

[0118] The terminal displays the received recipe in an easy-to-understand manner for the user.

[0119] Step 7:

[0120] The terminal provides the user with a form to enter feedback about the recipe.

[0121] Step 8:

[0122] Sends the user-entered feedback to the server.

[0123] User Action

[0124] Step 1:

[0125] Users enter their preferences, dietary history, and allergy information into a form on the terminal.

[0126] Step 2:

[0127] The user sends the entered profile information to the server.

[0128] Step 3:

[0129] The user inputs the desired recipe conditions into a form on the terminal.

[0130] Step 4:

[0131] The user inputs a recipe request and sends it to the server.

[0132] Step 5:

[0133] The user checks the recipe displayed on the terminal.

[0134] Step 6:

[0135] The user creates a dish based on the displayed recipe.

[0136] Step 7:

[0137] The user enters feedback about the created recipe into a form on the terminal.

[0138] Step 8:

[0139] The user sends the input feedback to the server.

[0140] Example 1

[0141] 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."

[0142] Conventional recipe provision systems have difficulty providing optimal recipes based on individual users' preferences, dietary history, and allergy information. Furthermore, they lack a mechanism for collecting user feedback to improve the system's accuracy, making it impossible to respond quickly and accurately to user needs. This has resulted in problems such as users having to spend time and effort searching for recipes that suit them.

[0143] 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.

[0144] In this invention, the server includes means for collecting user preferences, dietary history, and allergy information, means for training a generative AI model based on the user's profile, means for generating recipes that meet the user's desired conditions using the trained generative AI model, means for providing the generated recipes to the user, and means for collecting user feedback and improving the accuracy of the generative AI model. This makes it possible to quickly and accurately respond to the user's individual needs and provide optimal recipes. Furthermore, by generating recipes using prompts, recipes that meet the user's preferences can be quickly generated. Furthermore, by saving the user's profile and feedback, the accuracy of the system can be continuously improved.

[0145] "User preferences" refers to information about the user's favorite foods and cooking methods.

[0146] "Dietary history" refers to historical information about meals the user has taken in the past.

[0147] "Allergy information" refers to data about foods or ingredients to which a user has an allergic reaction.

[0148] A "generative AI model" is an artificial intelligence model that learns data and generates recipes based on the user's preferences and conditions.

[0149] "User profile" refers to personal data such as a user's preferences, dietary history, and allergy information.

[0150] A "recipe" is a list of instructions and ingredients for making a particular dish.

[0151] "Feedback" refers to the user's thoughts and evaluations of the system and recipes.

[0152] A "prompt" is a condition or instruction that is input to a generative AI model to generate a recipe.

[0153] A "database" is a system that organizes and stores collected information so that it can be searched and retrieved when needed.

[0154] A "server" is a computer system that collects, processes, stores, and serves information from users.

[0155] A "terminal" is a device that a user uses to enter information and receive generated recipes.

[0156] This invention relates to a system that collects and analyzes user preferences, dietary history, and allergy information to provide recipes optimized for each user. This system consists of three main elements: a server, a terminal, and a user.

[0157] Server embodiment

[0158] The server has the following features:

[0159] 1. Collecting and storing user profiles

[0160] The server receives the user's preferences, dietary history, and allergy information sent from the device and stores it in a database. For example, if a user provides information that they are "vegetarian and have a peanut allergy," the server stores that information in the database.

[0161] 2. Training the generative AI model

[0162] The server trains a generative AI model based on the collected user profile. For example, based on the user's preference information "I like spicy food," the model learns patterns of spicy ingredients and recipes.

[0163] 3. Recipe Generation

[0164] The server uses the learned generative AI model to generate recipes that meet the user's desired conditions (time required, type of ingredients, etc.). For example, if the user requests a "vegetarian dish that can be made in 30 minutes or less," the server generates a recipe that reflects those conditions. An example of a prompt sentence is "Please generate a recipe for a vegetarian dish that can be made in 30 minutes or less."

[0165] 4. Providing the generated recipe

[0166] The server sends the generated recipe to the device. For example, the server sends the generated recipe for "vegetarian pasta that can be made in 30 minutes or less" to the device.

[0167] 5. Collecting and Using Feedback

[0168] The server receives feedback from users and retrains the generative AI model to improve its accuracy. For example, if a user provides feedback such as "the vegetarian pasta was bland," the server incorporates this feedback into the training data.

[0169] Terminal embodiment

[0170] The terminal acts as an interface with the user:

[0171] 1. Enter your user information

[0172] The terminal provides a form for the user to input information about preferences, dietary history, and allergies, and transmits the input profile information to the server. For example, the user inputs information such as "I am a vegetarian" into the terminal and presses the send button.

[0173] 2. Enter recipe conditions

[0174] The terminal provides a form for the user to input the desired recipe conditions (time required, type of ingredients, etc.) and sends the input request to the server. For example, a user inputs information requesting "vegetarian dishes that can be made in 30 minutes or less" and presses the send button.

[0175] 3. View recipes

[0176] The device receives the original recipe sent from the server and displays it to the user. For example, the device displays a recipe for "vegetarian pasta that can be made in under 30 minutes."

[0177] 4. Enter your feedback

[0178] The terminal provides a form for the user to input feedback on the recipe created by the user, and transmits the input feedback information to the server. For example, the user inputs feedback such as "the pasta was bland" and presses the send button.

[0179] User's embodiment

[0180] To use the optimized recipe, users follow these steps:

[0181] 1. Providing Profile Information

[0182] The user enters their preferences, dietary history, and allergy information into a form on the terminal. For example, the user enters that they follow a gluten-free diet.

[0183] 2. Specify recipe conditions

[0184] The user inputs the desired recipe conditions into a form on the terminal. For example, the user specifies "a gluten-free snack that can be made in 10 minutes or less." An example of a prompt sentence is "Please generate a recipe for a gluten-free snack that can be made in 10 minutes or less."

[0185] 3. Check the recipe and cook

[0186] The user checks the recipe displayed on the device and prepares the dish based on it. For example, the user makes cookies based on the recipe for "10-minute gluten-free cookies" displayed on the device.

[0187] 4. Providing Feedback

[0188] The user inputs their thoughts and suggestions for improvement about the recipe into a form on the device and sends the feedback to the server. For example, the user inputs feedback such as "I wish the cookies were a little softer when baked."

[0189] By implementing this system, users can quickly and accurately receive recipes optimized for their preferences and conditions. In addition, by continuously collecting and incorporating feedback from users, the accuracy of the generative AI model can be improved, enabling the provision of better services.

[0190] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0191] Step 1:

[0192] Entering User Profile Information

[0193] The terminal displays a form for the user to enter preferences, dietary history, and allergy information.

[0194] The user enters information into the form displayed on the terminal and presses the "Submit" button.

[0195] Input: User preferences, dietary history, and allergy information (e.g., "I'm vegetarian and have a peanut allergy").

[0196] Output: The entered information is sent from the terminal to the server.

[0197] Specific operation: When the user clicks the "Submit" button, the input information is sent from the terminal to the server.

[0198] Step 2:

[0199] Submitting and storing profile information

[0200] The terminal transmits the information entered by the user to the server.

[0201] The server stores the received information in a database.

[0202] Input: User profile information (e.g., "I'm a vegetarian and have a peanut allergy").

[0203] Output: The information is stored in a database.

[0204] Specific operation: The server analyzes the received data and stores it in a database.

[0205] Step 3:

[0206] Training a generative AI model

[0207] The server trains the generative AI model based on user information stored in a database.

[0208] Input: User information stored in a database (e.g., "I like spicy food").

[0209] Output: A trained generative AI model.

[0210] How it works: The server inputs the stored data into the AI ​​model, allowing it to learn patterns.

[0211] Step 4:

[0212] Entering recipe conditions

[0213] The terminal provides a form for the user to input desired recipe conditions (required time, type of ingredients, etc.).

[0214] The user inputs the desired conditions and presses the "Submit" button.

[0215] Input: User recipe criteria (e.g., "vegetarian meals that can be made in under 30 minutes").

[0216] Output: The entered conditions are sent from the terminal to the server.

[0217] Specific operation: When the user clicks the "Send" button, the desired conditions are sent from the terminal to the server.

[0218] Step 5:

[0219] Sending and generating recipe conditions

[0220] The terminal transmits the input conditions to the server.

[0221] The server generates a recipe using a generative AI model based on the received conditions.

[0222] Input: User recipe criteria (e.g., "vegetarian meals that can be made in under 30 minutes").

[0223] Output: The generated recipe (e.g. "Vegetarian pasta in under 30 minutes").

[0224] Specific operation: The server provides the conditions as prompts to the generative AI model, which then generates the optimal recipe. An example of the prompt is, "Generate a vegetarian recipe that can be made in under 30 minutes."

[0225] Step 6:

[0226] Providing the generated recipe

[0227] The server transmits the generated recipe to the terminal.

[0228] The terminal displays the received recipe to the user.

[0229] Input: The generated recipe (e.g., "Vegetarian pasta in under 30 minutes").

[0230] Output: The recipe is printed to the terminal.

[0231] Specific behavior: The server sends the recipe to the device, and the device displays it to the user.

[0232] Step 7:

[0233] Enter your feedback

[0234] The terminal provides a form for users to enter feedback on the recipes they have created.

[0235] The user enters the feedback and presses the "Submit" button.

[0236] Input: User feedback (e.g., "The pasta was bland").

[0237] Output: The input feedback information is sent from the device to the server.

[0238] Specific operation: When the user clicks the "Submit" button, the feedback information is sent from the terminal to the server.

[0239] Step 8:

[0240] Send and save feedback

[0241] The terminal transmits the input feedback to the server.

[0242] The server stores the received feedback in a database.

[0243] Input: User feedback information (e.g., "The pasta was bland").

[0244] Output: The feedback information is stored in a database.

[0245] Specific behavior: The server analyzes the received feedback and stores it in a database.

[0246] Step 9:

[0247] Reflecting feedback

[0248] The server retrains the generative AI model based on the collected feedback, improving the model's accuracy.

[0249] Input: Feedback information stored in a database (e.g., "The pasta was bland").

[0250] Output: A generative AI model with improved accuracy.

[0251] Specific operation: The server inputs the feedback data into the AI ​​model and retrains the model.

[0252] (Application example 1)

[0253] 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."

[0254] Conventional food delivery systems have difficulty suggesting optimal dishes based on a user's individual preferences, allergies, and dietary history. Even if a system existed that provided recipes that matched a user's desired conditions, it was not possible to link the system directly from ordering to delivery. This made it difficult for users to easily enjoy dishes that suited their dietary habits. Furthermore, the system lacked sufficient functionality to reflect user feedback and improve the accuracy of recipes.

[0255] 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.

[0256] In this invention, the server includes a means for collecting user preferences, dietary history, and allergy information, a means for training a generative AI model based on the user's profile, and a means for generating recipes that meet the user's desired conditions using the trained generative AI model. This allows the user to receive individually optimized recipe suggestions. The server also includes a means for providing the generated recipes to the user and a means for collecting feedback from the user to improve the accuracy of the generative AI model. Furthermore, the server includes a means for suggesting individually optimized dishes based on the user's profile and a means for directly ordering the suggested dishes and delivering them to a specified address, allowing the user to easily order and quickly receive dishes that suit their diet. This system allows users to easily enjoy dishes tailored to their preferences and constraints, and further improves accuracy based on feedback.

[0257] "User preferences" refers to information about the dishes and ingredients that the user likes to eat.

[0258] "Dietary history" is a record of the foods and meals a user has eaten in the past.

[0259] "Allergy information" is information about foods and ingredients that cause allergic reactions to the user.

[0260] A "generative AI model" is a model that learns and is generated using artificial intelligence, and suggests optimal recipes based on the user's individual information.

[0261] "Profile" is a general term for personal information such as a user's preferences, dietary history, and allergy information.

[0262] A "recipe" is a guideline that shows the steps and ingredients for making a dish.

[0263] "Feedback" refers to the user's evaluation of the food they have provided and their suggestions for improvement.

[0264] "Delivery" is the process of delivering the food ordered by the user to the address specified.

[0265] A "means" is a method or device for achieving a specific function or purpose.

[0266] The system of this invention is realized through collaboration between a server and a terminal, and provides optimized meals based on the user's preferences, dietary history, and allergy information, and then handles the entire process from directly ordering the meals to delivery.

[0267] The server has the following main functions:

[0268] 1. Collecting user preferences, dietary history, and allergy information

[0269] The server receives the user's preferences, dietary history, and allergy information sent from the device and stores it in a database. For example, if a user provides information such as "I'm a vegetarian and have a peanut allergy," the server stores that information in the database.

[0270] 2. Training the generative AI model

[0271] The server trains a generative AI model based on the collected user profile information, allowing it to suggest dishes optimized for the user's preferences and conditions. For example, if a user has a preference for spicy food, the server can train the model to recommend spicy recipes.

[0272] 3. Recipe Generation

[0273] The server uses the trained generative AI model to generate recipes that meet the user's criteria. For example, for a request for "vegetarian dishes that can be made in under 30 minutes," it generates a recipe for vegetarian pasta.

[0274] 4. Providing recipes and taking orders

[0275] The generated recipe is sent from the server to the terminal, where the user can check it and order it directly. For example, a user can view the suggested vegetarian pasta recipe and order it if they like it.

[0276] 5. Collecting user feedback and improving model accuracy

[0277] When users send feedback about the food they've been served, the server collects it and uses it to retrain the generative AI model. For example, feedback like "the pasta was bland" can be reflected in the next recommendation.

[0278] The terminal has the following main functions:

[0279] 1. Enter your user profile

[0280] The device has a form where users can enter their preferences, allergy information, and dietary history, for example, "I'm a vegetarian and have a peanut allergy."

[0281] 2. Enter your recipe request

[0282] It provides a form where users can input their desired cooking criteria and send it to the server. For example, they can input criteria such as "vegetarian dishes that can be prepared in 30 minutes or less."

[0283] 3. View recipes and order

[0284] The recipe sent from the server is displayed on the device, and the user can check the recipe. Also, by pressing the order button, the user can directly order the dish. For example, a recipe for vegetarian pasta can be displayed and the user can order it.

[0285] 4. Enter your feedback

[0286] It has a form where users can enter their feedback about the food and send it to the server. For example, they can enter feedback such as "The pasta was bland."

[0287] As a concrete example, if a vegetarian user requests a dish that can be prepared in under 30 minutes, the server generates a recipe based on that condition and sends it to the device. The user then orders a dish based on the generated recipe and it is delivered. Feedback on the dish can then be sent from the device to improve the accuracy of the next suggestion.

[0288] Example prompt for a generative AI model:

[0289] Suggest the best recipes based on your user profile below.

[0290] Food preference: Vegetarian

[0291] Allergy Information: Peanuts

[0292] Time required: 30 minutes or less

[0293] Generate the best vegetarian, peanut-free recipe that can be made in under 30 minutes and meets the following criteria:

[0294] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0295] Step 1:

[0296] The user inputs and sends profile information (preferences, dietary history, allergy information) into the device. Input data: Information such as "I'm a vegetarian and have a peanut allergy." The input data is sent from the device to the server.

[0297] Step 2:

[0298] The server receives the user's profile information sent from the device and stores it in a database, which includes information on preferences, dietary history, and allergies.

[0299] Step 3:

[0300] The server trains the generative AI model based on the collected user profile information. Input data: User preferences, past dietary data, and allergy information. The generative AI model uses this data to learn how to suggest recipes.

[0301] Step 4:

[0302] The user inputs specific recipe requirements (time required, type of ingredients, etc.) from the terminal and sends them to the server. Input data: For example, desired requirements for a vegetarian dish that can be made in 30 minutes or less.

[0303] Step 5:

[0304] The server uses the trained generative AI model to generate recipes that best fit the user's desired conditions. Input data: the trained model and the user's request conditions. Output data: a vegetarian pasta recipe that can be made in under 30 minutes, for example.

[0305] Step 6:

[0306] The server sends the generated recipe to the terminal, which displays it to the user. Input data: Data on the generated recipe. Output data: Recipe display on the user's terminal screen.

[0307] Step 7:

[0308] The user checks the provided recipe and places an order. Input data: User's confirmation and order intention. The terminal sends the order information to the server.

[0309] Step 8:

[0310] The server accepts the user's order and arranges delivery to the specified address. Input data: User's order information and delivery address. Output data: Order processing and start of delivery procedure.

[0311] Step 9:

[0312] The user inputs feedback about the dish from the terminal and sends it to the server. Input data: Contents of the feedback (for example, "The pasta was bland").

[0313] Step 10:

[0314] The server receives feedback from users and uses it to retrain the generative AI model. Input data: Feedback information. Output data: Improved generative AI model.

[0315] 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.

[0316] This invention relates to a system that provides recipes optimized for individual users based on their preferences, dietary history, allergy information, and emotions. This system combines a generative AI model and an emotion engine to provide more personalized recipes.

[0317] Server embodiment

[0318] The server has the following main functions:

[0319] 1. Collecting and storing user profiles

[0320] The server receives the user's preferences, dietary history, and allergy information sent from the terminal.

[0321] The received information is stored in a database.

[0322] Example: If a user provides information such as "I'm a vegetarian and I have a peanut allergy," the server stores that information in a database.

[0323] 2. Training the generative AI model

[0324] The server trains a generative AI model based on the collected user profiles.

[0325] Example: Based on a user's preference information such as "I like spicy food," the model learns patterns of spicy ingredients and recipes.

[0326] 3. Recipe Generation

[0327] The server uses the learned generative AI model to generate recipes that meet the user's desired conditions (time required, type of ingredients, etc.).

[0328] Example: If a user requests a vegetarian meal that can be prepared in under 30 minutes, the server generates a recipe that reflects that request.

[0329] 4. Emotional Engine Adjustment

[0330] The server uses an emotion engine to recognize and analyze the user's emotions and adjusts the parameters of the generative AI model based on the results.

[0331] Example: If a user is feeling stressed, the emotion engine will adjust the generative AI model to suggest recipes that include ingredients and cooking methods that have a relaxing effect.

[0332] 5. Providing recipes

[0333] The server sends the generated original recipe to the terminal.

[0334] Example: Send a server-generated recipe for "vegetarian pasta that can be made in under 30 minutes."

[0335] 6. Collect and use feedback

[0336] The server receives feedback from users and uses it to retrain the generative AI model to improve its accuracy.

[0337] Example: If a user provides feedback such as "The vegetarian pasta was bland," that feedback is reflected as training data.

[0338] Terminal embodiment

[0339] The terminal acts as an interface with the user:

[0340] 1. Enter your user profile

[0341] The terminal provides a form for the user to input preferences, dietary history, and allergy information.

[0342] The entered profile information is sent to the server.

[0343] Example: A user enters the information "I am a vegetarian" into a terminal and presses the send button.

[0344] 2. Enter your recipe request

[0345] The terminal provides a form for the user to input desired recipe conditions (required time, type of ingredients, etc.).

[0346] The input request is sent to the server.

[0347] Example: A user enters information about a "vegetarian meal that can be prepared in under 30 minutes" and presses the submit button.

[0348] 3. View recipes

[0349] The terminal receives the original recipe sent from the server and displays it to the user.

[0350] Example: Display a recipe sent from the server for "vegetarian pasta that can be made in under 30 minutes."

[0351] 4. Entering Emotion Data

[0352] The device provides an interface for inputting and acquiring user emotions, which can be read using a facial recognition camera or voice assistant.

[0353] Example: The device reads the user's emotions through a facial recognition camera and transmits them to a server.

[0354] 5. Enter your feedback

[0355] The terminal provides a form for users to enter feedback on the recipes they have created.

[0356] The input feedback information is sent to the server.

[0357] Example: A user enters feedback such as "The pasta was bland" and presses the submit button.

[0358] User's embodiment

[0359] Users use the system to receive recipes tailored to their personal tastes and requirements:

[0360] 1. Providing Profile Information

[0361] The user enters their preferences, dietary history, and allergy information into a form on the terminal.

[0362] Example: A user enters that they "follow a gluten-free diet."

[0363] 2. Specify recipe conditions

[0364] The user inputs the desired recipe conditions into a form on the terminal.

[0365] Example: A user requests a "gluten-free snack that can be made in under 10 minutes."

[0366] 3. Providing Emotion Data

[0367] Users provide their emotional data through the device's interface, and in some cases emotion recognition is performed using a facial recognition camera or voice.

[0368] Example: When a user feels stressed, the emotional data is sent to the server via the device.

[0369] 4. Check the recipe and cook

[0370] The user checks the recipe displayed on the terminal and prepares the dish based on it.

[0371] Example: A user makes cookies based on the recipe for "10-Minute Gluten-Free Cookies" displayed on their device.

[0372] 5. Providing Feedback

[0373] Users enter their thoughts and suggestions for improvement about the recipe they have cooked into a form on their device and send the feedback to the server.

[0374] Example: A user provides feedback such as "I would prefer the cookies to be a little softer."

[0375] The processing flow will be explained below.

[0376] Server Processing

[0377] Step 1:

[0378] The server receives the user's preferences, dietary history, and allergy information sent from the terminal.

[0379] Step 2:

[0380] The server stores the received user profile information in a database.

[0381] Step 3:

[0382] The server retrieves the user profile from the database and inputs that information into the generative AI model to learn.

[0383] Step 4:

[0384] The server receives the recipe conditions (required time, type of ingredients, etc.) sent from the terminal.

[0385] Step 5:

[0386] The server uses a generative AI model to generate recipes that fit the user's requirements, taking into account the difficulty of obtaining ingredients and the time required.

[0387] Step 6:

[0388] The server uses an emotion engine to analyze the user's emotion data and reflects it in the recipe it generates.

[0389] Step 7:

[0390] The server sends the generated recipe to the terminal.

[0391] Step 8:

[0392] The server receives the user feedback sent from the terminal.

[0393] Step 9:

[0394] The server stores the received feedback in a database and uses it to retrain the generative AI model to improve its accuracy.

[0395] Terminal handling

[0396] Step 1:

[0397] The terminal provides the user with a form to enter information about preferences, dietary history, and allergies.

[0398] Step 2:

[0399] The profile information entered by the user is sent to the server.

[0400] Step 3:

[0401] The terminal provides the user with a form for inputting the desired recipe conditions (required time, type of ingredients, etc.).

[0402] Step 4:

[0403] A recipe request entered by the user is sent to the server.

[0404] Step 5:

[0405] The device provides an interface for acquiring the user's emotional data, which can be acquired using a facial recognition camera or a voice assistant.

[0406] Step 6:

[0407] The acquired emotion data is transmitted to the server.

[0408] Step 7:

[0409] The terminal receives the original recipe sent from the server and presents it to the user.

[0410] Step 8:

[0411] The terminal provides the user with a form to enter feedback about the recipe.

[0412] Step 9:

[0413] Sends the user-entered feedback to the server.

[0414] User Action

[0415] Step 1:

[0416] Users enter their preferences, dietary history, and allergy information into a form on the terminal.

[0417] Step 2:

[0418] The user sends the entered profile information to the server.

[0419] Step 3:

[0420] The user inputs the desired recipe conditions into a form on the terminal.

[0421] Step 4:

[0422] The user inputs a recipe request and sends it to the server.

[0423] Step 5:

[0424] Users provide their emotional data through the device's interface, and in some cases emotion recognition is performed using a facial recognition camera or voice.

[0425] Step 6:

[0426] The user checks the recipe displayed on the terminal.

[0427] Step 7:

[0428] The user creates a dish based on the displayed recipe.

[0429] Step 8:

[0430] The user enters feedback about the created recipe into a form on the terminal.

[0431] Step 9:

[0432] The user sends the input feedback to the server.

[0433] Example 2

[0434] 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."

[0435] Conventional recipe provision systems have difficulty providing personalized recipes based on a user's individual preferences, specific health information, and even temporary emotional states. They also have difficulty efficiently incorporating user feedback to improve the quality of generated recipes. This poses a challenge in continuously generating recipes that satisfy users.

[0436] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting user preference, dietary history, and allergy information, means for training a generative AI model based on the user's profile, means for preprocessing the collected data, means for generating recipes that meet the user's desired conditions using the trained generative AI model, means for acquiring and recognizing user emotion data, means for adjusting parameters of the generative AI model based on the emotion data, means for providing the generated recipes to the user, and means for collecting user feedback and re-training the generative AI model to improve its accuracy. This makes it possible to provide recipes optimized for the individual needs of the user, thereby increasing user satisfaction and continuously generating high-quality recipes.

[0437] "User preferences" refers to the types of ingredients and dishes that the user prefers, their taste preferences, and so on.

[0438] "Dietary history" is information about meals the user has eaten in the past, including frequency, type, and amount of meals.

[0439] "Allergy information" refers to information about a user's sensitivity to certain foods or ingredients.

[0440] A "generative AI model" refers to an artificial intelligence model that automatically generates recipes based on collected data.

[0441] "User profile" is a collective term for data that compiles information about a user's personal preferences, health information, and dietary information.

[0442] "Preprocessing" refers to the preparation work required to prepare data into a format that is easy for a generative AI model to handle.

[0443] "Recipe conditions" are specific requirements for the dish desired by the user, including the required time and the type of ingredients.

[0444] "Emotional Data" is data that indicates the user's current emotional state and is used by the Emotion Engine to recognize and analyze it.

[0445] "Adjusting the parameters of a generative AI model" refers to making adjustments to optimize the behavior and output of a generative AI model based on inputs such as emotional data and feedback.

[0446] "Feedback" refers to information such as opinions, impressions, and suggestions for improvement regarding a recipe provided by a user.

[0447] "Retraining" refers to additional learning to improve the accuracy of a generative AI model based on collected feedback information.

[0448] This invention is a system that provides individually optimized recipes using a user's preferences, dietary history, allergy information, and emotional data. The system operates primarily in cooperation between a server, a terminal, and the user.

[0449] server

[0450] The server uses hardware and software with the following features:

[0451] 1. Collection and storage of user profile:

[0452] The server receives the user's preferences, dietary history, and allergy information sent from the device and stores it in a database using databases such as MongoDB or MySQL.

[0453] Example: If a user enters "I'm a vegetarian and have a peanut allergy," store that information in a database.

[0454] 2. Training the generative AI model:

[0455] The server preprocesses the collected user data to train a generative AI model (e.g., GPT-3). Preprocessing includes text cleaning and data standardization.

[0456] Example: If a user provides information such as "I like spicy food," the model learns patterns for spicy food.

[0457] 3. Generate the recipe:

[0458] The server uses the trained generative AI model to generate recipes based on the user's desired conditions, taking into account factors such as the required time and the type of ingredients.

[0459] Example: If a user requests a vegetarian meal that can be prepared in under 30 minutes, a recipe that meets those criteria is generated.

[0460] 4. Emotional engine regulation:

[0461] The server uses an emotion engine to analyze the user's emotion data and adjust the parameters of the generative AI model.

[0462] Example: If a user is feeling stressed, the emotion engine will train the model to suggest recipes that include ingredients and cooking methods that have a relaxing effect.

[0463] 5. Recipe provided:

[0464] The server sends the generated recipe to the terminal.

[0465] Example: Generate a recipe for "vegetarian pasta that can be made in under 30 minutes" and send it to your device.

[0466] 6. Collect and use feedback:

[0467] The server collects user feedback and retrains the generative AI model, improving the accuracy of the recipes.

[0468] Example: If a user provides feedback such as "the pasta was bland," that information is included in the training data.

[0469] Terminal

[0470] The terminal interfaces directly with the user and provides the following functions:

[0471] 1. Fill in your user profile:

[0472] The terminal displays a form for the user to enter preferences, dietary history, and allergy information, and sends the entered data to the server.

[0473] Example: A user enters the information "I am a vegetarian" into a terminal and presses the send button.

[0474] 2. Enter your recipe request:

[0475] The terminal provides a form for the user to input desired recipe conditions, and the input information is sent to the server.

[0476] Example: A user enters information about a "vegetarian meal that can be prepared in under 30 minutes" and submits it.

[0477] 3. View recipe:

[0478] The terminal displays the recipe sent from the server to the user.

[0479] Example: Display a recipe for "Vegetarian pasta in under 30 minutes."

[0480] 4. Enter emotion data:

[0481] The device provides an interface to capture the user's emotions and uses a facial recognition camera and voice assistant.

[0482] Example: The device reads the user's emotions through a facial recognition camera and transmits the information to a server.

[0483] 5. Enter your feedback:

[0484] The terminal provides a form for users to enter feedback on the recipes they create.

[0485] Example: A user types "The pasta was bland" and presses the submit button.

[0486] User

[0487] The user uses the system in the following steps:

[0488] 1. Provide your profile information:

[0489] Users enter their preferences, dietary history, and allergy information into a form on the terminal.

[0490] Example: A user enters "I follow a gluten-free diet."

[0491] 2. Specify recipe conditions:

[0492] The user inputs the desired recipe conditions into a form on the terminal.

[0493] Example: A user requests a "gluten-free snack that can be made in under 10 minutes."

[0494] 3. Providing Emotion Data:

[0495] Users provide emotion data through their devices, which may be achieved through facial recognition cameras or voice-based emotion recognition.

[0496] Example: When a user feels stressed, the emotional data is sent to the server via the device.

[0497] 4. Check the recipe and cook:

[0498] The user checks the recipe displayed on the terminal and prepares the dish.

[0499] Example: Make cookies based on the recipe for "10-Minute Gluten-Free Cookies."

[0500] 5. Providing Feedback:

[0501] The user enters their thoughts and suggestions for improvement on the recipe they have cooked into a form on their device and sends it to the server.

[0502] Example: A user types, "I prefer the cookies to be a little softer."

[0503] Prompt Sentence Examples

[0504] "Spicy vegetarian pasta that can be made in 30 minutes"

[0505] "Gluten-free snacks you can make in under 10 minutes"

[0506] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0507] Step 1:

[0508] Enter your user profile

[0509] Subject: Device

[0510] Description: The device displays a form for users to enter their preferences, dietary history, and allergy information. When the user enters information into the form and presses the submit button, the data is sent to the server in JSON or XML format.

[0511] Input: User inputs profile information (preferences, dietary history, allergy information)

[0512] Output: Profile information sent to the server

[0513] Step 2:

[0514] Receiving and storing user profiles

[0515] Subject: Server

[0516] Description: The server receives user profile information sent from the device and stores it in a database, which can be MongoDB or MySQL.

[0517] Input: User profile information sent from the device

[0518] Output: Profile information stored in a database

[0519] What happens: The server receives the HTTP request, the parser parses the data, and then inserts the data into the database.

[0520] Step 3:

[0521] Training a generative AI model

[0522] Subject: Server

[0523] Description: The server retrieves user profile data from a database and trains a generative AI model (e.g., GPT-3) after preprocessing the data, which includes text cleaning and tokenization.

[0524] Input: User profile data stored in the database

[0525] Output: Trained generative AI model

[0526] What it does: Cleans data using data science libraries (e.g., Pandas, NLTK) to build a training dataset, then trains a generative AI model.

[0527] Step 4:

[0528] Acquiring emotion data

[0529] Subject: Device

[0530] Description: The device collects emotional data using a facial recognition camera or voice assistant to obtain the user's emotional data, which is then sent to a server.

[0531] Input: User emotion data (face recognition results, voice analysis results)

[0532] Output: Emotion data sent to the server

[0533] Specific operation: The device activates the camera to capture the user's facial expression, estimates the emotion using a facial recognition algorithm, and sends the data to the server.

[0534] Step 5:

[0535] Entering a Recipe Request

[0536] Subject: Device

[0537] Description: The terminal displays a form for the user to enter the desired recipe conditions (required time, type of ingredients, etc.) When the user enters the conditions and presses the send button, the data is sent to the server.

[0538] Input: User input of recipe conditions

[0539] Output: Recipe conditions sent to the server

[0540] Specific operation: By entering conditions into the form input fields and pressing the submit button, the data is sent to the server as an HTTP request.

[0541] Step 6:

[0542] Recipe Generation

[0543] Subject: Server

[0544] Description: The server generates recipes using a generative AI model based on the user's profile data and recipe conditions. If emotional data is included, the model parameters are adjusted taking that data into account.

[0545] Input: Profile data, emotion data, recipe conditions stored on the server

[0546] Output: The generated recipe

[0547] What it does: Enter a prompt into GPT-3, such as "vegetarian recipe that can be made in under 30 minutes," and retrieve the generated recipe.

[0548] Step 7:

[0549] Recipe provided

[0550] Subject: Server

[0551] Description: The server sends the generated recipe to the terminal. The terminal displays the received recipe to the user.

[0552] Input: Generated recipe

[0553] Output: The recipe displayed on the user's terminal

[0554] Specific operation: The generated recipe is sent to the terminal in the form of an HTTP response, and the terminal receives it and displays it on the screen.

[0555] Step 8:

[0556] Enter your feedback

[0557] Subject: Device

[0558] Description: The terminal provides a form for users to enter feedback on the recipes they have created. When the user enters their feedback and presses the submit button, the data is sent to the server.

[0559] Input: User input of feedback

[0560] Output: Feedback sent to the server

[0561] Specific behavior: By entering feedback into the form input fields and pressing the submit button, the data is sent to the server as an HTTP request.

[0562] Step 9:

[0563] Save and retrain feedback

[0564] Subject: Server

[0565] Description: The server stores the received feedback in a database and retrains the generative AI model based on that feedback.

[0566] Input: User-submitted feedback

[0567] Output: A generative AI model that reflects the learning results

[0568] Specific operation: The new feedback data is stored in the database and added to the existing training dataset for retraining.

[0569] (Application example 2)

[0570] 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."

[0571] Conventional recipe provision systems have limitations in personalization based on user preferences and allergy information, and in particular, they have a problem of insufficient provision of appropriate services based on emotional data. Furthermore, the in-car environment is not optimized to reflect the emotional state of the occupants, so passenger comfort cannot be fully ensured.

[0572] 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.

[0573] In this invention, the server includes means for collecting user preferences, dietary history, and allergy information, means for training a generative AI model based on the user's profile, means for generating recipes that meet the user's desired conditions using the trained generative AI model, means for providing the generated recipes to the user, means for collecting user feedback and improving the accuracy of the generative AI model, means for recognizing and analyzing the user's emotions and adjusting the parameters of the generative AI model based on the results, and means for optimizing the in-car environment based on the emotion data, thereby enabling the provision of personalized recipes according to the user's emotional state and the optimization of the in-car environment.

[0574] "User preferences" refer to the characteristics and types of food and recipes that a user prefers.

[0575] "Dietary history" refers to the history and trends of the meals a user has eaten in the past.

[0576] "Allergy information" refers to information indicating that a user has an allergic reaction to a particular food or ingredient.

[0577] "User profile" refers to all information about an individual, such as the user's preferences, dietary history, and allergy information.

[0578] A "generative AI model" is an artificial intelligence model that generates recipes based on collected user profile information.

[0579] A "recipe" is a set of instructions that specifically outlines cooking steps and a list of ingredients.

[0580] "Feedback" refers to information such as impressions and ratings of a recipe after the user has actually tried it.

[0581] "Emotional data" refers to information related to the user's emotional state, which can be obtained from facial expressions, tone of voice, heart rate, etc.

[0582] "In-vehicle environment" refers to the physical conditions of the space occupied by occupants inside an autonomous vehicle, including lighting, acoustics, temperature, and air quality.

[0583] A "parameter" is a numerical value that determines the behavior and performance of a generative AI model.

[0584] To implement this invention, a system is constructed in which a server, a terminal, and a user cooperate with each other. The server plays the following main roles.

[0585] server

[0586] The server operates as follows to collect user information and provide recipes using generative AI models.

[0587] 1. Collecting and storing user profiles

[0588] The server receives the user's preferences, dietary history, allergy information, and emotional data sent from the device and stores it in a database. For example, if a user enters "I'm a vegetarian and I have a peanut allergy," this information will be stored in the database.

[0589] 2. Training the generative AI model

[0590] The server trains a generative AI model based on the collected user profile. Specifically, for example, for a user who has a preference for spicy food, the model learns patterns of spicy ingredients and recipes.

[0591] 3. Recipe Generation

[0592] The server uses the learned generative AI model to generate recipes that meet the user's desired conditions (time required, type of ingredients, etc.) For example, it generates a recipe based on a user request such as "I want a vegetarian dish that can be made in under 30 minutes."

[0593] 4. Emotional Engine Adjustment

[0594] The server uses an emotion engine to analyze the user's emotional state and adjusts the parameters of the generative AI model based on the results: if the user is feeling stressed, the model is adjusted to suggest dishes that have a relaxing effect.

[0595] 5. Optimizing the in-car environment

[0596] The environment inside the autonomous vehicle (lighting, music, temperature, etc.) is optimized based on emotional data. Specifically, if the passenger wants to relax, relaxing music will be played and the temperature will be set appropriately.

[0597] 6. Collect and use feedback

[0598] The generative AI model is retrained to improve its accuracy using user-provided feedback. For example, if feedback such as "the pasta was bland" is collected, this is reflected in the model.

[0599] Terminal

[0600] The terminal serves the following roles as an interface with the user.

[0601] 1. Enter your user profile

[0602] The terminal provides a form for users to input their preferences, dietary history, and allergy information, which is then sent to the server.

[0603] 2. Enter your recipe request

[0604] The user inputs the desired conditions (time required, type of material, etc.) and sends the request to the server.

[0605] 3. View recipes

[0606] The original recipe sent from the server is displayed and provided to the user.

[0607] 4. Entering Emotion Data

[0608] Using facial recognition cameras and voice assistants, users' emotional data is collected and sent to a server.

[0609] 5. Enter your feedback

[0610] The user inputs feedback about the created recipe and sends it to the server.

[0611] User

[0612] Users can access the system via their device and are provided with individually optimized recipes and in-car environments.

[0613] 1. Providing Profile Information

[0614] The user enters profile information using a form on the terminal and sends it to the server.

[0615] 2. Specify recipe conditions

[0616] Use the terminal to specify recipe conditions (required time, type of ingredients).

[0617] 3. Providing Emotion Data

[0618] Using a facial recognition camera or voice assistant, you can provide your emotional state to the system.

[0619] 4. Check the recipe and cook

[0620] Cook a dish based on the recipe provided and check the results.

[0621] 5. Providing Feedback

[0622] Feedback about the cooked recipe is entered into the terminal and sent to the server.

[0623] Specific examples

[0624] For example, if a user inputs "I'm vegetarian and would like a recipe that can be made in 30 minutes or less," the server will use the trained generative AI model to generate the appropriate recipe and provide it to the user via their device. Also, if the user is feeling stressed, the server will suggest recipes and in-car environments that have a relaxing effect.

[0625] Prompt Sentence Examples

[0626] "The passenger is stressed, so please set the car to relaxing music and an appropriate temperature. The passenger's profile information is that they like classical music and are allergic to pollen."

[0627] These components enable the system to provide personalized recipes that take into account the user's emotional state and optimize the in-car environment.

[0628] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0629] Step 1:

[0630] The user enters their user profile on the device. Using the device, the user enters their preferences, dietary history, allergy information, etc., which the device then sends to the server. Specific input data includes "user's name," "being a vegetarian," "having a peanut allergy," etc. The server stores this input data in a database.

[0631] Step 2:

[0632] Recipe requests are input via the device. The user inputs the desired recipe conditions (e.g., vegetarian food, time required within 30 minutes) through the device interface. This request data is sent from the device to the server. The server uses this data to train the generative AI model and generate the recipe.

[0633] Step 3:

[0634] The generative AI model is trained on the server. The server trains the generative AI model based on the user profile information collected in step 1. Specifically, the model learns preference information such as "I like spicy food" and recognizes patterns of spicy ingredients and recipes. This process obtains the user profile as input and the trained AI model as output.

[0635] Step 4:

[0636] The server generates the recipe. Using the trained generative AI model, it generates a recipe that matches the user's desired conditions entered in step 2. For example, if the user enters "I'm looking for a vegetarian dish that can be prepared in under 30 minutes," the generative AI model creates a recipe that meets those conditions, and the server sends the recipe to the device.

[0637] Step 5:

[0638] Analyzes emotional states and adjusts parameters. The server uses an emotion engine to analyze the user's emotional data sent from the device and adjusts the parameters of the generative AI model based on the results. For example, if the user is feeling stressed, the generative AI model is adjusted to suggest dishes that have a relaxing effect. This process obtains emotional data as input and an adjusted AI model as output.

[0639] Step 6:

[0640] Optimizing the in-car environment. The server optimizes the environment inside the autonomous vehicle based on emotional data. Specifically, when the passenger feels like relaxing, it plays relaxing music and sets the temperature appropriately. This process obtains emotional data as input and optimized in-car environment settings as output.

[0641] Step 7:

[0642] It collects and utilizes feedback. The device provides an interface for inputting and sending feedback from users, who input their thoughts and ratings on the recipes they have cooked. The server collects this feedback and performs re-learning to improve the accuracy of the generative AI model. A specific example of how this works is to retrain the AI ​​model based on feedback such as "the pasta was bland." This process obtains feedback data as input and an improved AI model as output.

[0643] 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.

[0644] 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.

[0645] 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.

[0646] [Second embodiment]

[0647] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0648] 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.

[0649] 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).

[0650] 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.

[0651] 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.

[0652] 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).

[0653] 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.

[0654] 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.

[0655] 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.

[0656] 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.

[0657] 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.

[0658] 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."

[0659] The present invention relates to a system that collects and analyzes user preferences, dietary history, and allergy information, and provides recipes optimized for each individual user.

[0660] Server embodiment

[0661] The server has the following main functions:

[0662] 1. Collecting and storing user profiles

[0663] The server receives the user's preferences, dietary history, and allergy information sent from the terminal.

[0664] The received information is stored in a database.

[0665] Example: If a user provides information such as "I'm a vegetarian and I have a peanut allergy," the server stores that information in a database.

[0666] 2. Training the generative AI model

[0667] The server trains a generative AI model based on the collected user profiles.

[0668] Example: Based on a user's preference information such as "I like spicy food," the model learns patterns of spicy ingredients and recipes.

[0669] 3. Recipe Generation

[0670] The server uses the learned generative AI model to generate recipes that meet the user's desired conditions (time required, type of ingredients, etc.).

[0671] Example: If a user requests a vegetarian meal that can be prepared in under 30 minutes, the server generates a recipe that reflects that request.

[0672] 4. Providing recipes

[0673] The server sends the generated original recipe to the terminal.

[0674] Example: Send a server-generated recipe for "vegetarian pasta that can be made in under 30 minutes."

[0675] 5. Collect and use feedback

[0676] The server receives feedback from users and uses it to retrain the generative AI model to improve its accuracy.

[0677] Example: If a user provides feedback such as "The vegetarian pasta was bland," that feedback is reflected as training data.

[0678] Terminal embodiment

[0679] The terminal acts as an interface with the user:

[0680] 1. Enter your user profile

[0681] The terminal provides a form for the user to input preferences, dietary history, and allergy information.

[0682] The entered profile information is sent to the server.

[0683] Example: A user enters the information "I am a vegetarian" into a terminal and presses the send button.

[0684] 2. Enter your recipe request

[0685] The terminal provides a form for the user to input desired recipe conditions (required time, type of ingredients, etc.).

[0686] The input request is sent to the server.

[0687] Example: A user enters information about a "vegetarian meal that can be prepared in under 30 minutes" and presses the submit button.

[0688] 3. View recipes

[0689] The terminal receives the original recipe sent from the server and displays it to the user.

[0690] Example: Display a recipe sent from the server for "vegetarian pasta that can be made in under 30 minutes."

[0691] 4. Enter your feedback

[0692] The terminal provides a form for users to enter feedback on the recipes they have created.

[0693] The input feedback information is sent to the server.

[0694] Example: A user enters feedback such as "The pasta was bland" and presses the submit button.

[0695] User's embodiment

[0696] Users use the system to receive recipes tailored to their personal tastes and requirements:

[0697] 1. Providing Profile Information

[0698] The user enters their preferences, dietary history, and allergy information into a form on the terminal.

[0699] Example: A user enters that they "follow a gluten-free diet."

[0700] 2. Specify recipe conditions

[0701] The user inputs the conditions of the desired recipe into a form on the terminal.

[0702] Example: A user requests a "gluten-free snack that can be made in under 10 minutes."

[0703] 3. Check the recipe and cook

[0704] The user checks the recipe displayed on the terminal and prepares the dish based on it.

[0705] Example: A user makes cookies based on the recipe for "10-Minute Gluten-Free Cookies" displayed on their device.

[0706] 4. Providing Feedback

[0707] Users enter their thoughts and suggestions for improvement about the recipe they have cooked into a form on their device and send the feedback to the server.

[0708] Example: A user provides feedback such as "I would prefer the cookies to be a little softer."

[0709] The processing flow will be explained below.

[0710] Server Processing

[0711] Step 1:

[0712] The server receives the user's preferences, dietary history, and allergy information sent from the terminal.

[0713] Step 2:

[0714] The server stores the received user profile information in a database.

[0715] Step 3:

[0716] The server retrieves the user profile from the database and inputs it into the generative AI model for learning.

[0717] Step 4:

[0718] The server receives the recipe conditions (required time, type of ingredients, etc.) sent from the terminal.

[0719] Step 5:

[0720] The server uses a generative AI model to generate recipes that fit the user's requirements, taking into account the difficulty of obtaining ingredients and the time required.

[0721] Step 6:

[0722] The server sends the generated recipe to the terminal.

[0723] Step 7:

[0724] The server receives the user feedback sent from the terminal.

[0725] Step 8:

[0726] The server stores the received feedback in a database and uses it to retrain the generative AI model to improve its accuracy.

[0727] Terminal handling

[0728] Step 1:

[0729] The terminal provides the user with a form to enter information about preferences, dietary history, and allergies.

[0730] Step 2:

[0731] The profile information entered by the user is sent to the server.

[0732] Step 3:

[0733] The terminal provides the user with a form for inputting the desired recipe conditions (required time, type of ingredients, etc.).

[0734] Step 4:

[0735] A recipe request entered by the user is sent to the server.

[0736] Step 5:

[0737] The terminal receives the original recipe sent from the server.

[0738] Step 6:

[0739] The terminal displays the received recipe in an easy-to-understand manner for the user.

[0740] Step 7:

[0741] The terminal provides the user with a form to enter feedback about the recipe.

[0742] Step 8:

[0743] Sends the user-entered feedback to the server.

[0744] User Action

[0745] Step 1:

[0746] Users enter their preferences, dietary history, and allergy information into a form on the terminal.

[0747] Step 2:

[0748] The user sends the entered profile information to the server.

[0749] Step 3:

[0750] The user inputs the desired recipe conditions into a form on the terminal.

[0751] Step 4:

[0752] The user inputs a recipe request and sends it to the server.

[0753] Step 5:

[0754] The user checks the recipe displayed on the terminal.

[0755] Step 6:

[0756] The user creates a dish based on the displayed recipe.

[0757] Step 7:

[0758] The user enters feedback about the created recipe into a form on the terminal.

[0759] Step 8:

[0760] The user sends the input feedback to the server.

[0761] Example 1

[0762] 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."

[0763] Conventional recipe provision systems have difficulty providing optimal recipes based on individual users' preferences, dietary history, and allergy information. Furthermore, they lack a mechanism for collecting user feedback to improve the system's accuracy, making it impossible to respond quickly and accurately to user needs. This has resulted in problems such as users having to spend time and effort searching for recipes that suit them.

[0764] 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.

[0765] In this invention, the server includes means for collecting user preferences, dietary history, and allergy information, means for training a generative AI model based on the user's profile, means for generating recipes that meet the user's desired conditions using the trained generative AI model, means for providing the generated recipes to the user, and means for collecting user feedback and improving the accuracy of the generative AI model. This makes it possible to quickly and accurately respond to the user's individual needs and provide optimal recipes. Furthermore, by generating recipes using prompts, recipes that meet the user's preferences can be quickly generated. Furthermore, by saving the user's profile and feedback, the accuracy of the system can be continuously improved.

[0766] "User preferences" refers to information about the user's favorite foods and cooking methods.

[0767] "Dietary history" refers to historical information about meals the user has taken in the past.

[0768] "Allergy information" refers to data about foods or ingredients to which a user has an allergic reaction.

[0769] A "generative AI model" is an artificial intelligence model that learns data and generates recipes based on the user's preferences and conditions.

[0770] "User profile" refers to personal data such as a user's preferences, dietary history, and allergy information.

[0771] A "recipe" is a list of instructions and ingredients for making a particular dish.

[0772] "Feedback" refers to the user's thoughts and evaluations of the system and recipes.

[0773] A "prompt" is a condition or instruction that is input to a generative AI model to generate a recipe.

[0774] A "database" is a system that organizes and stores collected information so that it can be searched and retrieved when needed.

[0775] A "server" is a computer system that collects, processes, stores, and serves information from users.

[0776] A "terminal" is a device that a user uses to enter information and receive generated recipes.

[0777] This invention relates to a system that collects and analyzes user preferences, dietary history, and allergy information to provide recipes optimized for each user. This system consists of three main elements: a server, a terminal, and a user.

[0778] Server embodiment

[0779] The server has the following features:

[0780] 1. Collecting and storing user profiles

[0781] The server receives the user's preferences, dietary history, and allergy information sent from the device and stores it in a database. For example, if a user provides information that they are "vegetarian and have a peanut allergy," the server stores that information in the database.

[0782] 2. Training the generative AI model

[0783] The server trains a generative AI model based on the collected user profile. For example, based on the user's preference information "I like spicy food," the model learns patterns of spicy ingredients and recipes.

[0784] 3. Recipe Generation

[0785] The server uses the learned generative AI model to generate recipes that meet the user's desired conditions (time required, type of ingredients, etc.). For example, if the user requests a "vegetarian dish that can be made in 30 minutes or less," the server generates a recipe that reflects those conditions. An example of a prompt sentence is "Please generate a recipe for a vegetarian dish that can be made in 30 minutes or less."

[0786] 4. Providing the generated recipe

[0787] The server sends the generated recipe to the device. For example, the server sends the generated recipe for "vegetarian pasta that can be made in 30 minutes or less" to the device.

[0788] 5. Collecting and Using Feedback

[0789] The server receives feedback from users and retrains the generative AI model to improve its accuracy. For example, if a user provides feedback such as "the vegetarian pasta was bland," the server incorporates this feedback into the training data.

[0790] Terminal embodiment

[0791] The terminal acts as an interface with the user:

[0792] 1. Enter your user information

[0793] The terminal provides a form for the user to input information about preferences, dietary history, and allergies, and transmits the input profile information to the server. For example, the user inputs information such as "I am a vegetarian" into the terminal and presses the send button.

[0794] 2. Enter recipe conditions

[0795] The terminal provides a form for the user to input the desired recipe conditions (time required, type of ingredients, etc.) and sends the input request to the server. For example, a user inputs information requesting "vegetarian dishes that can be made in 30 minutes or less" and presses the send button.

[0796] 3. View recipes

[0797] The device receives the original recipe sent from the server and displays it to the user. For example, the device displays a recipe for "vegetarian pasta that can be made in under 30 minutes."

[0798] 4. Enter your feedback

[0799] The terminal provides a form for the user to input feedback on the recipe created by the user, and transmits the input feedback information to the server. For example, the user inputs feedback such as "the pasta was bland" and presses the send button.

[0800] User's embodiment

[0801] To use the optimized recipe, users follow these steps:

[0802] 1. Providing Profile Information

[0803] The user enters their preferences, dietary history, and allergy information into a form on the terminal. For example, the user enters that they follow a gluten-free diet.

[0804] 2. Specify recipe conditions

[0805] The user inputs the desired recipe conditions into a form on the terminal. For example, the user specifies "a gluten-free snack that can be made in 10 minutes or less." An example of a prompt sentence is "Please generate a recipe for a gluten-free snack that can be made in 10 minutes or less."

[0806] 3. Check the recipe and cook

[0807] The user checks the recipe displayed on the device and prepares the dish based on it. For example, the user makes cookies based on the recipe for "10-minute gluten-free cookies" displayed on the device.

[0808] 4. Providing Feedback

[0809] The user inputs their thoughts and suggestions for improvement about the recipe into a form on the device and sends the feedback to the server. For example, the user inputs feedback such as "I wish the cookies were a little softer when baked."

[0810] By implementing this system, users can quickly and accurately receive recipes optimized for their preferences and conditions. In addition, by continuously collecting and incorporating feedback from users, the accuracy of the generative AI model can be improved, enabling the provision of better services.

[0811] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0812] Step 1:

[0813] Entering User Profile Information

[0814] The terminal displays a form for the user to enter preferences, dietary history, and allergy information.

[0815] The user enters information into the form displayed on the terminal and presses the "Submit" button.

[0816] Input: User preferences, dietary history, and allergy information (e.g., "I'm vegetarian and have a peanut allergy").

[0817] Output: The entered information is sent from the terminal to the server.

[0818] Specific operation: When the user clicks the "Submit" button, the input information is sent from the terminal to the server.

[0819] Step 2:

[0820] Submitting and storing profile information

[0821] The terminal transmits the information entered by the user to the server.

[0822] The server stores the received information in a database.

[0823] Input: User profile information (e.g., "I'm a vegetarian and have a peanut allergy").

[0824] Output: The information is stored in a database.

[0825] Specific operation: The server analyzes the received data and stores it in a database.

[0826] Step 3:

[0827] Training a generative AI model

[0828] The server trains the generative AI model based on user information stored in a database.

[0829] Input: User information stored in a database (e.g., "I like spicy food").

[0830] Output: A trained generative AI model.

[0831] How it works: The server inputs the stored data into the AI ​​model, allowing it to learn patterns.

[0832] Step 4:

[0833] Entering recipe conditions

[0834] The terminal provides a form for the user to input desired recipe conditions (required time, type of ingredients, etc.).

[0835] The user inputs the desired conditions and presses the "Submit" button.

[0836] Input: User recipe criteria (e.g., "vegetarian meals that can be made in under 30 minutes").

[0837] Output: The entered conditions are sent from the terminal to the server.

[0838] Specific operation: When the user clicks the "Send" button, the desired conditions are sent from the terminal to the server.

[0839] Step 5:

[0840] Sending and generating recipe conditions

[0841] The terminal transmits the input conditions to the server.

[0842] The server generates a recipe using a generative AI model based on the received conditions.

[0843] Input: User recipe criteria (e.g., "vegetarian meals that can be made in under 30 minutes").

[0844] Output: The generated recipe (e.g. "Vegetarian pasta in under 30 minutes").

[0845] Specific operation: The server provides the conditions as prompts to the generative AI model, which then generates the optimal recipe. An example of the prompt is, "Generate a vegetarian recipe that can be made in under 30 minutes."

[0846] Step 6:

[0847] Providing the generated recipe

[0848] The server transmits the generated recipe to the terminal.

[0849] The terminal displays the received recipe to the user.

[0850] Input: The generated recipe (e.g., "Vegetarian pasta in under 30 minutes").

[0851] Output: The recipe is printed to the terminal.

[0852] Specific behavior: The server sends the recipe to the device, and the device displays it to the user.

[0853] Step 7:

[0854] Enter your feedback

[0855] The terminal provides a form for users to enter feedback on the recipes they have created.

[0856] The user enters the feedback and presses the "Submit" button.

[0857] Input: User feedback (e.g., "The pasta was bland").

[0858] Output: The input feedback information is sent from the device to the server.

[0859] Specific operation: When the user clicks the "Submit" button, the feedback information is sent from the terminal to the server.

[0860] Step 8:

[0861] Send and save feedback

[0862] The terminal transmits the input feedback to the server.

[0863] The server stores the received feedback in a database.

[0864] Input: User feedback information (e.g., "The pasta was bland").

[0865] Output: The feedback information is stored in a database.

[0866] Specific behavior: The server analyzes the received feedback and stores it in a database.

[0867] Step 9:

[0868] Reflecting feedback

[0869] The server retrains the generative AI model based on the collected feedback, improving the model's accuracy.

[0870] Input: Feedback information stored in a database (e.g., "The pasta was bland").

[0871] Output: A generative AI model with improved accuracy.

[0872] Specific operation: The server inputs the feedback data into the AI ​​model and retrains the model.

[0873] (Application example 1)

[0874] 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."

[0875] Conventional food delivery systems have difficulty suggesting optimal dishes based on a user's individual preferences, allergies, and dietary history. Even if a system existed that provided recipes that matched a user's desired conditions, it was not possible to link the system directly from ordering to delivery. This made it difficult for users to easily enjoy dishes that suited their dietary habits. Furthermore, the system lacked sufficient functionality to reflect user feedback and improve the accuracy of recipes.

[0876] 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.

[0877] In this invention, the server includes a means for collecting user preferences, dietary history, and allergy information, a means for training a generative AI model based on the user's profile, and a means for generating recipes that meet the user's desired conditions using the trained generative AI model. This allows the user to receive individually optimized recipe suggestions. The server also includes a means for providing the generated recipes to the user and a means for collecting feedback from the user to improve the accuracy of the generative AI model. Furthermore, the server includes a means for suggesting individually optimized dishes based on the user's profile and a means for directly ordering the suggested dishes and delivering them to a specified address, allowing the user to easily order and quickly receive dishes that suit their diet. This system allows users to easily enjoy dishes tailored to their preferences and constraints, and further improves accuracy based on feedback.

[0878] "User preferences" refers to information about the dishes and ingredients that the user likes to eat.

[0879] "Dietary history" is a record of the foods and meals a user has eaten in the past.

[0880] "Allergy information" is information about foods and ingredients that cause allergic reactions to the user.

[0881] A "generative AI model" is a model that learns and is generated using artificial intelligence, and suggests optimal recipes based on the user's individual information.

[0882] "Profile" is a general term for personal information such as a user's preferences, dietary history, and allergy information.

[0883] A "recipe" is a guideline that shows the steps and ingredients for making a dish.

[0884] "Feedback" refers to the user's evaluation of the food they have provided and their suggestions for improvement.

[0885] "Delivery" is the process of delivering the food ordered by the user to the address specified.

[0886] A "means" is a method or device for achieving a specific function or purpose.

[0887] The system of this invention is realized through collaboration between a server and a terminal, and provides optimized meals based on the user's preferences, dietary history, and allergy information, and then handles the entire process from directly ordering the meals to delivery.

[0888] The server has the following main functions:

[0889] 1. Collecting user preferences, dietary history, and allergy information

[0890] The server receives the user's preferences, dietary history, and allergy information sent from the device and stores it in a database. For example, if a user provides information such as "I'm a vegetarian and have a peanut allergy," the server stores that information in the database.

[0891] 2. Training the generative AI model

[0892] The server trains a generative AI model based on the collected user profile information, allowing it to suggest dishes optimized for the user's preferences and conditions. For example, if a user has a preference for spicy food, the server can train the model to recommend spicy recipes.

[0893] 3. Recipe Generation

[0894] The server uses the trained generative AI model to generate recipes that meet the user's criteria. For example, for a request for "vegetarian dishes that can be made in under 30 minutes," it generates a recipe for vegetarian pasta.

[0895] 4. Providing recipes and taking orders

[0896] The generated recipe is sent from the server to the terminal, where the user can check it and order it directly. For example, a user can view the suggested vegetarian pasta recipe and order it if they like it.

[0897] 5. Collecting user feedback and improving model accuracy

[0898] When users send feedback about the food they've been served, the server collects it and uses it to retrain the generative AI model. For example, feedback like "the pasta was bland" can be reflected in the next recommendation.

[0899] The terminal has the following main functions:

[0900] 1. Enter your user profile

[0901] The device has a form where users can enter their preferences, allergy information, and dietary history, for example, "I'm a vegetarian and have a peanut allergy."

[0902] 2. Enter your recipe request

[0903] It provides a form where users can input their desired cooking criteria and send it to the server. For example, they can input criteria such as "vegetarian dishes that can be prepared in 30 minutes or less."

[0904] 3. View recipes and order

[0905] The recipe sent from the server is displayed on the device, and the user can check the recipe. Also, by pressing the order button, the user can directly order the dish. For example, a recipe for vegetarian pasta can be displayed and the user can order it.

[0906] 4. Enter your feedback

[0907] It has a form where users can enter their feedback about the food and send it to the server. For example, they can enter feedback such as "The pasta was bland."

[0908] As a concrete example, if a vegetarian user requests a dish that can be prepared in under 30 minutes, the server generates a recipe based on that condition and sends it to the device. The user then orders a dish based on the generated recipe and it is delivered. Feedback on the dish can then be sent from the device to improve the accuracy of the next suggestion.

[0909] Example prompt for a generative AI model:

[0910] Suggest the best recipes based on your user profile below.

[0911] Food preference: Vegetarian

[0912] Allergy Information: Peanuts

[0913] Time required: 30 minutes or less

[0914] Generate the best vegetarian, peanut-free recipe that can be made in under 30 minutes and meets the following criteria:

[0915] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0916] Step 1:

[0917] The user inputs and sends profile information (preferences, dietary history, allergy information) into the device. Input data: Information such as "I'm a vegetarian and have a peanut allergy." The input data is sent from the device to the server.

[0918] Step 2:

[0919] The server receives the user's profile information sent from the device and stores it in a database, which includes information on preferences, dietary history, and allergies.

[0920] Step 3:

[0921] The server trains the generative AI model based on the collected user profile information. Input data: User preferences, past dietary data, and allergy information. The generative AI model uses this data to learn how to suggest recipes.

[0922] Step 4:

[0923] The user inputs specific recipe requirements (time required, type of ingredients, etc.) from the terminal and sends them to the server. Input data: For example, desired requirements for a vegetarian dish that can be made in 30 minutes or less.

[0924] Step 5:

[0925] The server uses the trained generative AI model to generate recipes that best fit the user's desired conditions. Input data: the trained model and the user's request conditions. Output data: a vegetarian pasta recipe that can be made in under 30 minutes, for example.

[0926] Step 6:

[0927] The server sends the generated recipe to the terminal, which displays it to the user. Input data: Data on the generated recipe. Output data: Recipe display on the user's terminal screen.

[0928] Step 7:

[0929] The user checks the provided recipe and places an order. Input data: User's confirmation and order intention. The terminal sends the order information to the server.

[0930] Step 8:

[0931] The server accepts the user's order and arranges delivery to the specified address. Input data: User's order information and delivery address. Output data: Order processing and start of delivery procedure.

[0932] Step 9:

[0933] The user inputs feedback about the dish from the terminal and sends it to the server. Input data: Contents of the feedback (for example, "The pasta was bland").

[0934] Step 10:

[0935] The server receives feedback from users and uses it to retrain the generative AI model. Input data: Feedback information. Output data: Improved generative AI model.

[0936] 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.

[0937] This invention relates to a system that provides recipes optimized for individual users based on their preferences, dietary history, allergy information, and emotions. This system combines a generative AI model and an emotion engine to provide more personalized recipes.

[0938] Server embodiment

[0939] The server has the following main functions:

[0940] 1. Collecting and storing user profiles

[0941] The server receives the user's preferences, dietary history, and allergy information sent from the terminal.

[0942] The received information is stored in a database.

[0943] Example: If a user provides information such as "I'm a vegetarian and I have a peanut allergy," the server stores that information in a database.

[0944] 2. Training the generative AI model

[0945] The server trains a generative AI model based on the collected user profiles.

[0946] Example: Based on a user's preference information such as "I like spicy food," the model learns patterns of spicy ingredients and recipes.

[0947] 3. Recipe Generation

[0948] The server uses the learned generative AI model to generate recipes that meet the user's desired conditions (time required, type of ingredients, etc.).

[0949] Example: If a user requests a vegetarian meal that can be prepared in under 30 minutes, the server generates a recipe that reflects that request.

[0950] 4. Emotional Engine Adjustment

[0951] The server uses an emotion engine to recognize and analyze the user's emotions and adjusts the parameters of the generative AI model based on the results.

[0952] Example: If a user is feeling stressed, the emotion engine will adjust the generative AI model to suggest recipes that include ingredients and cooking methods that have a relaxing effect.

[0953] 5. Providing recipes

[0954] The server sends the generated original recipe to the terminal.

[0955] Example: Send a server-generated recipe for "vegetarian pasta that can be made in under 30 minutes."

[0956] 6. Collect and use feedback

[0957] The server receives feedback from users and uses it to retrain the generative AI model to improve its accuracy.

[0958] Example: If a user provides feedback such as "The vegetarian pasta was bland," that feedback is reflected as training data.

[0959] Terminal embodiment

[0960] The terminal acts as an interface with the user:

[0961] 1. Enter your user profile

[0962] The terminal provides a form for the user to input preferences, dietary history, and allergy information.

[0963] The entered profile information is sent to the server.

[0964] Example: A user enters the information "I am a vegetarian" into a terminal and presses the send button.

[0965] 2. Enter your recipe request

[0966] The terminal provides a form for the user to input desired recipe conditions (required time, type of ingredients, etc.).

[0967] The input request is sent to the server.

[0968] Example: A user enters information about a "vegetarian meal that can be prepared in under 30 minutes" and presses the submit button.

[0969] 3. View recipes

[0970] The terminal receives the original recipe sent from the server and displays it to the user.

[0971] Example: Display a recipe sent from the server for "vegetarian pasta that can be made in under 30 minutes."

[0972] 4. Entering Emotion Data

[0973] The device provides an interface for inputting and acquiring user emotions, which can be read using a facial recognition camera or voice assistant.

[0974] Example: The device reads the user's emotions through a facial recognition camera and transmits them to a server.

[0975] 5. Enter your feedback

[0976] The terminal provides a form for users to enter feedback on the recipes they have created.

[0977] The input feedback information is sent to the server.

[0978] Example: A user enters feedback such as "The pasta was bland" and presses the submit button.

[0979] User's embodiment

[0980] Users use the system to receive recipes tailored to their personal tastes and requirements:

[0981] 1. Providing Profile Information

[0982] The user enters their preferences, dietary history, and allergy information into a form on the terminal.

[0983] Example: A user enters that they "follow a gluten-free diet."

[0984] 2. Specify recipe conditions

[0985] The user inputs the desired recipe conditions into a form on the terminal.

[0986] Example: A user requests a "gluten-free snack that can be made in under 10 minutes."

[0987] 3. Providing Emotion Data

[0988] Users provide their emotional data through the device's interface, and in some cases emotion recognition is performed using a facial recognition camera or voice.

[0989] Example: When a user feels stressed, the emotional data is sent to the server via the device.

[0990] 4. Check the recipe and cook

[0991] The user checks the recipe displayed on the terminal and prepares the dish based on it.

[0992] Example: A user makes cookies based on the recipe for "10-Minute Gluten-Free Cookies" displayed on their device.

[0993] 5. Providing Feedback

[0994] Users enter their thoughts and suggestions for improvement about the recipe they have cooked into a form on their device and send the feedback to the server.

[0995] Example: A user provides feedback such as "I would prefer the cookies to be a little softer."

[0996] The processing flow will be explained below.

[0997] Server Processing

[0998] Step 1:

[0999] The server receives the user's preferences, dietary history, and allergy information sent from the terminal.

[1000] Step 2:

[1001] The server stores the received user profile information in a database.

[1002] Step 3:

[1003] The server retrieves the user profile from the database and inputs that information into the generative AI model to learn.

[1004] Step 4:

[1005] The server receives the recipe conditions (required time, type of ingredients, etc.) sent from the terminal.

[1006] Step 5:

[1007] The server uses a generative AI model to generate recipes that fit the user's requirements, taking into account the difficulty of obtaining ingredients and the time required.

[1008] Step 6:

[1009] The server uses an emotion engine to analyze the user's emotion data and reflects it in the recipe it generates.

[1010] Step 7:

[1011] The server sends the generated recipe to the terminal.

[1012] Step 8:

[1013] The server receives the user feedback sent from the terminal.

[1014] Step 9:

[1015] The server stores the received feedback in a database and uses it to retrain the generative AI model to improve its accuracy.

[1016] Terminal handling

[1017] Step 1:

[1018] The terminal provides the user with a form to enter information about preferences, dietary history, and allergies.

[1019] Step 2:

[1020] The profile information entered by the user is sent to the server.

[1021] Step 3:

[1022] The terminal provides the user with a form for inputting the desired recipe conditions (required time, type of ingredients, etc.).

[1023] Step 4:

[1024] A recipe request entered by the user is sent to the server.

[1025] Step 5:

[1026] The device provides an interface for acquiring the user's emotional data, which can be acquired using a facial recognition camera or a voice assistant.

[1027] Step 6:

[1028] The acquired emotion data is transmitted to the server.

[1029] Step 7:

[1030] The terminal receives the original recipe sent from the server and presents it to the user.

[1031] Step 8:

[1032] The terminal provides the user with a form to enter feedback about the recipe.

[1033] Step 9:

[1034] Sends the user-entered feedback to the server.

[1035] User Action

[1036] Step 1:

[1037] Users enter their preferences, dietary history, and allergy information into a form on the terminal.

[1038] Step 2:

[1039] The user sends the entered profile information to the server.

[1040] Step 3:

[1041] The user inputs the desired recipe conditions into a form on the terminal.

[1042] Step 4:

[1043] The user inputs a recipe request and sends it to the server.

[1044] Step 5:

[1045] Users provide their emotional data through the device's interface, and in some cases emotion recognition is performed using a facial recognition camera or voice.

[1046] Step 6:

[1047] The user checks the recipe displayed on the terminal.

[1048] Step 7:

[1049] The user creates a dish based on the displayed recipe.

[1050] Step 8:

[1051] The user enters feedback about the created recipe into a form on the terminal.

[1052] Step 9:

[1053] The user sends the input feedback to the server.

[1054] Example 2

[1055] 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."

[1056] Conventional recipe provision systems have difficulty providing personalized recipes based on a user's individual preferences, specific health information, and even temporary emotional states. They also have difficulty efficiently incorporating user feedback to improve the quality of generated recipes. This poses a challenge in continuously generating recipes that satisfy users.

[1057] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting user preference, dietary history, and allergy information, means for training a generative AI model based on the user's profile, means for preprocessing the collected data, means for generating recipes that meet the user's desired conditions using the trained generative AI model, means for acquiring and recognizing user emotion data, means for adjusting parameters of the generative AI model based on the emotion data, means for providing the generated recipes to the user, and means for collecting user feedback and re-training the generative AI model to improve its accuracy. This makes it possible to provide recipes optimized for the individual needs of the user, thereby increasing user satisfaction and continuously generating high-quality recipes.

[1058] "User preferences" refers to the types of ingredients and dishes that the user prefers, their taste preferences, and so on.

[1059] "Dietary history" is information about meals the user has eaten in the past, including frequency, type, and amount of meals.

[1060] "Allergy information" refers to information about a user's sensitivity to certain foods or ingredients.

[1061] A "generative AI model" refers to an artificial intelligence model that automatically generates recipes based on collected data.

[1062] "User profile" is a collective term for data that compiles information about a user's personal preferences, health information, and dietary information.

[1063] "Preprocessing" refers to the preparation work required to prepare data into a format that is easy for a generative AI model to handle.

[1064] "Recipe conditions" are specific requirements for the dish desired by the user, including the required time and the type of ingredients.

[1065] "Emotional Data" is data that indicates the user's current emotional state and is used by the Emotion Engine to recognize and analyze it.

[1066] "Adjusting the parameters of a generative AI model" refers to making adjustments to optimize the behavior and output of a generative AI model based on inputs such as emotional data and feedback.

[1067] "Feedback" refers to information such as opinions, impressions, and suggestions for improvement regarding a recipe provided by a user.

[1068] "Retraining" refers to additional learning to improve the accuracy of a generative AI model based on collected feedback information.

[1069] This invention is a system that provides individually optimized recipes using a user's preferences, dietary history, allergy information, and emotional data. The system operates primarily in cooperation between a server, a terminal, and the user.

[1070] server

[1071] The server uses hardware and software with the following features:

[1072] 1. Collection and storage of user profile:

[1073] The server receives the user's preferences, dietary history, and allergy information sent from the device and stores it in a database using databases such as MongoDB or MySQL.

[1074] Example: If a user enters "I'm a vegetarian and have a peanut allergy," store that information in a database.

[1075] 2. Training the generative AI model:

[1076] The server preprocesses the collected user data to train a generative AI model (e.g., GPT-3). Preprocessing includes text cleaning and data standardization.

[1077] Example: If a user provides information such as "I like spicy food," the model learns patterns for spicy food.

[1078] 3. Generate the recipe:

[1079] The server uses the trained generative AI model to generate recipes based on the user's desired conditions, taking into account factors such as the required time and the type of ingredients.

[1080] Example: If a user requests a vegetarian meal that can be prepared in under 30 minutes, a recipe that meets those criteria is generated.

[1081] 4. Emotional engine regulation:

[1082] The server uses an emotion engine to analyze the user's emotion data and adjust the parameters of the generative AI model.

[1083] Example: If a user is feeling stressed, the emotion engine will train the model to suggest recipes that include ingredients and cooking methods that have a relaxing effect.

[1084] 5. Recipe provided:

[1085] The server sends the generated recipe to the terminal.

[1086] Example: Generate a recipe for "vegetarian pasta that can be made in under 30 minutes" and send it to your device.

[1087] 6. Collect and use feedback:

[1088] The server collects user feedback and retrains the generative AI model, improving the accuracy of the recipes.

[1089] Example: If a user provides feedback such as "the pasta was bland," that information is included in the training data.

[1090] Terminal

[1091] The terminal interfaces directly with the user and provides the following functions:

[1092] 1. Fill in your user profile:

[1093] The terminal displays a form for the user to enter preferences, dietary history, and allergy information, and sends the entered data to the server.

[1094] Example: A user enters the information "I am a vegetarian" into a terminal and presses the send button.

[1095] 2. Enter your recipe request:

[1096] The terminal provides a form for the user to input desired recipe conditions, and the input information is sent to the server.

[1097] Example: A user enters information about a "vegetarian meal that can be prepared in under 30 minutes" and submits it.

[1098] 3. View recipe:

[1099] The terminal displays the recipe sent from the server to the user.

[1100] Example: Display a recipe for "Vegetarian pasta in under 30 minutes."

[1101] 4. Enter emotion data:

[1102] The device provides an interface to capture the user's emotions and uses a facial recognition camera and voice assistant.

[1103] Example: The device reads the user's emotions through a facial recognition camera and transmits the information to a server.

[1104] 5. Enter your feedback:

[1105] The terminal provides a form for users to enter feedback on the recipes they create.

[1106] Example: A user types "The pasta was bland" and presses the submit button.

[1107] User

[1108] The user uses the system in the following steps:

[1109] 1. Provide your profile information:

[1110] Users enter their preferences, dietary history, and allergy information into a form on the terminal.

[1111] Example: A user enters "I follow a gluten-free diet."

[1112] 2. Specify recipe conditions:

[1113] The user inputs the desired recipe conditions into a form on the terminal.

[1114] Example: A user requests a "gluten-free snack that can be made in under 10 minutes."

[1115] 3. Providing Emotion Data:

[1116] Users provide emotion data through their devices, which may be achieved through facial recognition cameras or voice-based emotion recognition.

[1117] Example: When a user feels stressed, the emotional data is sent to the server via the device.

[1118] 4. Check the recipe and cook:

[1119] The user checks the recipe displayed on the terminal and prepares the dish.

[1120] Example: Make cookies based on the recipe for "10-Minute Gluten-Free Cookies."

[1121] 5. Providing Feedback:

[1122] The user enters their thoughts and suggestions for improvement on the recipe they have cooked into a form on their device and sends it to the server.

[1123] Example: A user types, "I prefer the cookies to be a little softer."

[1124] Prompt Sentence Examples

[1125] "Spicy vegetarian pasta that can be made in 30 minutes"

[1126] "Gluten-free snacks you can make in under 10 minutes"

[1127] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1128] Step 1:

[1129] Enter your user profile

[1130] Subject: Device

[1131] Description: The device displays a form for users to enter their preferences, dietary history, and allergy information. When the user enters information into the form and presses the submit button, the data is sent to the server in JSON or XML format.

[1132] Input: User inputs profile information (preferences, dietary history, allergy information)

[1133] Output: Profile information sent to the server

[1134] Step 2:

[1135] Receiving and storing user profiles

[1136] Subject: Server

[1137] Description: The server receives user profile information sent from the device and stores it in a database, which can be MongoDB or MySQL.

[1138] Input: User profile information sent from the device

[1139] Output: Profile information stored in a database

[1140] What happens: The server receives the HTTP request, the parser parses the data, and then inserts the data into the database.

[1141] Step 3:

[1142] Training a generative AI model

[1143] Subject: Server

[1144] Description: The server retrieves user profile data from a database and trains a generative AI model (e.g., GPT-3) after preprocessing the data, which includes text cleaning and tokenization.

[1145] Input: User profile data stored in the database

[1146] Output: Trained generative AI model

[1147] What it does: Cleans data using data science libraries (e.g., Pandas, NLTK) to build a training dataset, then trains a generative AI model.

[1148] Step 4:

[1149] Acquiring emotion data

[1150] Subject: Device

[1151] Description: The device collects emotional data using a facial recognition camera or voice assistant to obtain the user's emotional data, which is then sent to a server.

[1152] Input: User emotion data (face recognition results, voice analysis results)

[1153] Output: Emotion data sent to the server

[1154] Specific operation: The device activates the camera to capture the user's facial expression, estimates the emotion using a facial recognition algorithm, and sends the data to the server.

[1155] Step 5:

[1156] Entering a Recipe Request

[1157] Subject: Device

[1158] Description: The terminal displays a form for the user to enter the desired recipe conditions (required time, type of ingredients, etc.) When the user enters the conditions and presses the send button, the data is sent to the server.

[1159] Input: User input of recipe conditions

[1160] Output: Recipe conditions sent to the server

[1161] Specific operation: By entering conditions into the form input fields and pressing the submit button, the data is sent to the server as an HTTP request.

[1162] Step 6:

[1163] Recipe Generation

[1164] Subject: Server

[1165] Description: The server generates recipes using a generative AI model based on the user's profile data and recipe conditions. If emotional data is included, the model parameters are adjusted taking that data into account.

[1166] Input: Profile data, emotion data, recipe conditions stored on the server

[1167] Output: The generated recipe

[1168] What it does: Enter a prompt into GPT-3, such as "vegetarian recipe that can be made in under 30 minutes," and retrieve the generated recipe.

[1169] Step 7:

[1170] Recipe provided

[1171] Subject: Server

[1172] Description: The server sends the generated recipe to the terminal. The terminal displays the received recipe to the user.

[1173] Input: Generated recipe

[1174] Output: The recipe displayed on the user's terminal

[1175] Specific operation: The generated recipe is sent to the terminal in the form of an HTTP response, and the terminal receives it and displays it on the screen.

[1176] Step 8:

[1177] Enter your feedback

[1178] Subject: Device

[1179] Description: The terminal provides a form for users to enter feedback on the recipes they have created. When the user enters their feedback and presses the submit button, the data is sent to the server.

[1180] Input: User input of feedback

[1181] Output: Feedback sent to the server

[1182] Specific behavior: By entering feedback into the form input fields and pressing the submit button, the data is sent to the server as an HTTP request.

[1183] Step 9:

[1184] Save and retrain feedback

[1185] Subject: Server

[1186] Description: The server stores the received feedback in a database and retrains the generative AI model based on that feedback.

[1187] Input: User-submitted feedback

[1188] Output: A generative AI model that reflects the learning results

[1189] Specific operation: The new feedback data is stored in the database and added to the existing training dataset for retraining.

[1190] (Application example 2)

[1191] 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."

[1192] Conventional recipe provision systems have limitations in personalization based on user preferences and allergy information, and in particular, they have a problem of insufficient provision of appropriate services based on emotional data. Furthermore, the in-car environment is not optimized to reflect the emotional state of the occupants, so passenger comfort cannot be fully ensured.

[1193] 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.

[1194] In this invention, the server includes means for collecting user preferences, dietary history, and allergy information, means for training a generative AI model based on the user's profile, means for generating recipes that meet the user's desired conditions using the trained generative AI model, means for providing the generated recipes to the user, means for collecting user feedback and improving the accuracy of the generative AI model, means for recognizing and analyzing the user's emotions and adjusting the parameters of the generative AI model based on the results, and means for optimizing the in-car environment based on the emotion data, thereby enabling the provision of personalized recipes according to the user's emotional state and the optimization of the in-car environment.

[1195] "User preferences" refer to the characteristics and types of food and recipes that a user prefers.

[1196] "Dietary history" refers to the history and trends of the meals a user has eaten in the past.

[1197] "Allergy information" refers to information indicating that a user has an allergic reaction to a particular food or ingredient.

[1198] "User profile" refers to all information about an individual, such as the user's preferences, dietary history, and allergy information.

[1199] A "generative AI model" is an artificial intelligence model that generates recipes based on collected user profile information.

[1200] A "recipe" is a set of instructions that specifically outlines cooking steps and a list of ingredients.

[1201] "Feedback" refers to information such as impressions and ratings of a recipe after the user has actually tried it.

[1202] "Emotional data" refers to information related to the user's emotional state, which can be obtained from facial expressions, tone of voice, heart rate, etc.

[1203] "In-vehicle environment" refers to the physical conditions of the space occupied by occupants inside an autonomous vehicle, including lighting, acoustics, temperature, and air quality.

[1204] A "parameter" is a numerical value that determines the behavior and performance of a generative AI model.

[1205] To implement this invention, a system is constructed in which a server, a terminal, and a user cooperate with each other. The server plays the following main roles.

[1206] server

[1207] The server operates as follows to collect user information and provide recipes using generative AI models.

[1208] 1. Collecting and storing user profiles

[1209] The server receives the user's preferences, dietary history, allergy information, and emotional data sent from the device and stores it in a database. For example, if a user enters "I'm a vegetarian and I have a peanut allergy," this information will be stored in the database.

[1210] 2. Training the generative AI model

[1211] The server trains a generative AI model based on the collected user profile. Specifically, for example, for a user who has a preference for spicy food, the model learns patterns of spicy ingredients and recipes.

[1212] 3. Recipe Generation

[1213] The server uses the learned generative AI model to generate recipes that meet the user's desired conditions (time required, type of ingredients, etc.) For example, it generates a recipe based on a user request such as "I want a vegetarian dish that can be made in under 30 minutes."

[1214] 4. Emotional Engine Adjustment

[1215] The server uses an emotion engine to analyze the user's emotional state and adjusts the parameters of the generative AI model based on the results: if the user is feeling stressed, the model is adjusted to suggest dishes that have a relaxing effect.

[1216] 5. Optimizing the in-car environment

[1217] The environment inside the autonomous vehicle (lighting, music, temperature, etc.) is optimized based on emotional data. Specifically, if the passenger wants to relax, relaxing music will be played and the temperature will be set appropriately.

[1218] 6. Collect and use feedback

[1219] The generative AI model is retrained to improve its accuracy using user-provided feedback. For example, if feedback such as "the pasta was bland" is collected, this is reflected in the model.

[1220] Terminal

[1221] The terminal serves the following roles as an interface with the user.

[1222] 1. Enter your user profile

[1223] The terminal provides a form for users to input their preferences, dietary history, and allergy information, which is then sent to the server.

[1224] 2. Enter your recipe request

[1225] The user inputs the desired conditions (time required, type of material, etc.) and sends the request to the server.

[1226] 3. View recipes

[1227] The original recipe sent from the server is displayed and provided to the user.

[1228] 4. Entering Emotion Data

[1229] Using facial recognition cameras and voice assistants, users' emotional data is collected and sent to a server.

[1230] 5. Enter your feedback

[1231] The user inputs feedback about the created recipe and sends it to the server.

[1232] User

[1233] Users can access the system via their device and are provided with individually optimized recipes and in-car environments.

[1234] 1. Providing Profile Information

[1235] The user enters profile information using a form on the terminal and sends it to the server.

[1236] 2. Specify recipe conditions

[1237] Use the terminal to specify recipe conditions (required time, type of ingredients).

[1238] 3. Providing Emotion Data

[1239] Using a facial recognition camera or voice assistant, you can provide your emotional state to the system.

[1240] 4. Check the recipe and cook

[1241] Cook a dish based on the recipe provided and check the results.

[1242] 5. Providing Feedback

[1243] Feedback about the cooked recipe is entered into the terminal and sent to the server.

[1244] Specific examples

[1245] For example, if a user inputs "I'm vegetarian and would like a recipe that can be made in 30 minutes or less," the server will use the trained generative AI model to generate the appropriate recipe and provide it to the user via their device. Also, if the user is feeling stressed, the server will suggest recipes and in-car environments that have a relaxing effect.

[1246] Prompt Sentence Examples

[1247] "The passenger is stressed, so please set the car to relaxing music and an appropriate temperature. The passenger's profile information is that they like classical music and are allergic to pollen."

[1248] These components enable the system to provide personalized recipes that take into account the user's emotional state and optimize the in-car environment.

[1249] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1250] Step 1:

[1251] The user enters their user profile on the device. Using the device, the user enters their preferences, dietary history, allergy information, etc., which the device then sends to the server. Specific input data includes "user's name," "being a vegetarian," "having a peanut allergy," etc. The server stores this input data in a database.

[1252] Step 2:

[1253] Recipe requests are input via the device. The user inputs the desired recipe conditions (e.g., vegetarian food, time required within 30 minutes) through the device interface. This request data is sent from the device to the server. The server uses this data to train the generative AI model and generate the recipe.

[1254] Step 3:

[1255] The generative AI model is trained on the server. The server trains the generative AI model based on the user profile information collected in step 1. Specifically, the model learns preference information such as "I like spicy food" and recognizes patterns of spicy ingredients and recipes. This process obtains the user profile as input and the trained AI model as output.

[1256] Step 4:

[1257] The server generates the recipe. Using the trained generative AI model, it generates a recipe that matches the user's desired conditions entered in step 2. For example, if the user enters "I'm looking for a vegetarian dish that can be prepared in under 30 minutes," the generative AI model creates a recipe that meets those conditions, and the server sends the recipe to the device.

[1258] Step 5:

[1259] Analyzes emotional states and adjusts parameters. The server uses an emotion engine to analyze the user's emotional data sent from the device and adjusts the parameters of the generative AI model based on the results. For example, if the user is feeling stressed, the generative AI model is adjusted to suggest dishes that have a relaxing effect. This process obtains emotional data as input and an adjusted AI model as output.

[1260] Step 6:

[1261] Optimizing the in-car environment. The server optimizes the environment inside the autonomous vehicle based on emotional data. Specifically, when the passenger feels like relaxing, it plays relaxing music and sets the temperature appropriately. This process obtains emotional data as input and optimized in-car environment settings as output.

[1262] Step 7:

[1263] It collects and utilizes feedback. The device provides an interface for inputting and sending feedback from users, who input their thoughts and ratings on the recipes they have cooked. The server collects this feedback and performs re-learning to improve the accuracy of the generative AI model. A specific example of how this works is to retrain the AI ​​model based on feedback such as "the pasta was bland." This process obtains feedback data as input and an improved AI model as output.

[1264] 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.

[1265] 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.

[1266] 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.

[1267] [Third embodiment]

[1268] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1269] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1270] 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).

[1271] 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.

[1272] 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.

[1273] 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).

[1274] 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.

[1275] 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.

[1276] 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.

[1277] 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.

[1278] 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.

[1279] 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."

[1280] The present invention relates to a system that collects and analyzes user preferences, dietary history, and allergy information, and provides recipes optimized for each individual user.

[1281] Server embodiment

[1282] The server has the following main functions:

[1283] 1. Collecting and storing user profiles

[1284] The server receives the user's preferences, dietary history, and allergy information sent from the terminal.

[1285] The received information is stored in a database.

[1286] Example: If a user provides information such as "I'm a vegetarian and I have a peanut allergy," the server stores that information in a database.

[1287] 2. Training the generative AI model

[1288] The server trains a generative AI model based on the collected user profiles.

[1289] Example: Based on a user's preference information such as "I like spicy food," the model learns patterns of spicy ingredients and recipes.

[1290] 3. Recipe Generation

[1291] The server uses the learned generative AI model to generate recipes that meet the user's desired conditions (time required, type of ingredients, etc.).

[1292] Example: If a user requests a vegetarian meal that can be prepared in under 30 minutes, the server generates a recipe that reflects that request.

[1293] 4. Providing recipes

[1294] The server sends the generated original recipe to the terminal.

[1295] Example: Send a server-generated recipe for "vegetarian pasta that can be made in under 30 minutes."

[1296] 5. Collect and use feedback

[1297] The server receives feedback from users and uses it to retrain the generative AI model to improve its accuracy.

[1298] Example: If a user provides feedback such as "The vegetarian pasta was bland," that feedback is reflected as training data.

[1299] Terminal embodiment

[1300] The terminal acts as an interface with the user:

[1301] 1. Enter your user profile

[1302] The terminal provides a form for the user to input preferences, dietary history, and allergy information.

[1303] The entered profile information is sent to the server.

[1304] Example: A user enters the information "I am a vegetarian" into a terminal and presses the send button.

[1305] 2. Enter your recipe request

[1306] The terminal provides a form for the user to input desired recipe conditions (required time, type of ingredients, etc.).

[1307] The input request is sent to the server.

[1308] Example: A user enters information about a "vegetarian meal that can be prepared in under 30 minutes" and presses the submit button.

[1309] 3. View recipes

[1310] The terminal receives the original recipe sent from the server and displays it to the user.

[1311] Example: Display a recipe sent from the server for "vegetarian pasta that can be made in under 30 minutes."

[1312] 4. Enter your feedback

[1313] The terminal provides a form for users to enter feedback on the recipes they have created.

[1314] The input feedback information is sent to the server.

[1315] Example: A user enters feedback such as "The pasta was bland" and presses the submit button.

[1316] User's embodiment

[1317] Users use the system to receive recipes tailored to their personal tastes and requirements:

[1318] 1. Providing Profile Information

[1319] The user enters their preferences, dietary history, and allergy information into a form on the terminal.

[1320] Example: A user enters that they "follow a gluten-free diet."

[1321] 2. Specify recipe conditions

[1322] The user inputs the conditions of the desired recipe into a form on the terminal.

[1323] Example: A user requests a "gluten-free snack that can be made in under 10 minutes."

[1324] 3. Check the recipe and cook

[1325] The user checks the recipe displayed on the terminal and prepares the dish based on it.

[1326] Example: A user makes cookies based on the recipe for "10-Minute Gluten-Free Cookies" displayed on their device.

[1327] 4. Providing Feedback

[1328] Users enter their thoughts and suggestions for improvement about the recipe they have cooked into a form on their device and send the feedback to the server.

[1329] Example: A user provides feedback such as "I would prefer the cookies to be a little softer."

[1330] The processing flow will be explained below.

[1331] Server Processing

[1332] Step 1:

[1333] The server receives the user's preferences, dietary history, and allergy information sent from the terminal.

[1334] Step 2:

[1335] The server stores the received user profile information in a database.

[1336] Step 3:

[1337] The server retrieves the user profile from the database and inputs it into the generative AI model for learning.

[1338] Step 4:

[1339] The server receives the recipe conditions (required time, type of ingredients, etc.) sent from the terminal.

[1340] Step 5:

[1341] The server uses a generative AI model to generate recipes that fit the user's requirements, taking into account the difficulty of obtaining ingredients and the time required.

[1342] Step 6:

[1343] The server sends the generated recipe to the terminal.

[1344] Step 7:

[1345] The server receives the user feedback sent from the terminal.

[1346] Step 8:

[1347] The server stores the received feedback in a database and uses it to retrain the generative AI model to improve its accuracy.

[1348] Terminal handling

[1349] Step 1:

[1350] The terminal provides the user with a form to enter information about preferences, dietary history, and allergies.

[1351] Step 2:

[1352] The profile information entered by the user is sent to the server.

[1353] Step 3:

[1354] The terminal provides the user with a form for inputting the desired recipe conditions (required time, type of ingredients, etc.).

[1355] Step 4:

[1356] A recipe request entered by the user is sent to the server.

[1357] Step 5:

[1358] The terminal receives the original recipe sent from the server.

[1359] Step 6:

[1360] The terminal displays the received recipe in an easy-to-understand manner for the user.

[1361] Step 7:

[1362] The terminal provides the user with a form to enter feedback about the recipe.

[1363] Step 8:

[1364] Sends the user-entered feedback to the server.

[1365] User Action

[1366] Step 1:

[1367] Users enter their preferences, dietary history, and allergy information into a form on the terminal.

[1368] Step 2:

[1369] The user sends the entered profile information to the server.

[1370] Step 3:

[1371] The user inputs the desired recipe conditions into a form on the terminal.

[1372] Step 4:

[1373] The user inputs a recipe request and sends it to the server.

[1374] Step 5:

[1375] The user checks the recipe displayed on the terminal.

[1376] Step 6:

[1377] The user creates a dish based on the displayed recipe.

[1378] Step 7:

[1379] The user enters feedback about the created recipe into a form on the terminal.

[1380] Step 8:

[1381] The user sends the input feedback to the server.

[1382] Example 1

[1383] 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."

[1384] Conventional recipe provision systems have difficulty providing optimal recipes based on individual users' preferences, dietary history, and allergy information. Furthermore, they lack a mechanism for collecting user feedback to improve the system's accuracy, making it impossible to respond quickly and accurately to user needs. This has resulted in problems such as users having to spend time and effort searching for recipes that suit them.

[1385] 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.

[1386] In this invention, the server includes means for collecting user preferences, dietary history, and allergy information, means for training a generative AI model based on the user's profile, means for generating recipes that meet the user's desired conditions using the trained generative AI model, means for providing the generated recipes to the user, and means for collecting user feedback and improving the accuracy of the generative AI model. This makes it possible to quickly and accurately respond to the user's individual needs and provide optimal recipes. Furthermore, by generating recipes using prompts, recipes that meet the user's preferences can be quickly generated. Furthermore, by saving the user's profile and feedback, the accuracy of the system can be continuously improved.

[1387] "User preferences" refers to information about the user's favorite foods and cooking methods.

[1388] "Dietary history" refers to historical information about meals the user has taken in the past.

[1389] "Allergy information" refers to data about foods or ingredients to which a user has an allergic reaction.

[1390] A "generative AI model" is an artificial intelligence model that learns data and generates recipes based on the user's preferences and conditions.

[1391] "User profile" refers to personal data such as a user's preferences, dietary history, and allergy information.

[1392] A "recipe" is a list of instructions and ingredients for making a particular dish.

[1393] "Feedback" refers to the user's thoughts and evaluations of the system and recipes.

[1394] A "prompt" is a condition or instruction that is input to a generative AI model to generate a recipe.

[1395] A "database" is a system that organizes and stores collected information so that it can be searched and retrieved when needed.

[1396] A "server" is a computer system that collects, processes, stores, and serves information from users.

[1397] A "terminal" is a device that a user uses to enter information and receive generated recipes.

[1398] This invention relates to a system that collects and analyzes user preferences, dietary history, and allergy information to provide recipes optimized for each user. This system consists of three main elements: a server, a terminal, and a user.

[1399] Server embodiment

[1400] The server has the following features:

[1401] 1. Collecting and storing user profiles

[1402] The server receives the user's preferences, dietary history, and allergy information sent from the device and stores it in a database. For example, if a user provides information that they are "vegetarian and have a peanut allergy," the server stores that information in the database.

[1403] 2. Training the generative AI model

[1404] The server trains a generative AI model based on the collected user profile. For example, based on the user's preference information "I like spicy food," the model learns patterns of spicy ingredients and recipes.

[1405] 3. Recipe Generation

[1406] The server uses the learned generative AI model to generate recipes that meet the user's desired conditions (time required, type of ingredients, etc.). For example, if the user requests a "vegetarian dish that can be made in 30 minutes or less," the server generates a recipe that reflects those conditions. An example of a prompt sentence is "Please generate a recipe for a vegetarian dish that can be made in 30 minutes or less."

[1407] 4. Providing the generated recipe

[1408] The server sends the generated recipe to the device. For example, the server sends the generated recipe for "vegetarian pasta that can be made in 30 minutes or less" to the device.

[1409] 5. Collecting and Using Feedback

[1410] The server receives feedback from users and retrains the generative AI model to improve its accuracy. For example, if a user provides feedback such as "the vegetarian pasta was bland," the server incorporates this feedback into the training data.

[1411] Terminal embodiment

[1412] The terminal acts as an interface with the user:

[1413] 1. Enter your user information

[1414] The terminal provides a form for the user to input information about preferences, dietary history, and allergies, and transmits the input profile information to the server. For example, the user inputs information such as "I am a vegetarian" into the terminal and presses the send button.

[1415] 2. Enter recipe conditions

[1416] The terminal provides a form for the user to input the desired recipe conditions (time required, type of ingredients, etc.) and sends the input request to the server. For example, a user inputs information requesting "vegetarian dishes that can be made in 30 minutes or less" and presses the send button.

[1417] 3. View recipes

[1418] The device receives the original recipe sent from the server and displays it to the user. For example, the device displays a recipe for "vegetarian pasta that can be made in under 30 minutes."

[1419] 4. Enter your feedback

[1420] The terminal provides a form for the user to input feedback on the recipe created by the user, and transmits the input feedback information to the server. For example, the user inputs feedback such as "the pasta was bland" and presses the send button.

[1421] User's embodiment

[1422] To use the optimized recipe, users follow these steps:

[1423] 1. Providing Profile Information

[1424] The user enters their preferences, dietary history, and allergy information into a form on the terminal. For example, the user enters that they follow a gluten-free diet.

[1425] 2. Specify recipe conditions

[1426] The user inputs the desired recipe conditions into a form on the terminal. For example, the user specifies "a gluten-free snack that can be made in 10 minutes or less." An example of a prompt sentence is "Please generate a recipe for a gluten-free snack that can be made in 10 minutes or less."

[1427] 3. Check the recipe and cook

[1428] The user checks the recipe displayed on the device and prepares the dish based on it. For example, the user makes cookies based on the recipe for "10-minute gluten-free cookies" displayed on the device.

[1429] 4. Providing Feedback

[1430] The user inputs their thoughts and suggestions for improvement about the recipe into a form on the device and sends the feedback to the server. For example, the user inputs feedback such as "I wish the cookies were a little softer when baked."

[1431] By implementing this system, users can quickly and accurately receive recipes optimized for their preferences and conditions. In addition, by continuously collecting and incorporating feedback from users, the accuracy of the generative AI model can be improved, enabling the provision of better services.

[1432] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1433] Step 1:

[1434] Entering User Profile Information

[1435] The terminal displays a form for the user to enter preferences, dietary history, and allergy information.

[1436] The user enters information into the form displayed on the terminal and presses the "Submit" button.

[1437] Input: User preferences, dietary history, and allergy information (e.g., "I'm vegetarian and have a peanut allergy").

[1438] Output: The entered information is sent from the terminal to the server.

[1439] Specific operation: When the user clicks the "Submit" button, the input information is sent from the terminal to the server.

[1440] Step 2:

[1441] Submitting and storing profile information

[1442] The terminal transmits the information entered by the user to the server.

[1443] The server stores the received information in a database.

[1444] Input: User profile information (e.g., "I'm a vegetarian and have a peanut allergy").

[1445] Output: The information is stored in a database.

[1446] Specific operation: The server analyzes the received data and stores it in a database.

[1447] Step 3:

[1448] Training a generative AI model

[1449] The server trains the generative AI model based on user information stored in a database.

[1450] Input: User information stored in a database (e.g., "I like spicy food").

[1451] Output: A trained generative AI model.

[1452] How it works: The server inputs the stored data into the AI ​​model, allowing it to learn patterns.

[1453] Step 4:

[1454] Entering recipe conditions

[1455] The terminal provides a form for the user to input desired recipe conditions (required time, type of ingredients, etc.).

[1456] The user inputs the desired conditions and presses the "Submit" button.

[1457] Input: User recipe criteria (e.g., "vegetarian meals that can be made in under 30 minutes").

[1458] Output: The entered conditions are sent from the terminal to the server.

[1459] Specific operation: When the user clicks the "Send" button, the desired conditions are sent from the terminal to the server.

[1460] Step 5:

[1461] Sending and generating recipe conditions

[1462] The terminal transmits the input conditions to the server.

[1463] The server generates a recipe using a generative AI model based on the received conditions.

[1464] Input: User recipe criteria (e.g., "vegetarian meals that can be made in under 30 minutes").

[1465] Output: The generated recipe (e.g. "Vegetarian pasta in under 30 minutes").

[1466] Specific operation: The server provides the conditions as prompts to the generative AI model, which then generates the optimal recipe. An example of the prompt is, "Generate a vegetarian recipe that can be made in under 30 minutes."

[1467] Step 6:

[1468] Providing the generated recipe

[1469] The server transmits the generated recipe to the terminal.

[1470] The terminal displays the received recipe to the user.

[1471] Input: The generated recipe (e.g., "Vegetarian pasta in under 30 minutes").

[1472] Output: The recipe is printed to the terminal.

[1473] Specific behavior: The server sends the recipe to the device, and the device displays it to the user.

[1474] Step 7:

[1475] Enter your feedback

[1476] The terminal provides a form for users to enter feedback on the recipes they have created.

[1477] The user enters the feedback and presses the "Submit" button.

[1478] Input: User feedback (e.g., "The pasta was bland").

[1479] Output: The input feedback information is sent from the device to the server.

[1480] Specific operation: When the user clicks the "Submit" button, the feedback information is sent from the terminal to the server.

[1481] Step 8:

[1482] Send and save feedback

[1483] The terminal transmits the input feedback to the server.

[1484] The server stores the received feedback in a database.

[1485] Input: User feedback information (e.g., "The pasta was bland").

[1486] Output: The feedback information is stored in a database.

[1487] Specific behavior: The server analyzes the received feedback and stores it in a database.

[1488] Step 9:

[1489] Reflecting feedback

[1490] The server retrains the generative AI model based on the collected feedback, improving the model's accuracy.

[1491] Input: Feedback information stored in a database (e.g., "The pasta was bland").

[1492] Output: A generative AI model with improved accuracy.

[1493] Specific operation: The server inputs the feedback data into the AI ​​model and retrains the model.

[1494] (Application example 1)

[1495] 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."

[1496] Conventional food delivery systems have difficulty suggesting optimal dishes based on a user's individual preferences, allergies, and dietary history. Even if a system existed that provided recipes that matched a user's desired conditions, it was not possible to link the system directly from ordering to delivery. This made it difficult for users to easily enjoy dishes that suited their dietary habits. Furthermore, the system lacked sufficient functionality to reflect user feedback and improve the accuracy of recipes.

[1497] 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.

[1498] In this invention, the server includes a means for collecting user preferences, dietary history, and allergy information, a means for training a generative AI model based on the user's profile, and a means for generating recipes that meet the user's desired conditions using the trained generative AI model. This allows the user to receive individually optimized recipe suggestions. The server also includes a means for providing the generated recipes to the user and a means for collecting feedback from the user to improve the accuracy of the generative AI model. Furthermore, the server includes a means for suggesting individually optimized dishes based on the user's profile and a means for directly ordering the suggested dishes and delivering them to a specified address, allowing the user to easily order and quickly receive dishes that suit their diet. This system allows users to easily enjoy dishes tailored to their preferences and constraints, and further improves accuracy based on feedback.

[1499] "User preferences" refers to information about the dishes and ingredients that the user likes to eat.

[1500] "Dietary history" is a record of the foods and meals a user has eaten in the past.

[1501] "Allergy information" is information about foods and ingredients that cause allergic reactions to the user.

[1502] A "generative AI model" is a model that learns and is generated using artificial intelligence, and suggests optimal recipes based on the user's individual information.

[1503] "Profile" is a general term for personal information such as a user's preferences, dietary history, and allergy information.

[1504] A "recipe" is a guideline that shows the steps and ingredients for making a dish.

[1505] "Feedback" refers to the user's evaluation of the food they have provided and their suggestions for improvement.

[1506] "Delivery" is the process of delivering the food ordered by the user to the address specified.

[1507] A "means" is a method or device for achieving a specific function or purpose.

[1508] The system of this invention is realized through collaboration between a server and a terminal, and provides optimized meals based on the user's preferences, dietary history, and allergy information, and then handles the entire process from directly ordering the meals to delivery.

[1509] The server has the following main functions:

[1510] 1. Collecting user preferences, dietary history, and allergy information

[1511] The server receives the user's preferences, dietary history, and allergy information sent from the device and stores it in a database. For example, if a user provides information such as "I'm a vegetarian and have a peanut allergy," the server stores that information in the database.

[1512] 2. Training the generative AI model

[1513] The server trains a generative AI model based on the collected user profile information, allowing it to suggest dishes optimized for the user's preferences and conditions. For example, if a user has a preference for spicy food, the server can train the model to recommend spicy recipes.

[1514] 3. Recipe Generation

[1515] The server uses the trained generative AI model to generate recipes that meet the user's criteria. For example, for a request for "vegetarian dishes that can be made in under 30 minutes," it generates a recipe for vegetarian pasta.

[1516] 4. Providing recipes and taking orders

[1517] The generated recipe is sent from the server to the terminal, where the user can check it and order it directly. For example, a user can view the suggested vegetarian pasta recipe and order it if they like it.

[1518] 5. Collecting user feedback and improving model accuracy

[1519] When users send feedback about the food they've been served, the server collects it and uses it to retrain the generative AI model. For example, feedback like "the pasta was bland" can be reflected in the next recommendation.

[1520] The terminal has the following main functions:

[1521] 1. Enter your user profile

[1522] The device has a form where users can enter their preferences, allergy information, and dietary history, for example, "I'm a vegetarian and have a peanut allergy."

[1523] 2. Enter your recipe request

[1524] It provides a form where users can input their desired cooking criteria and send it to the server. For example, they can input criteria such as "vegetarian dishes that can be prepared in 30 minutes or less."

[1525] 3. View recipes and order

[1526] The recipe sent from the server is displayed on the device, and the user can check the recipe. Also, by pressing the order button, the user can directly order the dish. For example, a recipe for vegetarian pasta can be displayed and the user can order it.

[1527] 4. Enter your feedback

[1528] It has a form where users can enter their feedback about the food and send it to the server. For example, they can enter feedback such as "The pasta was bland."

[1529] As a concrete example, if a vegetarian user requests a dish that can be prepared in under 30 minutes, the server generates a recipe based on that condition and sends it to the device. The user then orders a dish based on the generated recipe and it is delivered. Feedback on the dish can then be sent from the device to improve the accuracy of the next suggestion.

[1530] Example prompt for a generative AI model:

[1531] Suggest the best recipes based on your user profile below.

[1532] Food preference: Vegetarian

[1533] Allergy Information: Peanuts

[1534] Time required: 30 minutes or less

[1535] Generate the best vegetarian, peanut-free recipe that can be made in under 30 minutes and meets the following criteria:

[1536] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1537] Step 1:

[1538] The user inputs and sends profile information (preferences, dietary history, allergy information) into the device. Input data: Information such as "I'm a vegetarian and have a peanut allergy." The input data is sent from the device to the server.

[1539] Step 2:

[1540] The server receives the user's profile information sent from the device and stores it in a database, which includes information on preferences, dietary history, and allergies.

[1541] Step 3:

[1542] The server trains the generative AI model based on the collected user profile information. Input data: User preferences, past dietary data, and allergy information. The generative AI model uses this data to learn how to suggest recipes.

[1543] Step 4:

[1544] The user inputs specific recipe requirements (time required, type of ingredients, etc.) from the terminal and sends them to the server. Input data: For example, desired requirements for a vegetarian dish that can be made in 30 minutes or less.

[1545] Step 5:

[1546] The server uses the trained generative AI model to generate recipes that best fit the user's desired conditions. Input data: the trained model and the user's request conditions. Output data: a vegetarian pasta recipe that can be made in under 30 minutes, for example.

[1547] Step 6:

[1548] The server sends the generated recipe to the terminal, which displays it to the user. Input data: Data on the generated recipe. Output data: Recipe display on the user's terminal screen.

[1549] Step 7:

[1550] The user checks the provided recipe and places an order. Input data: User's confirmation and order intention. The terminal sends the order information to the server.

[1551] Step 8:

[1552] The server accepts the user's order and arranges delivery to the specified address. Input data: User's order information and delivery address. Output data: Order processing and start of delivery procedure.

[1553] Step 9:

[1554] The user inputs feedback about the dish from the terminal and sends it to the server. Input data: Contents of the feedback (for example, "The pasta was bland").

[1555] Step 10:

[1556] The server receives feedback from users and uses it to retrain the generative AI model. Input data: Feedback information. Output data: Improved generative AI model.

[1557] 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.

[1558] This invention relates to a system that provides recipes optimized for individual users based on their preferences, dietary history, allergy information, and emotions. This system combines a generative AI model and an emotion engine to provide more personalized recipes.

[1559] Server embodiment

[1560] The server has the following main functions:

[1561] 1. Collecting and storing user profiles

[1562] The server receives the user's preferences, dietary history, and allergy information sent from the terminal.

[1563] The received information is stored in a database.

[1564] Example: If a user provides information such as "I'm a vegetarian and I have a peanut allergy," the server stores that information in a database.

[1565] 2. Training the generative AI model

[1566] The server trains a generative AI model based on the collected user profiles.

[1567] Example: Based on a user's preference information such as "I like spicy food," the model learns patterns of spicy ingredients and recipes.

[1568] 3. Recipe Generation

[1569] The server uses the learned generative AI model to generate recipes that meet the user's desired conditions (time required, type of ingredients, etc.).

[1570] Example: If a user requests a vegetarian meal that can be prepared in under 30 minutes, the server generates a recipe that reflects that request.

[1571] 4. Emotional Engine Adjustment

[1572] The server uses an emotion engine to recognize and analyze the user's emotions and adjusts the parameters of the generative AI model based on the results.

[1573] Example: If a user is feeling stressed, the emotion engine will adjust the generative AI model to suggest recipes that include ingredients and cooking methods that have a relaxing effect.

[1574] 5. Providing recipes

[1575] The server sends the generated original recipe to the terminal.

[1576] Example: Send a server-generated recipe for "vegetarian pasta that can be made in under 30 minutes."

[1577] 6. Collect and use feedback

[1578] The server receives feedback from users and uses it to retrain the generative AI model to improve its accuracy.

[1579] Example: If a user provides feedback such as "The vegetarian pasta was bland," that feedback is reflected as training data.

[1580] Terminal embodiment

[1581] The terminal acts as an interface with the user:

[1582] 1. Enter your user profile

[1583] The terminal provides a form for the user to input preferences, dietary history, and allergy information.

[1584] The entered profile information is sent to the server.

[1585] Example: A user enters the information "I am a vegetarian" into a terminal and presses the send button.

[1586] 2. Enter your recipe request

[1587] The terminal provides a form for the user to input desired recipe conditions (required time, type of ingredients, etc.).

[1588] The input request is sent to the server.

[1589] Example: A user enters information about a "vegetarian meal that can be prepared in under 30 minutes" and presses the submit button.

[1590] 3. View recipes

[1591] The terminal receives the original recipe sent from the server and displays it to the user.

[1592] Example: Display a recipe sent from the server for "vegetarian pasta that can be made in under 30 minutes."

[1593] 4. Entering Emotion Data

[1594] The device provides an interface for inputting and acquiring user emotions, which can be read using a facial recognition camera or voice assistant.

[1595] Example: The device reads the user's emotions through a facial recognition camera and transmits them to a server.

[1596] 5. Enter your feedback

[1597] The terminal provides a form for users to enter feedback on the recipes they have created.

[1598] The input feedback information is sent to the server.

[1599] Example: A user enters feedback such as "The pasta was bland" and presses the submit button.

[1600] User's embodiment

[1601] Users use the system to receive recipes tailored to their personal tastes and requirements:

[1602] 1. Providing Profile Information

[1603] The user enters their preferences, dietary history, and allergy information into a form on the terminal.

[1604] Example: A user enters that they "follow a gluten-free diet."

[1605] 2. Specify recipe conditions

[1606] The user inputs the desired recipe conditions into a form on the terminal.

[1607] Example: A user requests a "gluten-free snack that can be made in under 10 minutes."

[1608] 3. Providing Emotion Data

[1609] Users provide their emotional data through the device's interface, and in some cases emotion recognition is performed using a facial recognition camera or voice.

[1610] Example: When a user feels stressed, the emotional data is sent to the server via the device.

[1611] 4. Check the recipe and cook

[1612] The user checks the recipe displayed on the terminal and prepares the dish based on it.

[1613] Example: A user makes cookies based on the recipe for "10-Minute Gluten-Free Cookies" displayed on their device.

[1614] 5. Providing Feedback

[1615] Users enter their thoughts and suggestions for improvement about the recipe they have cooked into a form on their device and send the feedback to the server.

[1616] Example: A user provides feedback such as "I would prefer the cookies to be a little softer."

[1617] The processing flow will be explained below.

[1618] Server Processing

[1619] Step 1:

[1620] The server receives the user's preferences, dietary history, and allergy information sent from the terminal.

[1621] Step 2:

[1622] The server stores the received user profile information in a database.

[1623] Step 3:

[1624] The server retrieves the user profile from the database and inputs that information into the generative AI model to learn.

[1625] Step 4:

[1626] The server receives the recipe conditions (required time, type of ingredients, etc.) sent from the terminal.

[1627] Step 5:

[1628] The server uses a generative AI model to generate recipes that fit the user's requirements, taking into account the difficulty of obtaining ingredients and the time required.

[1629] Step 6:

[1630] The server uses an emotion engine to analyze the user's emotion data and reflects it in the recipe it generates.

[1631] Step 7:

[1632] The server sends the generated recipe to the terminal.

[1633] Step 8:

[1634] The server receives the user feedback sent from the terminal.

[1635] Step 9:

[1636] The server stores the received feedback in a database and uses it to retrain the generative AI model to improve its accuracy.

[1637] Terminal handling

[1638] Step 1:

[1639] The terminal provides the user with a form to enter information about preferences, dietary history, and allergies.

[1640] Step 2:

[1641] The profile information entered by the user is sent to the server.

[1642] Step 3:

[1643] The terminal provides the user with a form for inputting the desired recipe conditions (required time, type of ingredients, etc.).

[1644] Step 4:

[1645] A recipe request entered by the user is sent to the server.

[1646] Step 5:

[1647] The device provides an interface for acquiring the user's emotional data, which can be acquired using a facial recognition camera or a voice assistant.

[1648] Step 6:

[1649] The acquired emotion data is transmitted to the server.

[1650] Step 7:

[1651] The terminal receives the original recipe sent from the server and presents it to the user.

[1652] Step 8:

[1653] The terminal provides the user with a form to enter feedback about the recipe.

[1654] Step 9:

[1655] Sends the user-entered feedback to the server.

[1656] User Action

[1657] Step 1:

[1658] Users enter their preferences, dietary history, and allergy information into a form on the terminal.

[1659] Step 2:

[1660] The user sends the entered profile information to the server.

[1661] Step 3:

[1662] The user inputs the desired recipe conditions into a form on the terminal.

[1663] Step 4:

[1664] The user inputs a recipe request and sends it to the server.

[1665] Step 5:

[1666] Users provide their emotional data through the device's interface, and in some cases emotion recognition is performed using a facial recognition camera or voice.

[1667] Step 6:

[1668] The user checks the recipe displayed on the terminal.

[1669] Step 7:

[1670] The user creates a dish based on the displayed recipe.

[1671] Step 8:

[1672] The user enters feedback about the created recipe into a form on the terminal.

[1673] Step 9:

[1674] The user sends the input feedback to the server.

[1675] Example 2

[1676] 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."

[1677] Conventional recipe provision systems have difficulty providing personalized recipes based on a user's individual preferences, specific health information, and even temporary emotional states. They also have difficulty efficiently incorporating user feedback to improve the quality of generated recipes. This poses a challenge in continuously generating recipes that satisfy users.

[1678] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting user preference, dietary history, and allergy information, means for training a generative AI model based on the user's profile, means for preprocessing the collected data, means for generating recipes that meet the user's desired conditions using the trained generative AI model, means for acquiring and recognizing user emotion data, means for adjusting parameters of the generative AI model based on the emotion data, means for providing the generated recipes to the user, and means for collecting user feedback and re-training the generative AI model to improve its accuracy. This makes it possible to provide recipes optimized for the individual needs of the user, thereby increasing user satisfaction and continuously generating high-quality recipes.

[1679] "User preferences" refers to the types of ingredients and dishes that the user prefers, their taste preferences, and so on.

[1680] "Dietary history" is information about meals the user has eaten in the past, including frequency, type, and amount of meals.

[1681] "Allergy information" refers to information about a user's sensitivity to certain foods or ingredients.

[1682] A "generative AI model" refers to an artificial intelligence model that automatically generates recipes based on collected data.

[1683] "User profile" is a collective term for data that compiles information about a user's personal preferences, health information, and dietary information.

[1684] "Preprocessing" refers to the preparation work required to prepare data into a format that is easy for a generative AI model to handle.

[1685] "Recipe conditions" are specific requirements for the dish desired by the user, including the required time and the type of ingredients.

[1686] "Emotional Data" is data that indicates the user's current emotional state and is used by the Emotion Engine to recognize and analyze it.

[1687] "Adjusting the parameters of a generative AI model" refers to making adjustments to optimize the behavior and output of a generative AI model based on inputs such as emotional data and feedback.

[1688] "Feedback" refers to information such as opinions, impressions, and suggestions for improvement regarding a recipe provided by a user.

[1689] "Retraining" refers to additional learning to improve the accuracy of a generative AI model based on collected feedback information.

[1690] This invention is a system that provides individually optimized recipes using a user's preferences, dietary history, allergy information, and emotional data. The system operates primarily in cooperation between a server, a terminal, and the user.

[1691] server

[1692] The server uses hardware and software with the following features:

[1693] 1. Collection and storage of user profile:

[1694] The server receives the user's preferences, dietary history, and allergy information sent from the device and stores it in a database using databases such as MongoDB or MySQL.

[1695] Example: If a user enters "I'm a vegetarian and have a peanut allergy," store that information in a database.

[1696] 2. Training the generative AI model:

[1697] The server preprocesses the collected user data to train a generative AI model (e.g., GPT-3). Preprocessing includes text cleaning and data standardization.

[1698] Example: If a user provides information such as "I like spicy food," the model learns patterns for spicy food.

[1699] 3. Generate the recipe:

[1700] The server uses the trained generative AI model to generate recipes based on the user's desired conditions, taking into account factors such as the required time and the type of ingredients.

[1701] Example: If a user requests a vegetarian meal that can be prepared in under 30 minutes, a recipe that meets those criteria is generated.

[1702] 4. Emotional engine regulation:

[1703] The server uses an emotion engine to analyze the user's emotion data and adjust the parameters of the generative AI model.

[1704] Example: If a user is feeling stressed, the emotion engine will train the model to suggest recipes that include ingredients and cooking methods that have a relaxing effect.

[1705] 5. Recipe provided:

[1706] The server sends the generated recipe to the terminal.

[1707] Example: Generate a recipe for "vegetarian pasta that can be made in under 30 minutes" and send it to your device.

[1708] 6. Collect and use feedback:

[1709] The server collects user feedback and retrains the generative AI model, improving the accuracy of the recipes.

[1710] Example: If a user provides feedback such as "the pasta was bland," that information is included in the training data.

[1711] Terminal

[1712] The terminal interfaces directly with the user and provides the following functions:

[1713] 1. Fill in your user profile:

[1714] The terminal displays a form for the user to enter preferences, dietary history, and allergy information, and sends the entered data to the server.

[1715] Example: A user enters the information "I am a vegetarian" into a terminal and presses the send button.

[1716] 2. Enter your recipe request:

[1717] The terminal provides a form for the user to input desired recipe conditions, and the input information is sent to the server.

[1718] Example: A user enters information about a "vegetarian meal that can be prepared in under 30 minutes" and submits it.

[1719] 3. View recipe:

[1720] The terminal displays the recipe sent from the server to the user.

[1721] Example: Display a recipe for "Vegetarian pasta in under 30 minutes."

[1722] 4. Enter emotion data:

[1723] The device provides an interface to capture the user's emotions and uses a facial recognition camera and voice assistant.

[1724] Example: The device reads the user's emotions through a facial recognition camera and transmits the information to a server.

[1725] 5. Enter your feedback:

[1726] The terminal provides a form for users to enter feedback on the recipes they create.

[1727] Example: A user types "The pasta was bland" and presses the submit button.

[1728] User

[1729] The user uses the system in the following steps:

[1730] 1. Provide your profile information:

[1731] Users enter their preferences, dietary history, and allergy information into a form on the terminal.

[1732] Example: A user enters "I follow a gluten-free diet."

[1733] 2. Specify recipe conditions:

[1734] The user inputs the desired recipe conditions into a form on the terminal.

[1735] Example: A user requests a "gluten-free snack that can be made in under 10 minutes."

[1736] 3. Providing Emotion Data:

[1737] Users provide emotion data through their devices, which may be achieved through facial recognition cameras or voice-based emotion recognition.

[1738] Example: When a user feels stressed, the emotional data is sent to the server via the device.

[1739] 4. Check the recipe and cook:

[1740] The user checks the recipe displayed on the terminal and prepares the dish.

[1741] Example: Make cookies based on the recipe for "10-Minute Gluten-Free Cookies."

[1742] 5. Providing Feedback:

[1743] The user enters their thoughts and suggestions for improvement on the recipe they have cooked into a form on their device and sends it to the server.

[1744] Example: A user types, "I prefer the cookies to be a little softer."

[1745] Prompt Sentence Examples

[1746] "Spicy vegetarian pasta that can be made in 30 minutes"

[1747] "Gluten-free snacks you can make in under 10 minutes"

[1748] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1749] Step 1:

[1750] Enter your user profile

[1751] Subject: Device

[1752] Description: The device displays a form for users to enter their preferences, dietary history, and allergy information. When the user enters information into the form and presses the submit button, the data is sent to the server in JSON or XML format.

[1753] Input: User inputs profile information (preferences, dietary history, allergy information)

[1754] Output: Profile information sent to the server

[1755] Step 2:

[1756] Receiving and storing user profiles

[1757] Subject: Server

[1758] Description: The server receives user profile information sent from the device and stores it in a database, which can be MongoDB or MySQL.

[1759] Input: User profile information sent from the device

[1760] Output: Profile information stored in a database

[1761] What happens: The server receives the HTTP request, the parser parses the data, and then inserts the data into the database.

[1762] Step 3:

[1763] Training a generative AI model

[1764] Subject: Server

[1765] Description: The server retrieves user profile data from a database and trains a generative AI model (e.g., GPT-3) after preprocessing the data, which includes text cleaning and tokenization.

[1766] Input: User profile data stored in the database

[1767] Output: Trained generative AI model

[1768] What it does: Cleans data using data science libraries (e.g., Pandas, NLTK) to build a training dataset, then trains a generative AI model.

[1769] Step 4:

[1770] Acquiring emotion data

[1771] Subject: Device

[1772] Description: The device collects emotional data using a facial recognition camera or voice assistant to obtain the user's emotional data, which is then sent to a server.

[1773] Input: User emotion data (face recognition results, voice analysis results)

[1774] Output: Emotion data sent to the server

[1775] Specific operation: The device activates the camera to capture the user's facial expression, estimates the emotion using a facial recognition algorithm, and sends the data to the server.

[1776] Step 5:

[1777] Entering a Recipe Request

[1778] Subject: Device

[1779] Description: The terminal displays a form for the user to enter the desired recipe conditions (required time, type of ingredients, etc.) When the user enters the conditions and presses the send button, the data is sent to the server.

[1780] Input: User input of recipe conditions

[1781] Output: Recipe conditions sent to the server

[1782] Specific operation: By entering conditions into the form input fields and pressing the submit button, the data is sent to the server as an HTTP request.

[1783] Step 6:

[1784] Recipe Generation

[1785] Subject: Server

[1786] Description: The server generates recipes using a generative AI model based on the user's profile data and recipe conditions. If emotional data is included, the model parameters are adjusted taking that data into account.

[1787] Input: Profile data, emotion data, recipe conditions stored on the server

[1788] Output: The generated recipe

[1789] What it does: Enter a prompt into GPT-3, such as "vegetarian recipe that can be made in under 30 minutes," and retrieve the generated recipe.

[1790] Step 7:

[1791] Recipe provided

[1792] Subject: Server

[1793] Description: The server sends the generated recipe to the terminal. The terminal displays the received recipe to the user.

[1794] Input: Generated recipe

[1795] Output: The recipe displayed on the user's terminal

[1796] Specific operation: The generated recipe is sent to the terminal in the form of an HTTP response, and the terminal receives it and displays it on the screen.

[1797] Step 8:

[1798] Enter your feedback

[1799] Subject: Device

[1800] Description: The terminal provides a form for users to enter feedback on the recipes they have created. When the user enters their feedback and presses the submit button, the data is sent to the server.

[1801] Input: User input of feedback

[1802] Output: Feedback sent to the server

[1803] Specific behavior: By entering feedback into the form input fields and pressing the submit button, the data is sent to the server as an HTTP request.

[1804] Step 9:

[1805] Save and retrain feedback

[1806] Subject: Server

[1807] Description: The server stores the received feedback in a database and retrains the generative AI model based on that feedback.

[1808] Input: User-submitted feedback

[1809] Output: A generative AI model that reflects the learning results

[1810] Specific operation: The new feedback data is stored in the database and added to the existing training dataset for retraining.

[1811] (Application example 2)

[1812] 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."

[1813] Conventional recipe provision systems have limitations in personalization based on user preferences and allergy information, and in particular, they have a problem of insufficient provision of appropriate services based on emotional data. Furthermore, the in-car environment is not optimized to reflect the emotional state of the occupants, so passenger comfort cannot be fully ensured.

[1814] 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.

[1815] In this invention, the server includes means for collecting user preferences, dietary history, and allergy information, means for training a generative AI model based on the user's profile, means for generating recipes that meet the user's desired conditions using the trained generative AI model, means for providing the generated recipes to the user, means for collecting user feedback and improving the accuracy of the generative AI model, means for recognizing and analyzing the user's emotions and adjusting the parameters of the generative AI model based on the results, and means for optimizing the in-car environment based on the emotion data, thereby enabling the provision of personalized recipes according to the user's emotional state and the optimization of the in-car environment.

[1816] "User preferences" refer to the characteristics and types of food and recipes that a user prefers.

[1817] "Dietary history" refers to the history and trends of the meals a user has eaten in the past.

[1818] "Allergy information" refers to information indicating that a user has an allergic reaction to a particular food or ingredient.

[1819] "User profile" refers to all information about an individual, such as the user's preferences, dietary history, and allergy information.

[1820] A "generative AI model" is an artificial intelligence model that generates recipes based on collected user profile information.

[1821] A "recipe" is a set of instructions that specifically outlines cooking steps and a list of ingredients.

[1822] "Feedback" refers to information such as impressions and ratings of a recipe after the user has actually tried it.

[1823] "Emotional data" refers to information related to the user's emotional state, which can be obtained from facial expressions, tone of voice, heart rate, etc.

[1824] "In-vehicle environment" refers to the physical conditions of the space occupied by occupants inside an autonomous vehicle, including lighting, acoustics, temperature, and air quality.

[1825] A "parameter" is a numerical value that determines the behavior and performance of a generative AI model.

[1826] To implement this invention, a system is constructed in which a server, a terminal, and a user cooperate with each other. The server plays the following main roles.

[1827] server

[1828] The server operates as follows to collect user information and provide recipes using generative AI models.

[1829] 1. Collecting and storing user profiles

[1830] The server receives the user's preferences, dietary history, allergy information, and emotional data sent from the device and stores it in a database. For example, if a user enters "I'm a vegetarian and I have a peanut allergy," this information will be stored in the database.

[1831] 2. Training the generative AI model

[1832] The server trains a generative AI model based on the collected user profile. Specifically, for example, for a user who has a preference for spicy food, the model learns patterns of spicy ingredients and recipes.

[1833] 3. Recipe Generation

[1834] The server uses the learned generative AI model to generate recipes that meet the user's desired conditions (time required, type of ingredients, etc.) For example, it generates a recipe based on a user request such as "I want a vegetarian dish that can be made in under 30 minutes."

[1835] 4. Emotional Engine Adjustment

[1836] The server uses an emotion engine to analyze the user's emotional state and adjusts the parameters of the generative AI model based on the results: if the user is feeling stressed, the model is adjusted to suggest dishes that have a relaxing effect.

[1837] 5. Optimizing the in-car environment

[1838] The environment inside the autonomous vehicle (lighting, music, temperature, etc.) is optimized based on emotional data. Specifically, if the passenger wants to relax, relaxing music will be played and the temperature will be set appropriately.

[1839] 6. Collect and use feedback

[1840] The generative AI model is retrained to improve its accuracy using user-provided feedback. For example, if feedback such as "the pasta was bland" is collected, this is reflected in the model.

[1841] Terminal

[1842] The terminal serves the following roles as an interface with the user.

[1843] 1. Enter your user profile

[1844] The terminal provides a form for users to input their preferences, dietary history, and allergy information, which is then sent to the server.

[1845] 2. Enter your recipe request

[1846] The user inputs the desired conditions (time required, type of material, etc.) and sends the request to the server.

[1847] 3. View recipes

[1848] The original recipe sent from the server is displayed and provided to the user.

[1849] 4. Entering Emotion Data

[1850] Using facial recognition cameras and voice assistants, users' emotional data is collected and sent to a server.

[1851] 5. Enter your feedback

[1852] The user inputs feedback about the created recipe and sends it to the server.

[1853] User

[1854] Users can access the system via their device and are provided with individually optimized recipes and in-car environments.

[1855] 1. Providing Profile Information

[1856] The user enters profile information using a form on the terminal and sends it to the server.

[1857] 2. Specify recipe conditions

[1858] Use the terminal to specify recipe conditions (required time, type of ingredients).

[1859] 3. Providing Emotion Data

[1860] Using a facial recognition camera or voice assistant, you can provide your emotional state to the system.

[1861] 4. Check the recipe and cook

[1862] Cook a dish based on the recipe provided and check the results.

[1863] 5. Providing Feedback

[1864] Feedback about the cooked recipe is entered into the terminal and sent to the server.

[1865] Specific examples

[1866] For example, if a user inputs "I'm vegetarian and would like a recipe that can be made in 30 minutes or less," the server will use the trained generative AI model to generate the appropriate recipe and provide it to the user via their device. Also, if the user is feeling stressed, the server will suggest recipes and in-car environments that have a relaxing effect.

[1867] Prompt Sentence Examples

[1868] "The passenger is stressed, so please set the car to relaxing music and an appropriate temperature. The passenger's profile information is that they like classical music and are allergic to pollen."

[1869] These components enable the system to provide personalized recipes that take into account the user's emotional state and optimize the in-car environment.

[1870] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1871] Step 1:

[1872] The user enters their user profile on the device. Using the device, the user enters their preferences, dietary history, allergy information, etc., which the device then sends to the server. Specific input data includes "user's name," "being a vegetarian," "having a peanut allergy," etc. The server stores this input data in a database.

[1873] Step 2:

[1874] Recipe requests are input via the device. The user inputs the desired recipe conditions (e.g., vegetarian food, time required within 30 minutes) through the device interface. This request data is sent from the device to the server. The server uses this data to train the generative AI model and generate the recipe.

[1875] Step 3:

[1876] The generative AI model is trained on the server. The server trains the generative AI model based on the user profile information collected in step 1. Specifically, the model learns preference information such as "I like spicy food" and recognizes patterns of spicy ingredients and recipes. This process obtains the user profile as input and the trained AI model as output.

[1877] Step 4:

[1878] The server generates the recipe. Using the trained generative AI model, it generates a recipe that matches the user's desired conditions entered in step 2. For example, if the user enters "I'm looking for a vegetarian dish that can be prepared in under 30 minutes," the generative AI model creates a recipe that meets those conditions, and the server sends the recipe to the device.

[1879] Step 5:

[1880] Analyzes emotional states and adjusts parameters. The server uses an emotion engine to analyze the user's emotional data sent from the device and adjusts the parameters of the generative AI model based on the results. For example, if the user is feeling stressed, the generative AI model is adjusted to suggest dishes that have a relaxing effect. This process obtains emotional data as input and an adjusted AI model as output.

[1881] Step 6:

[1882] Optimizing the in-car environment. The server optimizes the environment inside the autonomous vehicle based on emotional data. Specifically, when the passenger feels like relaxing, it plays relaxing music and sets the temperature appropriately. This process obtains emotional data as input and optimized in-car environment settings as output.

[1883] Step 7:

[1884] It collects and utilizes feedback. The device provides an interface for inputting and sending feedback from users, who input their thoughts and ratings on the recipes they have cooked. The server collects this feedback and performs re-learning to improve the accuracy of the generative AI model. A specific example of how this works is to retrain the AI ​​model based on feedback such as "the pasta was bland." This process obtains feedback data as input and an improved AI model as output.

[1885] 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.

[1886] 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.

[1887] 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.

[1888] [Fourth embodiment]

[1889] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1890] 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.

[1891] 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).

[1892] 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.

[1893] 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.

[1894] 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).

[1895] 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.

[1896] 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.

[1897] 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.

[1898] 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.

[1899] 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.

[1900] 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.

[1901] 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."

[1902] The present invention relates to a system that collects and analyzes user preferences, dietary history, and allergy information, and provides recipes optimized for each individual user.

[1903] Server embodiment

[1904] The server has the following main functions:

[1905] 1. Collecting and storing user profiles

[1906] The server receives the user's preferences, dietary history, and allergy information sent from the terminal.

[1907] The received information is stored in a database.

[1908] Example: If a user provides information such as "I'm a vegetarian and I have a peanut allergy," the server stores that information in a database.

[1909] 2. Training the generative AI model

[1910] The server trains a generative AI model based on the collected user profiles.

[1911] Example: Based on a user's preference information such as "I like spicy food," the model learns patterns of spicy ingredients and recipes.

[1912] 3. Recipe Generation

[1913] The server uses the learned generative AI model to generate recipes that meet the user's desired conditions (time required, type of ingredients, etc.).

[1914] Example: If a user requests a vegetarian meal that can be prepared in under 30 minutes, the server generates a recipe that reflects that request.

[1915] 4. Providing recipes

[1916] The server sends the generated original recipe to the terminal.

[1917] Example: Send a server-generated recipe for "vegetarian pasta that can be made in under 30 minutes."

[1918] 5. Collect and use feedback

[1919] The server receives feedback from users and uses it to retrain the generative AI model to improve its accuracy.

[1920] Example: If a user provides feedback such as "The vegetarian pasta was bland," that feedback is reflected as training data.

[1921] Terminal embodiment

[1922] The terminal acts as an interface with the user:

[1923] 1. Enter your user profile

[1924] The terminal provides a form for the user to input preferences, dietary history, and allergy information.

[1925] The entered profile information is sent to the server.

[1926] Example: A user enters the information "I am a vegetarian" into a terminal and presses the send button.

[1927] 2. Enter your recipe request

[1928] The terminal provides a form for the user to input desired recipe conditions (required time, type of ingredients, etc.).

[1929] The input request is sent to the server.

[1930] Example: A user enters information about a "vegetarian meal that can be prepared in under 30 minutes" and presses the submit button.

[1931] 3. View recipes

[1932] The terminal receives the original recipe sent from the server and displays it to the user.

[1933] Example: Display a recipe sent from the server for "vegetarian pasta that can be made in under 30 minutes."

[1934] 4. Enter your feedback

[1935] The terminal provides a form for users to enter feedback on the recipes they have created.

[1936] The input feedback information is sent to the server.

[1937] Example: A user enters feedback such as "The pasta was bland" and presses the submit button.

[1938] User's embodiment

[1939] Users use the system to receive recipes tailored to their personal tastes and requirements:

[1940] 1. Providing Profile Information

[1941] The user enters their preferences, dietary history, and allergy information into a form on the terminal.

[1942] Example: A user enters that they "follow a gluten-free diet."

[1943] 2. Specify recipe conditions

[1944] The user inputs the conditions of the desired recipe into a form on the terminal.

[1945] Example: A user requests a "gluten-free snack that can be made in under 10 minutes."

[1946] 3. Check the recipe and cook

[1947] The user checks the recipe displayed on the terminal and prepares the dish based on it.

[1948] Example: A user makes cookies based on the recipe for "10-Minute Gluten-Free Cookies" displayed on their device.

[1949] 4. Providing Feedback

[1950] Users enter their thoughts and suggestions for improvement about the recipe they have cooked into a form on their device and send the feedback to the server.

[1951] Example: A user provides feedback such as "I would prefer the cookies to be a little softer."

[1952] The processing flow will be explained below.

[1953] Server Processing

[1954] Step 1:

[1955] The server receives the user's preferences, dietary history, and allergy information sent from the terminal.

[1956] Step 2:

[1957] The server stores the received user profile information in a database.

[1958] Step 3:

[1959] The server retrieves the user profile from the database and inputs it into the generative AI model for learning.

[1960] Step 4:

[1961] The server receives the recipe conditions (required time, type of ingredients, etc.) sent from the terminal.

[1962] Step 5:

[1963] The server uses a generative AI model to generate recipes that fit the user's requirements, taking into account the difficulty of obtaining ingredients and the time required.

[1964] Step 6:

[1965] The server sends the generated recipe to the terminal.

[1966] Step 7:

[1967] The server receives the user feedback sent from the terminal.

[1968] Step 8:

[1969] The server stores the received feedback in a database and uses it to retrain the generative AI model to improve its accuracy.

[1970] Terminal handling

[1971] Step 1:

[1972] The terminal provides the user with a form to enter information about preferences, dietary history, and allergies.

[1973] Step 2:

[1974] The profile information entered by the user is sent to the server.

[1975] Step 3:

[1976] The terminal provides the user with a form for inputting the desired recipe conditions (required time, type of ingredients, etc.).

[1977] Step 4:

[1978] A recipe request entered by the user is sent to the server.

[1979] Step 5:

[1980] The terminal receives the original recipe sent from the server.

[1981] Step 6:

[1982] The terminal displays the received recipe in an easy-to-understand manner for the user.

[1983] Step 7:

[1984] The terminal provides the user with a form to enter feedback about the recipe.

[1985] Step 8:

[1986] Sends the user-entered feedback to the server.

[1987] User Action

[1988] Step 1:

[1989] Users enter their preferences, dietary history, and allergy information into a form on the terminal.

[1990] Step 2:

[1991] The user sends the entered profile information to the server.

[1992] Step 3:

[1993] The user inputs the desired recipe conditions into a form on the terminal.

[1994] Step 4:

[1995] The user inputs a recipe request and sends it to the server.

[1996] Step 5:

[1997] The user checks the recipe displayed on the terminal.

[1998] Step 6:

[1999] The user creates a dish based on the displayed recipe.

[2000] Step 7:

[2001] The user enters feedback about the created recipe into a form on the terminal.

[2002] Step 8:

[2003] The user sends the input feedback to the server.

[2004] Example 1

[2005] 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."

[2006] Conventional recipe provision systems have difficulty providing optimal recipes based on individual users' preferences, dietary history, and allergy information. Furthermore, they lack a mechanism for collecting user feedback to improve the system's accuracy, making it impossible to respond quickly and accurately to user needs. This has resulted in problems such as users having to spend time and effort searching for recipes that suit them.

[2007] 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.

[2008] In this invention, the server includes means for collecting user preferences, dietary history, and allergy information, means for training a generative AI model based on the user's profile, means for generating recipes that meet the user's desired conditions using the trained generative AI model, means for providing the generated recipes to the user, and means for collecting user feedback and improving the accuracy of the generative AI model. This makes it possible to quickly and accurately respond to the user's individual needs and provide optimal recipes. Furthermore, by generating recipes using prompts, recipes that meet the user's preferences can be quickly generated. Furthermore, by saving the user's profile and feedback, the accuracy of the system can be continuously improved.

[2009] "User preferences" refers to information about the user's favorite foods and cooking methods.

[2010] "Dietary history" refers to historical information about meals the user has taken in the past.

[2011] "Allergy information" refers to data about foods or ingredients to which a user has an allergic reaction.

[2012] A "generative AI model" is an artificial intelligence model that learns data and generates recipes based on the user's preferences and conditions.

[2013] "User profile" refers to personal data such as a user's preferences, dietary history, and allergy information.

[2014] A "recipe" is a list of instructions and ingredients for making a particular dish.

[2015] "Feedback" refers to the user's thoughts and evaluations of the system and recipes.

[2016] A "prompt" is a condition or instruction that is input to a generative AI model to generate a recipe.

[2017] A "database" is a system that organizes and stores collected information so that it can be searched and retrieved when needed.

[2018] A "server" is a computer system that collects, processes, stores, and serves information from users.

[2019] A "terminal" is a device that a user uses to enter information and receive generated recipes.

[2020] This invention relates to a system that collects and analyzes user preferences, dietary history, and allergy information to provide recipes optimized for each user. This system consists of three main elements: a server, a terminal, and a user.

[2021] Server embodiment

[2022] The server has the following features:

[2023] 1. Collecting and storing user profiles

[2024] The server receives the user's preferences, dietary history, and allergy information sent from the device and stores it in a database. For example, if a user provides information that they are "vegetarian and have a peanut allergy," the server stores that information in the database.

[2025] 2. Training the generative AI model

[2026] The server trains a generative AI model based on the collected user profile. For example, based on the user's preference information "I like spicy food," the model learns patterns of spicy ingredients and recipes.

[2027] 3. Recipe Generation

[2028] The server uses the learned generative AI model to generate recipes that meet the user's desired conditions (time required, type of ingredients, etc.). For example, if the user requests a "vegetarian dish that can be made in 30 minutes or less," the server generates a recipe that reflects those conditions. An example of a prompt sentence is "Please generate a recipe for a vegetarian dish that can be made in 30 minutes or less."

[2029] 4. Providing the generated recipe

[2030] The server sends the generated recipe to the device. For example, the server sends the generated recipe for "vegetarian pasta that can be made in 30 minutes or less" to the device.

[2031] 5. Collecting and Using Feedback

[2032] The server receives feedback from users and retrains the generative AI model to improve its accuracy. For example, if a user provides feedback such as "the vegetarian pasta was bland," the server incorporates this feedback into the training data.

[2033] Terminal embodiment

[2034] The terminal acts as an interface with the user:

[2035] 1. Enter your user information

[2036] The terminal provides a form for the user to input information about preferences, dietary history, and allergies, and transmits the input profile information to the server. For example, the user inputs information such as "I am a vegetarian" into the terminal and presses the send button.

[2037] 2. Enter recipe conditions

[2038] The terminal provides a form for the user to input the desired recipe conditions (time required, type of ingredients, etc.) and sends the input request to the server. For example, a user inputs information requesting "vegetarian dishes that can be made in 30 minutes or less" and presses the send button.

[2039] 3. View recipes

[2040] The device receives the original recipe sent from the server and displays it to the user. For example, the device displays a recipe for "vegetarian pasta that can be made in under 30 minutes."

[2041] 4. Enter your feedback

[2042] The terminal provides a form for the user to input feedback on the recipe created by the user, and transmits the input feedback information to the server. For example, the user inputs feedback such as "the pasta was bland" and presses the send button.

[2043] User's embodiment

[2044] To use the optimized recipe, users follow these steps:

[2045] 1. Providing Profile Information

[2046] The user enters their preferences, dietary history, and allergy information into a form on the terminal. For example, the user enters that they follow a gluten-free diet.

[2047] 2. Specify recipe conditions

[2048] The user inputs the desired recipe conditions into a form on the terminal. For example, the user specifies "a gluten-free snack that can be made in 10 minutes or less." An example of a prompt sentence is "Please generate a recipe for a gluten-free snack that can be made in 10 minutes or less."

[2049] 3. Check the recipe and cook

[2050] The user checks the recipe displayed on the device and prepares the dish based on it. For example, the user makes cookies based on the recipe for "10-minute gluten-free cookies" displayed on the device.

[2051] 4. Providing Feedback

[2052] The user inputs their thoughts and suggestions for improvement about the recipe into a form on the device and sends the feedback to the server. For example, the user inputs feedback such as "I wish the cookies were a little softer when baked."

[2053] By implementing this system, users can quickly and accurately receive recipes optimized for their preferences and conditions. In addition, by continuously collecting and incorporating feedback from users, the accuracy of the generative AI model can be improved, enabling the provision of better services.

[2054] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2055] Step 1:

[2056] Entering User Profile Information

[2057] The terminal displays a form for the user to enter preferences, dietary history, and allergy information.

[2058] The user enters information into the form displayed on the terminal and presses the "Submit" button.

[2059] Input: User preferences, dietary history, and allergy information (e.g., "I'm vegetarian and have a peanut allergy").

[2060] Output: The entered information is sent from the terminal to the server.

[2061] Specific operation: When the user clicks the "Submit" button, the input information is sent from the terminal to the server.

[2062] Step 2:

[2063] Submitting and storing profile information

[2064] The terminal transmits the information entered by the user to the server.

[2065] The server stores the received information in a database.

[2066] Input: User profile information (e.g., "I'm a vegetarian and have a peanut allergy").

[2067] Output: The information is stored in a database.

[2068] Specific operation: The server analyzes the received data and stores it in a database.

[2069] Step 3:

[2070] Training a generative AI model

[2071] The server trains the generative AI model based on user information stored in a database.

[2072] Input: User information stored in a database (e.g., "I like spicy food").

[2073] Output: A trained generative AI model.

[2074] How it works: The server inputs the stored data into the AI ​​model, allowing it to learn patterns.

[2075] Step 4:

[2076] Entering recipe conditions

[2077] The terminal provides a form for the user to input desired recipe conditions (required time, type of ingredients, etc.).

[2078] The user inputs the desired conditions and presses the "Submit" button.

[2079] Input: User recipe criteria (e.g., "vegetarian meals that can be made in under 30 minutes").

[2080] Output: The entered conditions are sent from the terminal to the server.

[2081] Specific operation: When the user clicks the "Send" button, the desired conditions are sent from the terminal to the server.

[2082] Step 5:

[2083] Sending and generating recipe conditions

[2084] The terminal transmits the input conditions to the server.

[2085] The server generates a recipe using a generative AI model based on the received conditions.

[2086] Input: User recipe criteria (e.g., "vegetarian meals that can be made in under 30 minutes").

[2087] Output: The generated recipe (e.g. "Vegetarian pasta in under 30 minutes").

[2088] Specific operation: The server provides the conditions as prompts to the generative AI model, which then generates the optimal recipe. An example of the prompt is, "Generate a vegetarian recipe that can be made in under 30 minutes."

[2089] Step 6:

[2090] Providing the generated recipe

[2091] The server transmits the generated recipe to the terminal.

[2092] The terminal displays the received recipe to the user.

[2093] Input: The generated recipe (e.g., "Vegetarian pasta in under 30 minutes").

[2094] Output: The recipe is printed to the terminal.

[2095] Specific behavior: The server sends the recipe to the device, and the device displays it to the user.

[2096] Step 7:

[2097] Enter your feedback

[2098] The terminal provides a form for users to enter feedback on the recipes they have created.

[2099] The user enters the feedback and presses the "Submit" button.

[2100] Input: User feedback (e.g., "The pasta was bland").

[2101] Output: The input feedback information is sent from the device to the server.

[2102] Specific operation: When the user clicks the "Submit" button, the feedback information is sent from the terminal to the server.

[2103] Step 8:

[2104] Send and save feedback

[2105] The terminal transmits the input feedback to the server.

[2106] The server stores the received feedback in a database.

[2107] Input: User feedback information (e.g., "The pasta was bland").

[2108] Output: The feedback information is stored in a database.

[2109] Specific behavior: The server analyzes the received feedback and stores it in a database.

[2110] Step 9:

[2111] Reflecting feedback

[2112] The server retrains the generative AI model based on the collected feedback, improving the model's accuracy.

[2113] Input: Feedback information stored in a database (e.g., "The pasta was bland").

[2114] Output: A generative AI model with improved accuracy.

[2115] Specific operation: The server inputs the feedback data into the AI ​​model and retrains the model.

[2116] (Application example 1)

[2117] 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."

[2118] Conventional food delivery systems have difficulty suggesting optimal dishes based on a user's individual preferences, allergies, and dietary history. Even if a system existed that provided recipes that matched a user's desired conditions, it was not possible to link the system directly from ordering to delivery. This made it difficult for users to easily enjoy dishes that suited their dietary habits. Furthermore, the system lacked sufficient functionality to reflect user feedback and improve the accuracy of recipes.

[2119] 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.

[2120] In this invention, the server includes a means for collecting user preferences, dietary history, and allergy information, a means for training a generative AI model based on the user's profile, and a means for generating recipes that meet the user's desired conditions using the trained generative AI model. This allows the user to receive individually optimized recipe suggestions. The server also includes a means for providing the generated recipes to the user and a means for collecting feedback from the user to improve the accuracy of the generative AI model. Furthermore, the server includes a means for suggesting individually optimized dishes based on the user's profile and a means for directly ordering the suggested dishes and delivering them to a specified address, allowing the user to easily order and quickly receive dishes that suit their diet. This system allows users to easily enjoy dishes tailored to their preferences and constraints, and further improves accuracy based on feedback.

[2121] "User preferences" refers to information about the dishes and ingredients that the user likes to eat.

[2122] "Dietary history" is a record of the foods and meals a user has eaten in the past.

[2123] "Allergy information" is information about foods and ingredients that cause allergic reactions to the user.

[2124] A "generative AI model" is a model that learns and is generated using artificial intelligence, and suggests optimal recipes based on the user's individual information.

[2125] "Profile" is a general term for personal information such as a user's preferences, dietary history, and allergy information.

[2126] A "recipe" is a guideline that shows the steps and ingredients for making a dish.

[2127] "Feedback" refers to the user's evaluation of the food they have provided and their suggestions for improvement.

[2128] "Delivery" is the process of delivering the food ordered by the user to the address specified.

[2129] A "means" is a method or device for achieving a specific function or purpose.

[2130] The system of this invention is realized through collaboration between a server and a terminal, and provides optimized meals based on the user's preferences, dietary history, and allergy information, and then handles the entire process from directly ordering the meals to delivery.

[2131] The server has the following main functions:

[2132] 1. Collecting user preferences, dietary history, and allergy information

[2133] The server receives the user's preferences, dietary history, and allergy information sent from the device and stores it in a database. For example, if a user provides information such as "I'm a vegetarian and have a peanut allergy," the server stores that information in the database.

[2134] 2. Training the generative AI model

[2135] The server trains a generative AI model based on the collected user profile information, allowing it to suggest dishes optimized for the user's preferences and conditions. For example, if a user has a preference for spicy food, the server can train the model to recommend spicy recipes.

[2136] 3. Recipe Generation

[2137] The server uses the trained generative AI model to generate recipes that meet the user's criteria. For example, for a request for "vegetarian dishes that can be made in under 30 minutes," it generates a recipe for vegetarian pasta.

[2138] 4. Providing recipes and taking orders

[2139] The generated recipe is sent from the server to the terminal, where the user can check it and order it directly. For example, a user can view the suggested vegetarian pasta recipe and order it if they like it.

[2140] 5. Collecting user feedback and improving model accuracy

[2141] When users send feedback about the food they've been served, the server collects it and uses it to retrain the generative AI model. For example, feedback like "the pasta was bland" can be reflected in the next recommendation.

[2142] The terminal has the following main functions:

[2143] 1. Enter your user profile

[2144] The device has a form where users can enter their preferences, allergy information, and dietary history, for example, "I'm a vegetarian and have a peanut allergy."

[2145] 2. Enter your recipe request

[2146] It provides a form where users can input their desired cooking criteria and send it to the server. For example, they can input criteria such as "vegetarian dishes that can be prepared in 30 minutes or less."

[2147] 3. View recipes and order

[2148] The recipe sent from the server is displayed on the device, and the user can check the recipe. Also, by pressing the order button, the user can directly order the dish. For example, a recipe for vegetarian pasta can be displayed and the user can order it.

[2149] 4. Enter your feedback

[2150] It has a form where users can enter their feedback about the food and send it to the server. For example, they can enter feedback such as "The pasta was bland."

[2151] As a concrete example, if a vegetarian user requests a dish that can be prepared in under 30 minutes, the server generates a recipe based on that condition and sends it to the device. The user then orders a dish based on the generated recipe and it is delivered. Feedback on the dish can then be sent from the device to improve the accuracy of the next suggestion.

[2152] Example prompt for a generative AI model:

[2153] Suggest the best recipes based on your user profile below.

[2154] Food preference: Vegetarian

[2155] Allergy Information: Peanuts

[2156] Time required: 30 minutes or less

[2157] Generate the best vegetarian, peanut-free recipe that can be made in under 30 minutes and meets the following criteria:

[2158] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2159] Step 1:

[2160] The user inputs and sends profile information (preferences, dietary history, allergy information) into the device. Input data: Information such as "I'm a vegetarian and have a peanut allergy." The input data is sent from the device to the server.

[2161] Step 2:

[2162] The server receives the user's profile information sent from the device and stores it in a database, which includes information on preferences, dietary history, and allergies.

[2163] Step 3:

[2164] The server trains the generative AI model based on the collected user profile information. Input data: User preferences, past dietary data, and allergy information. The generative AI model uses this data to learn how to suggest recipes.

[2165] Step 4:

[2166] The user inputs specific recipe requirements (time required, type of ingredients, etc.) from the terminal and sends them to the server. Input data: For example, desired requirements for a vegetarian dish that can be made in 30 minutes or less.

[2167] Step 5:

[2168] The server uses the trained generative AI model to generate recipes that best fit the user's desired conditions. Input data: the trained model and the user's request conditions. Output data: a vegetarian pasta recipe that can be made in under 30 minutes, for example.

[2169] Step 6:

[2170] The server sends the generated recipe to the terminal, which displays it to the user. Input data: Data on the generated recipe. Output data: Recipe display on the user's terminal screen.

[2171] Step 7:

[2172] The user checks the provided recipe and places an order. Input data: User's confirmation and order intention. The terminal sends the order information to the server.

[2173] Step 8:

[2174] The server accepts the user's order and arranges delivery to the specified address. Input data: User's order information and delivery address. Output data: Order processing and start of delivery procedure.

[2175] Step 9:

[2176] The user inputs feedback about the dish from the terminal and sends it to the server. Input data: Contents of the feedback (for example, "The pasta was bland").

[2177] Step 10:

[2178] The server receives feedback from users and uses it to retrain the generative AI model. Input data: Feedback information. Output data: Improved generative AI model.

[2179] 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.

[2180] This invention relates to a system that provides recipes optimized for individual users based on their preferences, dietary history, allergy information, and emotions. This system combines a generative AI model and an emotion engine to provide more personalized recipes.

[2181] Server embodiment

[2182] The server has the following main functions:

[2183] 1. Collecting and storing user profiles

[2184] The server receives the user's preferences, dietary history, and allergy information sent from the terminal.

[2185] The received information is stored in a database.

[2186] Example: If a user provides information such as "I'm a vegetarian and I have a peanut allergy," the server stores that information in a database.

[2187] 2. Training the generative AI model

[2188] The server trains a generative AI model based on the collected user profiles.

[2189] Example: Based on a user's preference information such as "I like spicy food," the model learns patterns of spicy ingredients and recipes.

[2190] 3. Recipe Generation

[2191] The server uses the learned generative AI model to generate recipes that meet the user's desired conditions (time required, type of ingredients, etc.).

[2192] Example: If a user requests a vegetarian meal that can be prepared in under 30 minutes, the server generates a recipe that reflects that request.

[2193] 4. Emotional Engine Adjustment

[2194] The server uses an emotion engine to recognize and analyze the user's emotions and adjusts the parameters of the generative AI model based on the results.

[2195] Example: If a user is feeling stressed, the emotion engine will adjust the generative AI model to suggest recipes that include ingredients and cooking methods that have a relaxing effect.

[2196] 5. Providing recipes

[2197] The server sends the generated original recipe to the terminal.

[2198] Example: Send a server-generated recipe for "vegetarian pasta that can be made in under 30 minutes."

[2199] 6. Collect and use feedback

[2200] The server receives feedback from users and uses it to retrain the generative AI model to improve its accuracy.

[2201] Example: If a user provides feedback such as "The vegetarian pasta was bland," that feedback is reflected as training data.

[2202] Terminal embodiment

[2203] The terminal acts as an interface with the user:

[2204] 1. Enter your user profile

[2205] The terminal provides a form for the user to input preferences, dietary history, and allergy information.

[2206] The entered profile information is sent to the server.

[2207] Example: A user enters the information "I am a vegetarian" into a terminal and presses the send button.

[2208] 2. Enter your recipe request

[2209] The terminal provides a form for the user to input desired recipe conditions (required time, type of ingredients, etc.).

[2210] The input request is sent to the server.

[2211] Example: A user enters information about a "vegetarian meal that can be prepared in under 30 minutes" and presses the submit button.

[2212] 3. View recipes

[2213] The terminal receives the original recipe sent from the server and displays it to the user.

[2214] Example: Display a recipe sent from the server for "vegetarian pasta that can be made in under 30 minutes."

[2215] 4. Entering Emotion Data

[2216] The device provides an interface for inputting and acquiring user emotions, which can be read using a facial recognition camera or voice assistant.

[2217] Example: The device reads the user's emotions through a facial recognition camera and transmits them to a server.

[2218] 5. Enter your feedback

[2219] The terminal provides a form for users to enter feedback on the recipes they have created.

[2220] The input feedback information is sent to the server.

[2221] Example: A user enters feedback such as "The pasta was bland" and presses the submit button.

[2222] User's embodiment

[2223] Users use the system to receive recipes tailored to their personal tastes and requirements:

[2224] 1. Providing Profile Information

[2225] The user enters their preferences, dietary history, and allergy information into a form on the terminal.

[2226] Example: A user enters that they "follow a gluten-free diet."

[2227] 2. Specify recipe conditions

[2228] The user inputs the desired recipe conditions into a form on the terminal.

[2229] Example: A user requests a "gluten-free snack that can be made in under 10 minutes."

[2230] 3. Providing Emotion Data

[2231] Users provide their emotional data through the device's interface, and in some cases emotion recognition is performed using a facial recognition camera or voice.

[2232] Example: When a user feels stressed, the emotional data is sent to the server via the device.

[2233] 4. Check the recipe and cook

[2234] The user checks the recipe displayed on the terminal and prepares the dish based on it.

[2235] Example: A user makes cookies based on the recipe for "10-Minute Gluten-Free Cookies" displayed on their device.

[2236] 5. Providing Feedback

[2237] Users enter their thoughts and suggestions for improvement about the recipe they have cooked into a form on their device and send the feedback to the server.

[2238] Example: A user provides feedback such as "I would prefer the cookies to be a little softer."

[2239] The processing flow will be explained below.

[2240] Server Processing

[2241] Step 1:

[2242] The server receives the user's preferences, dietary history, and allergy information sent from the terminal.

[2243] Step 2:

[2244] The server stores the received user profile information in a database.

[2245] Step 3:

[2246] The server retrieves the user profile from the database and inputs that information into the generative AI model to learn.

[2247] Step 4:

[2248] The server receives the recipe conditions (required time, type of ingredients, etc.) sent from the terminal.

[2249] Step 5:

[2250] The server uses a generative AI model to generate recipes that fit the user's requirements, taking into account the difficulty of obtaining ingredients and the time required.

[2251] Step 6:

[2252] The server uses an emotion engine to analyze the user's emotion data and reflects it in the recipe it generates.

[2253] Step 7:

[2254] The server sends the generated recipe to the terminal.

[2255] Step 8:

[2256] The server receives the user feedback sent from the terminal.

[2257] Step 9:

[2258] The server stores the received feedback in a database and uses it to retrain the generative AI model to improve its accuracy.

[2259] Terminal handling

[2260] Step 1:

[2261] The terminal provides the user with a form to enter information about preferences, dietary history, and allergies.

[2262] Step 2:

[2263] The profile information entered by the user is sent to the server.

[2264] Step 3:

[2265] The terminal provides the user with a form for inputting the desired recipe conditions (required time, type of ingredients, etc.).

[2266] Step 4:

[2267] A recipe request entered by the user is sent to the server.

[2268] Step 5:

[2269] The device provides an interface for acquiring the user's emotional data, which can be acquired using a facial recognition camera or a voice assistant.

[2270] Step 6:

[2271] The acquired emotion data is transmitted to the server.

[2272] Step 7:

[2273] The terminal receives the original recipe sent from the server and presents it to the user.

[2274] Step 8:

[2275] The terminal provides the user with a form to enter feedback about the recipe.

[2276] Step 9:

[2277] Sends the user-entered feedback to the server.

[2278] User Action

[2279] Step 1:

[2280] Users enter their preferences, dietary history, and allergy information into a form on the terminal.

[2281] Step 2:

[2282] The user sends the entered profile information to the server.

[2283] Step 3:

[2284] The user inputs the desired recipe conditions into a form on the terminal.

[2285] Step 4:

[2286] The user inputs a recipe request and sends it to the server.

[2287] Step 5:

[2288] Users provide their emotional data through the device's interface, and in some cases emotion recognition is performed using a facial recognition camera or voice.

[2289] Step 6:

[2290] The user checks the recipe displayed on the terminal.

[2291] Step 7:

[2292] The user creates a dish based on the displayed recipe.

[2293] Step 8:

[2294] The user enters feedback about the created recipe into a form on the terminal.

[2295] Step 9:

[2296] The user sends the input feedback to the server.

[2297] Example 2

[2298] 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."

[2299] Conventional recipe provision systems have difficulty providing personalized recipes based on a user's individual preferences, specific health information, and even temporary emotional states. They also have difficulty efficiently incorporating user feedback to improve the quality of generated recipes. This poses a challenge in continuously generating recipes that satisfy users.

[2300] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting user preference, dietary history, and allergy information, means for training a generative AI model based on the user's profile, means for preprocessing the collected data, means for generating recipes that meet the user's desired conditions using the trained generative AI model, means for acquiring and recognizing user emotion data, means for adjusting parameters of the generative AI model based on the emotion data, means for providing the generated recipes to the user, and means for collecting user feedback and re-training the generative AI model to improve its accuracy. This makes it possible to provide recipes optimized for the individual needs of the user, thereby increasing user satisfaction and continuously generating high-quality recipes.

[2301] "User preferences" refers to the types of ingredients and dishes that the user prefers, their taste preferences, and so on.

[2302] "Dietary history" is information about meals the user has eaten in the past, including frequency, type, and amount of meals.

[2303] "Allergy information" refers to information about a user's sensitivity to certain foods or ingredients.

[2304] A "generative AI model" refers to an artificial intelligence model that automatically generates recipes based on collected data.

[2305] "User profile" is a collective term for data that compiles information about a user's personal preferences, health information, and dietary information.

[2306] "Preprocessing" refers to the preparation work required to prepare data into a format that is easy for a generative AI model to handle.

[2307] "Recipe conditions" are specific requirements for the dish desired by the user, including the required time and the type of ingredients.

[2308] "Emotional Data" is data that indicates the user's current emotional state and is used by the Emotion Engine to recognize and analyze it.

[2309] "Adjusting the parameters of a generative AI model" refers to making adjustments to optimize the behavior and output of a generative AI model based on inputs such as emotional data and feedback.

[2310] "Feedback" refers to information such as opinions, impressions, and suggestions for improvement regarding a recipe provided by a user.

[2311] "Retraining" refers to additional learning to improve the accuracy of a generative AI model based on collected feedback information.

[2312] This invention is a system that provides individually optimized recipes using a user's preferences, dietary history, allergy information, and emotional data. The system operates primarily in cooperation between a server, a terminal, and the user.

[2313] server

[2314] The server uses hardware and software with the following features:

[2315] 1. Collection and storage of user profile:

[2316] The server receives the user's preferences, dietary history, and allergy information sent from the device and stores it in a database using databases such as MongoDB or MySQL.

[2317] Example: If a user enters "I'm a vegetarian and have a peanut allergy," store that information in a database.

[2318] 2. Training the generative AI model:

[2319] The server preprocesses the collected user data to train a generative AI model (e.g., GPT-3). Preprocessing includes text cleaning and data standardization.

[2320] Example: If a user provides information such as "I like spicy food," the model learns patterns for spicy food.

[2321] 3. Generate the recipe:

[2322] The server uses the trained generative AI model to generate recipes based on the user's desired conditions, taking into account factors such as the required time and the type of ingredients.

[2323] Example: If a user requests a vegetarian meal that can be prepared in under 30 minutes, a recipe that meets those criteria is generated.

[2324] 4. Emotional engine regulation:

[2325] The server uses an emotion engine to analyze the user's emotion data and adjust the parameters of the generative AI model.

[2326] Example: If a user is feeling stressed, the emotion engine will train the model to suggest recipes that include ingredients and cooking methods that have a relaxing effect.

[2327] 5. Recipe provided:

[2328] The server sends the generated recipe to the terminal.

[2329] Example: Generate a recipe for "vegetarian pasta that can be made in under 30 minutes" and send it to your device.

[2330] 6. Collect and use feedback:

[2331] The server collects user feedback and retrains the generative AI model, improving the accuracy of the recipes.

[2332] Example: If a user provides feedback such as "the pasta was bland," that information is included in the training data.

[2333] Terminal

[2334] The terminal interfaces directly with the user and provides the following functions:

[2335] 1. Fill in your user profile:

[2336] The terminal displays a form for the user to enter preferences, dietary history, and allergy information, and sends the entered data to the server.

[2337] Example: A user enters the information "I am a vegetarian" into a terminal and presses the send button.

[2338] 2. Enter your recipe request:

[2339] The terminal provides a form for the user to input desired recipe conditions, and the input information is sent to the server.

[2340] Example: A user enters information about a "vegetarian meal that can be prepared in under 30 minutes" and submits it.

[2341] 3. View recipe:

[2342] The terminal displays the recipe sent from the server to the user.

[2343] Example: Display a recipe for "Vegetarian pasta in under 30 minutes."

[2344] 4. Enter emotion data:

[2345] The device provides an interface to capture the user's emotions and uses a facial recognition camera and voice assistant.

[2346] Example: The device reads the user's emotions through a facial recognition camera and transmits the information to a server.

[2347] 5. Enter your feedback:

[2348] The terminal provides a form for users to enter feedback on the recipes they create.

[2349] Example: A user types "The pasta was bland" and presses the submit button.

[2350] User

[2351] The user uses the system in the following steps:

[2352] 1. Provide your profile information:

[2353] Users enter their preferences, dietary history, and allergy information into a form on the terminal.

[2354] Example: A user enters "I follow a gluten-free diet."

[2355] 2. Specify recipe conditions:

[2356] The user inputs the desired recipe conditions into a form on the terminal.

[2357] Example: A user requests a "gluten-free snack that can be made in under 10 minutes."

[2358] 3. Providing Emotion Data:

[2359] Users provide emotion data through their devices, which may be achieved through facial recognition cameras or voice-based emotion recognition.

[2360] Example: When a user feels stressed, the emotional data is sent to the server via the device.

[2361] 4. Check the recipe and cook:

[2362] The user checks the recipe displayed on the terminal and prepares the dish.

[2363] Example: Make cookies based on the recipe for "10-Minute Gluten-Free Cookies."

[2364] 5. Providing Feedback:

[2365] The user enters their thoughts and suggestions for improvement on the recipe they have cooked into a form on their device and sends it to the server.

[2366] Example: A user types, "I prefer the cookies to be a little softer."

[2367] Prompt Sentence Examples

[2368] "Spicy vegetarian pasta that can be made in 30 minutes"

[2369] "Gluten-free snacks you can make in under 10 minutes"

[2370] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2371] Step 1:

[2372] Enter your user profile

[2373] Subject: Device

[2374] Description: The device displays a form for users to enter their preferences, dietary history, and allergy information. When the user enters information into the form and presses the submit button, the data is sent to the server in JSON or XML format.

[2375] Input: User inputs profile information (preferences, dietary history, allergy information)

[2376] Output: Profile information sent to the server

[2377] Step 2:

[2378] Receiving and storing user profiles

[2379] Subject: Server

[2380] Description: The server receives user profile information sent from the device and stores it in a database, which can be MongoDB or MySQL.

[2381] Input: User profile information sent from the device

[2382] Output: Profile information stored in a database

[2383] What happens: The server receives the HTTP request, the parser parses the data, and then inserts the data into the database.

[2384] Step 3:

[2385] Training a generative AI model

[2386] Subject: Server

[2387] Description: The server retrieves user profile data from a database and trains a generative AI model (e.g., GPT-3) after preprocessing the data, which includes text cleaning and tokenization.

[2388] Input: User profile data stored in the database

[2389] Output: Trained generative AI model

[2390] What it does: Cleans data using data science libraries (e.g., Pandas, NLTK) to build a training dataset, then trains a generative AI model.

[2391] Step 4:

[2392] Acquiring emotion data

[2393] Subject: Device

[2394] Description: The device collects emotional data using a facial recognition camera or voice assistant to obtain the user's emotional data, which is then sent to a server.

[2395] Input: User emotion data (face recognition results, voice analysis results)

[2396] Output: Emotion data sent to the server

[2397] Specific operation: The device activates the camera to capture the user's facial expression, estimates the emotion using a facial recognition algorithm, and sends the data to the server.

[2398] Step 5:

[2399] Entering a Recipe Request

[2400] Subject: Device

[2401] Description: The terminal displays a form for the user to enter the desired recipe conditions (required time, type of ingredients, etc.) When the user enters the conditions and presses the send button, the data is sent to the server.

[2402] Input: User input of recipe conditions

[2403] Output: Recipe conditions sent to the server

[2404] Specific operation: By entering conditions into the form input fields and pressing the submit button, the data is sent to the server as an HTTP request.

[2405] Step 6:

[2406] Recipe Generation

[2407] Subject: Server

[2408] Description: The server generates recipes using a generative AI model based on the user's profile data and recipe conditions. If emotional data is included, the model parameters are adjusted taking that data into account.

[2409] Input: Profile data, emotion data, recipe conditions stored on the server

[2410] Output: The generated recipe

[2411] What it does: Enter a prompt into GPT-3, such as "vegetarian recipe that can be made in under 30 minutes," and retrieve the generated recipe.

[2412] Step 7:

[2413] Recipe provided

[2414] Subject: Server

[2415] Description: The server sends the generated recipe to the terminal. The terminal displays the received recipe to the user.

[2416] Input: Generated recipe

[2417] Output: The recipe displayed on the user's terminal

[2418] Specific operation: The generated recipe is sent to the terminal in the form of an HTTP response, and the terminal receives it and displays it on the screen.

[2419] Step 8:

[2420] Enter your feedback

[2421] Subject: Device

[2422] Description: The terminal provides a form for users to enter feedback on the recipes they have created. When the user enters their feedback and presses the submit button, the data is sent to the server.

[2423] Input: User input of feedback

[2424] Output: Feedback sent to the server

[2425] Specific behavior: By entering feedback into the form input fields and pressing the submit button, the data is sent to the server as an HTTP request.

[2426] Step 9:

[2427] Save and retrain feedback

[2428] Subject: Server

[2429] Description: The server stores the received feedback in a database and retrains the generative AI model based on that feedback.

[2430] Input: User-submitted feedback

[2431] Output: A generative AI model that reflects the learning results

[2432] Specific operation: The new feedback data is stored in the database and added to the existing training dataset for retraining.

[2433] (Application example 2)

[2434] 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."

[2435] Conventional recipe provision systems have limitations in personalization based on user preferences and allergy information, and in particular, they have a problem of insufficient provision of appropriate services based on emotional data. Furthermore, the in-car environment is not optimized to reflect the emotional state of the occupants, so passenger comfort cannot be fully ensured.

[2436] 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.

[2437] In this invention, the server includes means for collecting user preferences, dietary history, and allergy information, means for training a generative AI model based on the user's profile, means for generating recipes that meet the user's desired conditions using the trained generative AI model, means for providing the generated recipes to the user, means for collecting user feedback and improving the accuracy of the generative AI model, means for recognizing and analyzing the user's emotions and adjusting the parameters of the generative AI model based on the results, and means for optimizing the in-car environment based on the emotion data, thereby enabling the provision of personalized recipes according to the user's emotional state and the optimization of the in-car environment.

[2438] "User preferences" refer to the characteristics and types of food and recipes that a user prefers.

[2439] "Dietary history" refers to the history and trends of the meals a user has eaten in the past.

[2440] "Allergy information" refers to information indicating that a user has an allergic reaction to a particular food or ingredient.

[2441] "User profile" refers to all information about an individual, such as the user's preferences, dietary history, and allergy information.

[2442] A "generative AI model" is an artificial intelligence model that generates recipes based on collected user profile information.

[2443] A "recipe" is a set of instructions that specifically outlines cooking steps and a list of ingredients.

[2444] "Feedback" refers to information such as impressions and ratings of a recipe after the user has actually tried it.

[2445] "Emotional data" refers to information related to the user's emotional state, which can be obtained from facial expressions, tone of voice, heart rate, etc.

[2446] "In-vehicle environment" refers to the physical conditions of the space occupied by occupants inside an autonomous vehicle, including lighting, acoustics, temperature, and air quality.

[2447] A "parameter" is a numerical value that determines the behavior and performance of a generative AI model.

[2448] To implement this invention, a system is constructed in which a server, a terminal, and a user cooperate with each other. The server plays the following main roles.

[2449] server

[2450] The server operates as follows to collect user information and provide recipes using generative AI models.

[2451] 1. Collecting and storing user profiles

[2452] The server receives the user's preferences, dietary history, allergy information, and emotional data sent from the device and stores it in a database. For example, if a user enters "I'm a vegetarian and I have a peanut allergy," this information will be stored in the database.

[2453] 2. Training the generative AI model

[2454] The server trains a generative AI model based on the collected user profile. Specifically, for example, for a user who has a preference for spicy food, the model learns patterns of spicy ingredients and recipes.

[2455] 3. Recipe Generation

[2456] The server uses the learned generative AI model to generate recipes that meet the user's desired conditions (time required, type of ingredients, etc.) For example, it generates a recipe based on a user request such as "I want a vegetarian dish that can be made in under 30 minutes."

[2457] 4. Emotional Engine Adjustment

[2458] The server uses an emotion engine to analyze the user's emotional state and adjusts the parameters of the generative AI model based on the results: if the user is feeling stressed, the model is adjusted to suggest dishes that have a relaxing effect.

[2459] 5. Optimizing the in-car environment

[2460] The environment inside the autonomous vehicle (lighting, music, temperature, etc.) is optimized based on emotional data. Specifically, if the passenger wants to relax, relaxing music will be played and the temperature will be set appropriately.

[2461] 6. Collect and use feedback

[2462] The generative AI model is retrained to improve its accuracy using user-provided feedback. For example, if feedback such as "the pasta was bland" is collected, this is reflected in the model.

[2463] Terminal

[2464] The terminal serves the following roles as an interface with the user.

[2465] 1. Enter your user profile

[2466] The terminal provides a form for users to input their preferences, dietary history, and allergy information, which is then sent to the server.

[2467] 2. Enter your recipe request

[2468] The user inputs the desired conditions (time required, type of material, etc.) and sends the request to the server.

[2469] 3. View recipes

[2470] The original recipe sent from the server is displayed and provided to the user.

[2471] 4. Entering Emotion Data

[2472] Using facial recognition cameras and voice assistants, users' emotional data is collected and sent to a server.

[2473] 5. Enter your feedback

[2474] The user inputs feedback about the created recipe and sends it to the server.

[2475] User

[2476] Users can access the system via their device and are provided with individually optimized recipes and in-car environments.

[2477] 1. Providing Profile Information

[2478] The user enters profile information using a form on the terminal and sends it to the server.

[2479] 2. Specify recipe conditions

[2480] Use the terminal to specify recipe conditions (required time, type of ingredients).

[2481] 3. Providing Emotion Data

[2482] Using a facial recognition camera or voice assistant, you can provide your emotional state to the system.

[2483] 4. Check the recipe and cook

[2484] Cook a dish based on the recipe provided and check the results.

[2485] 5. Providing Feedback

[2486] Feedback about the cooked recipe is entered into the terminal and sent to the server.

[2487] Specific examples

[2488] For example, if a user inputs "I'm vegetarian and would like a recipe that can be made in 30 minutes or less," the server will use the trained generative AI model to generate the appropriate recipe and provide it to the user via their device. Also, if the user is feeling stressed, the server will suggest recipes and in-car environments that have a relaxing effect.

[2489] Prompt Sentence Examples

[2490] "The passenger is stressed, so please set the car to relaxing music and an appropriate temperature. The passenger's profile information is that they like classical music and are allergic to pollen."

[2491] These components enable the system to provide personalized recipes that take into account the user's emotional state and optimize the in-car environment.

[2492] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2493] Step 1:

[2494] The user enters their user profile on the device. Using the device, the user enters their preferences, dietary history, allergy information, etc., which the device then sends to the server. Specific input data includes "user's name," "being a vegetarian," "having a peanut allergy," etc. The server stores this input data in a database.

[2495] Step 2:

[2496] Recipe requests are input via the device. The user inputs the desired recipe conditions (e.g., vegetarian food, time required within 30 minutes) through the device interface. This request data is sent from the device to the server. The server uses this data to train the generative AI model and generate the recipe.

[2497] Step 3:

[2498] The generative AI model is trained on the server. The server trains the generative AI model based on the user profile information collected in step 1. Specifically, the model learns preference information such as "I like spicy food" and recognizes patterns of spicy ingredients and recipes. This process obtains the user profile as input and the trained AI model as output.

[2499] Step 4:

[2500] The server generates the recipe. Using the trained generative AI model, it generates a recipe that matches the user's desired conditions entered in step 2. For example, if the user enters "I'm looking for a vegetarian dish that can be prepared in under 30 minutes," the generative AI model creates a recipe that meets those conditions, and the server sends the recipe to the device.

[2501] Step 5:

[2502] Analyzes emotional states and adjusts parameters. The server uses an emotion engine to analyze the user's emotional data sent from the device and adjusts the parameters of the generative AI model based on the results. For example, if the user is feeling stressed, the generative AI model is adjusted to suggest dishes that have a relaxing effect. This process obtains emotional data as input and an adjusted AI model as output.

[2503] Step 6:

[2504] Optimizing the in-car environment. The server optimizes the environment inside the autonomous vehicle based on emotional data. Specifically, when the passenger feels like relaxing, it plays relaxing music and sets the temperature appropriately. This process obtains emotional data as input and optimized in-car environment settings as output.

[2505] Step 7:

[2506] It collects and utilizes feedback. The device provides an interface for inputting and sending feedback from users, who input their thoughts and ratings on the recipes they have cooked. The server collects this feedback and performs re-learning to improve the accuracy of the generative AI model. A specific example of how this works is to retrain the AI ​​model based on feedback such as "the pasta was bland." This process obtains feedback data as input and an improved AI model as output.

[2507] 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.

[2508] 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.

[2509] 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.

[2510] 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.

[2511] 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.

[2512] 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.

[2513] 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).

[2514] 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.

[2515] 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."

[2516] 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.

[2517] 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).

[2518] 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.

[2519] 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.

[2520] 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.

[2521] 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.

[2522] 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.

[2523] 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.

[2524] 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.

[2525] 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.

[2526] 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.

[2527] 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.

[2528] The following is further disclosed regarding the above embodiment.

[2529] (Claim 1)

[2530] a means for collecting user preferences, dietary history, and allergy information;

[2531] a means for training a generative AI model based on a user's profile;

[2532] A means for generating recipes that meet the user's desired conditions using th...

Claims

1. a means for collecting user preferences, dietary history, and allergy information; a means for training a generative AI model based on a user's profile; A means for generating recipes that meet the user's desired conditions using the learned generative AI model; and A means for providing the generated recipe to a user; A means to collect user feedback and improve the accuracy of the generative AI model; and A system including:

2. 2. The system according to claim 1, further comprising means for generating a recipe based on recipe conditions desired by a user, taking into consideration the required time and the degree of difficulty in obtaining ingredients.

3. a database for storing user profiles and feedback; The system of claim 1 further comprising means for acquiring data from a database and reflecting the data in the generative AI model.

Images