system

Abstract

Provide a system. [Solution] means for receiving condition information input by a user; a generation means for generating a recipe based on the condition information; a means for providing the generated recipe to a user; A system including:

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] ---

[0005] In recent years, the proliferation of cooking shows, recipe books, and cooking videos has made it difficult for users to find recipes that suit their preferences. As a result, users have to spend a lot of time and effort searching for recipes that suit their preferences. Furthermore, it is difficult to suggest recipes that take into account individual user conditions, such as the user's hometown and age, the ingredients currently in the refrigerator, special dietary preferences, and food dislikes. The present invention aims to solve these problems by quickly and easily providing optimal cooking recipes based on the user's individual conditions. [Means for solving the problem]

[0006] The present invention relates to a system including a means for receiving condition information input by a user, a generating means for generating a recipe based on the condition information, and a means for providing the generated recipe to the user. Specifically, the condition information includes the user's place of origin, age, ingredients in the refrigerator, food preferences, and disliked ingredients, and the generating means includes a means for identifying a cooking style based on the user's place of origin and age, a means for generating a recipe taking into account the ingredients in the refrigerator, and a means for filtering recipes based on the user's preferences and disliked ingredients. Furthermore, the providing means includes a means for transmitting the generated recipe to the user's terminal, making it possible to quickly provide the user with the optimal cooking recipe.

[0007] ---

[0008] ---

[0009] "User" means a person or entity intended to use the System.

[0010] "Condition information" is specific information entered by the user, including place of origin, generation, ingredients in the refrigerator, food preferences, and food dislikes.

[0011] The "receiving means" is a means having a function for transmitting condition information from the user's terminal to the server and for the server to receive the condition information.

[0012] The "generation means" is a means having a function for generating an optimal cooking recipe based on the received condition information.

[0013] The "identification means" is a part of the generation means, and has the function of identifying a cooking style based on the user's place of origin and age.

[0014] The "consideration means" is a part of the generation means, and has the function of generating a recipe by taking into account ingredients in the user's refrigerator.

[0015] The "filtering means" is a part of the generating means, and has the function of filtering recipes based on the user's favorite and disliked ingredients.

[0016] The "provision means" is a means having a function for providing the generated recipe to the user.

[0017] A "terminal" is a device through which a user enters information and receives the resulting recipe.

[0018] The "server" is a computer system that receives information from users, generates recipes using generative AI, and sends the results to the terminal.

[0019] "Generative AI" is a system that uses artificial intelligence technology to generate optimal recipes based on received condition information.

[0020] ---

[0021] These are the definitions of important words included in the claims, which will clarify the meaning of each term in the patent document. [Brief explanation of the drawings]

[0022] [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

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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."

[0043] ---

[0044] System Overview

[0045] This invention relates to a system that uses generative AI to automatically generate optimal cooking recipes based on user-entered condition information and provides them to the user's device. This system can quickly suggest recipes that meet the user's needs and preferences. This system consists of a user's device, a server, and generative AI, and operates as follows:

[0046] System configuration

[0047] 1. User Device

[0048] This refers to the devices through which users input information, including PCs, smartphones, tablets, etc.

[0049] Users input their hometown, age, ingredients in the refrigerator, food preferences, and foods they dislike.

[0050] 2. Server

[0051] The condition information input by the user is received and analyzed.

[0052] Condition information is passed to the generative AI, and it is instructed to generate a recipe.

[0053] 3. Generative AI

[0054] A recipe is generated based on the condition information received from the server.

[0055] It identifies cooking styles based on place of origin and age, takes into account ingredients in the refrigerator, and reflects the user's likes and dislikes.

[0056] System operation flow

[0057] User operations

[0058] 1. The user launches the app

[0059] The user uses the device to access a dedicated app or website.

[0060] 2. Enter condition information

[0061] Users enter their hometown (e.g., Tokyo), age group (e.g., 30s), ingredients in the refrigerator (e.g., chicken, carrots, potatoes), food preferences (e.g., easy-to-make dishes, likes Japanese food), and ingredients they dislike (e.g., celery).

[0062] Sending data and creating recipes

[0063] 3. Data transmission

[0064] The user's input information is sent from the terminal to the server.

[0065] 4. Data Receipt and Analysis

[0066] The server analyzes the received data and extracts the necessary information.

[0067] 5. Instructions for creating recipes

[0068] The server instructs the generative AI to generate a recipe.

[0069] 6. Recipe Generation

[0070] The generative AI identifies the user's cooking style based on their hometown and age, takes into account the ingredients in the refrigerator, and generates recipes based on the user's likes and dislikes.

[0071] Recipe provided

[0072] 7. Submit your recipe

[0073] The generated recipe is sent from the server to the user's terminal.

[0074] 8. Viewing Recipes

[0075] The generated recipe is displayed on the user's device, and the user can follow it to cook the dish.

[0076] Specific examples

[0077] For example, if User A (30 years old, from Tokyo) has chicken, carrots, and potatoes in his refrigerator, the following will happen:

[0078] 1. User A's input

[0079] Birthplace: Tokyo

[0080] Age: 30s

[0081] Ingredients in the refrigerator: chicken, carrots, potatoes

[0082] Preferences: Easy to make dishes, I like Japanese food

[0083] Food I don't like: Celery

[0084] 2. Recipe creation and display

[0085] The server passes the information to the generative AI and instructs it to generate a recipe for "chicken and potatoes."

[0086] The generated recipe is sent to User A's terminal via the server.

[0087] User A checks the following recipe on his terminal:

[0088] Ingredients needed: 200g chicken, 1 carrot, 2 potatoes, soy sauce, mirin, sugar

[0089] Cooking Instructions:

[0090] 1. Cut the chicken into bite-sized pieces

[0091] 2. Cut the carrots and potatoes into chunks

[0092] 3. Add oil to a frying pan and fry the chicken.

[0093] 4. Add carrots and potatoes and stir fry

[0094] 5. Season with soy sauce, mirin, and sugar, cover, and simmer.

[0095] Duration: 30 minutes

[0096] Difficulty: Easy

[0097] In this way, User A can easily obtain cooking recipes that suit his or her preferences. This system allows users to quickly use the best recipes without having to go through complicated searches and information gathering.

[0098] ---

[0099] The processing flow will be explained below.

[0100] ---

[0101] Step 1:

[0102] The user launches the app. The user accesses a dedicated app or website and displays the information input screen.

[0103] Step 2:

[0104] The user inputs condition information, such as hometown, generation, ingredients in the refrigerator, food preferences, and foods they dislike.

[0105] Step 3:

[0106] The device sends the input information to the server, which converts the input condition information into JSON format and sends it to the server via a secure protocol.

[0107] Step 4:

[0108] The server analyzes the received data. The server analyzes the received JSON data and extracts the necessary information (place of origin, generation, ingredients, preferences, and disliked ingredients).

[0109] Step 5:

[0110] The server passes the data to the generative AI, which then passes the extracted information to the generative AI and requests it to generate a recipe.

[0111] Step 6:

[0112] The generative AI generates recipes based on the user's criteria. The generative AI performs the following process:

[0113] 1. Identify the user's cooking style based on their hometown and age.

[0114] 2. Generate recipes that take into account the ingredients you have in your refrigerator.

[0115] 3. Filter recipes based on the user's likes and dislikes.

[0116] Step 7:

[0117] The server formats the generated recipe. The server formats the recipe information to provide the recipe obtained from the generative AI to the user.

[0118] Step 8:

[0119] The server sends the recipe information to the user's device. The formatted recipe information is converted back to JSON format and sent to the user's device.

[0120] Step 9:

[0121] The terminal receives and displays the recipe information. The user's terminal analyzes the received recipe information and displays it on the user interface.

[0122] Step 10:

[0123] The user checks the recipe and starts cooking. The user starts cooking using the displayed recipe.

[0124] ---

[0125] These are the specific steps of the program's processing, which will give you a clearer understanding of how the system works.

[0126] Example 1

[0127] 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."

[0128] In today's busy lifestyles, it is difficult for users to find the perfect recipe based on their hometown, age, the ingredients in their refrigerator, and their preferences and dislikes. Existing recipe websites and apps require users to manually search through vast amounts of information to find the perfect recipe, which is time-consuming and laborious. Furthermore, these websites and apps do not fully consider the user's specific requirements, making it impossible to provide recipes that fully meet the user's needs. Therefore, there is a need for a system that allows users to easily and quickly find recipes that suit them.

[0129] 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.

[0130] In this invention, the server includes means for receiving condition information input by a user, means for generating a prompt sentence based on the condition information, means for generating a recipe using a generative AI model based on the prompt sentence, and means for providing the generated recipe to the user, thereby enabling the user to quickly obtain an optimal recipe based on their hometown, age, available ingredients, food preferences, and disliked ingredients.

[0131] "Means for receiving condition information entered by the user" refers to a function that allows the server to receive information such as place of origin, age, available ingredients, food preferences, and disliked ingredients entered by the user through the terminal.

[0132] "Means for generating prompt sentences" refers to a function that automatically creates sentences (prompt sentences) to give appropriate generation instructions to the generative AI model based on the received user condition information.

[0133] "Means for generating recipes using a generative AI model" refers to a function that uses AI technology to automatically generate cooking recipes that best fit the user's requirements based on the generated prompt text.

[0134] "Means for providing the generated recipe to the user" refers to the function of sending the cooking recipe provided by the generative AI model to the user's device so that the user can view it.

[0135] "Place of origin" refers to the area where the user grew up or lives, and is information that reflects the regional characteristics of the cuisine.

[0136] "Generation" refers to the user's age group, and refers to information that takes into consideration food preferences and nutritional balance according to age.

[0137] "Available ingredients" refers to ingredients currently in the user's refrigerator or kitchen, and information for efficiently using these ingredients.

[0138] "Food preferences" refers to the types of food and seasonings that a user likes, and refers to information that increases the user's satisfaction.

[0139] "Ingredients that the user dislikes" refers to ingredients that the user does not like or wants to avoid due to allergies, etc., and refers to information for generating recipes by excluding these ingredients.

[0140] System Overview

[0141] The system of the present invention automatically generates optimal cooking recipes based on user-entered condition information and provides them to the user's terminal. The system's purpose is to enable users to quickly and accurately obtain recipes that match their hometown, age, ingredients in the refrigerator, and food preferences and dislikes. The operation of the system of the present invention and specific implementation methods are described in detail below.

[0142] Hardware and Software Configuration

[0143] 1. User Device

[0144] The devices used include computers, smartphones, tablets, etc.

[0145] An interface is provided for the user to input condition information.

[0146] Examples: Windows PC, ANDROID (registered trademark) smartphone, iOS tablet

[0147] 2. Server

[0148] Receives and analyzes input information from the user.

[0149] A prompt sentence is generated for the generative AI, instructing it to generate a recipe.

[0150] It has the function of providing the generated recipe to the user's terminal.

[0151] Examples: Cloud servers using Amazon Web Services (AWS (registered trademark)), Microsoft (registered trademark) Azure (registered trademark)

[0152] 3. Generative AI

[0153] Based on the prompt received from the server, a recipe that meets the user's requirements is generated.

[0154] Recipes are generated using advanced natural language processing technology.

[0155] Examples: OpenAI's (registered trademark) GPT-3 (registered trademark) model, Google's (registered trademark) BERT model

[0156] Program processing

[0157] When a user enters condition information through an app or website, that information is sent from the device to the server. The server analyzes the received condition information and generates a prompt to pass to the generative AI. This prompt is sent to the generative AI, instructing it to generate a recipe. The generative AI generates an optimal recipe based on the prompt and returns it to the server. The server formats the generated recipe as needed and sends it to the user's device. The user can then check the recipe on their device and cook the dish based on it.

[0158] Specific operation example

[0159] 1. Enter user condition information

[0160] The user accesses the app using a device and enters the following information:

[0161] Birthplace: Tokyo

[0162] Age: 30s

[0163] Ingredients in the refrigerator: chicken, carrots, potatoes

[0164] Preferences: Easy to make dishes, I like Japanese food

[0165] Food I don't like: Celery

[0166] 2. Prompt generation

[0167] The server generates a prompt based on the information it receives, such as:

[0168] "Generate a recipe for a user in their 30s from Tokyo who has chicken, carrots, and potatoes in the fridge, who likes easy-to-make Japanese food, and who doesn't like celery."

[0169] 3. Recipe Generation

[0170] The generative AI model generates a recipe for "chicken and potatoes" based on the prompt it receives. The specific recipe is as follows:

[0171] Ingredients needed: 200g chicken, 1 carrot, 2 potatoes, soy sauce, mirin, sugar

[0172] Cooking Instructions:

[0173] 1. Cut the chicken into bite-sized pieces

[0174] 2. Cut the carrots and potatoes into chunks

[0175] 3. Add oil to a frying pan and fry the chicken.

[0176] 4. Add carrots and potatoes and stir fry

[0177] 5. Season with soy sauce, mirin, and sugar, cover, and simmer.

[0178] Duration: 30 minutes

[0179] Difficulty: Easy

[0180] 4. Providing recipes

[0181] The server receives the generated recipe and sends it to the user's terminal.

[0182] Users can check the recipe on their device and cook the food based on it.

[0183] As described above, this system allows users to easily and quickly find the optimal cooking recipe. This invention significantly reduces the effort required for users to find recipes that suit their preferences and conditions, allowing them to enjoy everyday cooking more efficiently.

[0184] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0185] Step 1:

[0186] The user enters information. Through a dedicated app or website, the user enters their hometown (e.g., Tokyo), age group (e.g., 30s), ingredients in the refrigerator (e.g., chicken, carrots, potatoes), food preferences (e.g., easy-to-make dishes, likes Japanese food), and ingredients they dislike (e.g., celery). This is the input information.

[0187] Step 2:

[0188] The terminal sends information to the server. The condition information entered by the user is sent from the terminal to the server using a secure communication protocol (e.g., HTTPS). The input data here is the condition information entered by the user, and the output data is the condition information sent to the server.

[0189] The user terminal transmits information quickly and securely.

[0190] Step 3:

[0191] The server receives and analyzes the information. The server receives the condition information sent from the terminal and analyzes this data. The input is the received condition information, and the output is the analyzed data. The analysis contents include extraction of place of origin, generation, ingredient list, preferences, and disliked ingredients.

[0192] Step 4:

[0193] The server generates and sends a prompt to the generative AI. Based on the analyzed condition information, the server generates a prompt to pass to the generative AI. The input is the analyzed condition information, and the output is the prompt. For example, a prompt might be generated that reads, "Please generate a recipe for a user in their 30s from Tokyo who has chicken, carrots, and potatoes in their refrigerator, who likes easy-to-make Japanese food, and who doesn't like celery."

[0194] Step 5:

[0195] The generative AI generates a recipe. After receiving a prompt, the generative AI generates a recipe according to the instructions. The input is the prompt, and the output is the generated recipe. Specifically, the AI ​​generates the optimal recipe from a database or existing recipe models, and creates a "chicken and potato stew" recipe as an example.

[0196] Step 6:

[0197] The server receives the generated recipe. The server receives the recipe output from the generative AI. The input is the recipe output from the generative AI, and the output is the recipe received by the server. The server formats the recipe as needed.

[0198] Step 7:

[0199] The server sends the recipe to the terminal. The formatted recipe is sent from the server to the user's terminal. The input data here is the formatted recipe, and the output data is the recipe sent to the user's terminal. The server sends the recipe securely and quickly.

[0200] Step 8:

[0201] The terminal displays the recipe to the user. The user terminal displays the recipe received from the server. The input is the recipe received from the server, and the output is the displayed recipe. The user can use the recipe displayed on the terminal as a reference to cook a dish. Specifically, the necessary ingredients and cooking steps are displayed in detail.

[0202] (Application example 1)

[0203] 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."

[0204] In modern society, many people lead busy lives, leaving them with insufficient time to cook. While there are many food delivery services available on the market, it is not easy to select a menu that matches the ingredients in your refrigerator and your preferences. Furthermore, current systems have limitations in proposing an appropriate delivery menu that takes into account each user's dietary preferences and disliked ingredients. Therefore, there is a need for a food delivery system that allows users to easily order food that matches their preferences.

[0205] 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.

[0206] In this invention, the server includes a means for receiving condition information entered by a user, a generating means for generating a recipe based on the condition information, a means for proposing a delivery menu based on the generated recipe, and a means for providing the proposed delivery menu to the user, thereby enabling the user to easily order an appropriate food delivery menu based on the ingredients in the refrigerator and their preferences.

[0207] definition statement

[0208] The "means for receiving condition information input by the user" is an interface that receives information input by the user, such as place of origin, generation, ingredients in the refrigerator, food preferences, and food dislikes.

[0209] The "generation means for generating a recipe based on the condition information" is a technical means for generating an appropriate cooking recipe based on the condition information input by the user.

[0210] "Means for proposing delivery menus based on generated recipes" refers to technical means for selecting optimal menus from affiliated food delivery services based on generated cooking recipes and proposing them to users.

[0211] "Means for providing users with suggested delivery menus" refers to a system that displays the selected and suggested delivery menus on the user's device and makes them available for ordering.

[0212] "Means for identifying cooking styles based on the user's place of origin and age" refers to technical means for extracting and identifying cooking styles appropriate for a particular region or era by utilizing the user's place of origin and age information.

[0213] MODE FOR CARRYING OUT THE INVENTION

[0214] System Overview

[0215] This system uses generative AI to generate optimal cooking recipes based on user-entered information, and then suggests and provides optimal food delivery menus based on those recipes, allowing users to easily order the optimal menu based on their preferences and the ingredients they have in their refrigerator.

[0216] System configuration

[0217] It consists of the following major hardware and software components:

[0218] 1. User Device

[0219] A device such as a smartphone, tablet, or PC that provides an interface for users to input condition information.

[0220] 2. Server

[0221] The condition information transmitted from the user terminal is received and analyzed.

[0222] It uses generative AI to generate recipes and suggests food delivery menus based on those recipes.

[0223] The proposed delivery menu is provided to the user terminal.

[0224] 3. Generative AI

[0225] Based on the condition information received from the server, a recipe is generated taking into consideration the user's hometown and age, ingredients in the refrigerator, food preferences, and food dislikes.

[0226] Based on the generated recipe, it compares it with the menus of affiliated restaurants and food delivery services to suggest the optimal delivery menu.

[0227] System operation flow

[0228] User operations

[0229] The user launches a dedicated application on their smartphone or computer and enters the following information:

[0230] Birthplace

[0231] era

[0232] Food in the refrigerator

[0233] Food preferences

[0234] Foods I don't like

[0235] Sending data and creating recipes

[0236] The server receives and analyzes the condition information sent by the user. It then passes the data to a generative AI that generates a recipe that meets the conditions. The generative AI then generates the optimal cooking recipe that matches the user's condition information.

[0237] Providing a proposed menu

[0238] Based on the generated recipe, the server selects an appropriate menu from affiliated food delivery services and sends it to the user's device. The user can then check the proposed food delivery menu on their device and place an order.

[0239] Specific examples

[0240] For example, the user enters the following criteria information:

[0241] Birthplace: Tokyo

[0242] Age: 30s

[0243] Ingredients in the refrigerator: chicken, carrots, potatoes

[0244] Preferences: Easy to make dishes, I like Japanese food

[0245] Food I don't like: Celery

[0246] The server receives these conditions and sends the following prompt to the generator AI:

[0247] Generate a cooking recipe based on the ingredients the user has in their refrigerator: chicken, carrots, potatoes; their preferences: easy-to-make dishes; they like Japanese food; and their least favorite ingredient: celery.

[0248] The generative AI uses this prompt to generate a recipe, for example, "chicken and potatoes." Based on this recipe, the system suggests delivery options for "chicken and potatoes" from affiliated Japanese restaurants. Users can check delivery options that include "chicken and potatoes" and place an order on the spot. This allows users to easily use the optimal food delivery service based on their preferences and the ingredients they have in their refrigerator.

[0249] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0250] Program processing steps

[0251] Step 1: User enters criteria information

[0252] Users launch a dedicated application on their smartphone or computer and enter their hometown, age, ingredients in the refrigerator, food preferences, and foods they dislike.

[0253] Input: User's hometown, age, ingredients in the refrigerator, food preferences and dislikes

[0254] Output: Entered condition information

[0255] Step 2: The device sends the condition information to the server

[0256] The terminal transmits the condition information input by the user to the server as a data packet.

[0257] Input: Condition information entered

[0258] Output: Data packet sent to the server

[0259] Step 3: The server receives and parses the condition information

[0260] The server receives the data packet sent from the terminal and analyzes the condition information, which precisely captures and identifies the data sent.

[0261] Input: A data packet containing the condition information entered by the user.

[0262] Output: Parsed condition information

[0263] Step 4: The server sends a prompt to the generative AI.

[0264] The server creates a prompt sentence to send to the generative AI based on the analyzed condition information. The server then sends the created prompt sentence to the generative AI.

[0265] Input: Parsed condition information

[0266] Output: Prompt sent to the generative AI

[0267] Step 5: Generative AI generates recipes

[0268] Based on the prompt received, the generative AI generates a recipe that takes into account the user's hometown, age, ingredients in the refrigerator, and food preferences and dislikes. In this process, the optimal recipe is generated based on the condition information.

[0269] Input: Prompt sent to the generative AI

[0270] Output: The generated recipe

[0271] Step 6: The server receives and parses the generated recipe

[0272] The server receives and analyzes the generated recipes sent back by the generative AI, and determines which food delivery menu items the recipes match.

[0273] Input: Generated recipe

[0274] Output: Menu suggestions adapted for restaurants and delivery services

[0275] Step 7: The server offers a delivery menu

[0276] The server compares the generated recipes with the menus of restaurants and delivery services to select the optimal delivery menu and then suggests the selected delivery menu.

[0277] Input: Generated recipes and menus from partner restaurants and delivery services

[0278] Output: Suggested delivery menu

[0279] Step 8: Your device will display a suggested delivery menu

[0280] The terminal receives the proposed delivery menu sent from the server and displays it to the user, who can then check the menu and place an order.

[0281] Input: Proposed delivery menu sent from the server

[0282] Output: Delivery menu displayed on the device

[0283] Through the above processing steps, users can easily order food delivery menus based on their preferences and the ingredients in their refrigerators.

[0284] 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.

[0285] ---

[0286] System Overview

[0287] This invention relates to a system that uses condition information entered by the user and an emotion recognition engine to provide optimal cooking recipes using generative AI. This system has the function of optimizing recipes according to the user's emotional state as well as their individual conditions. This system is composed of the user's device, a server, an emotion engine, and generative AI, and operates as follows:

[0288] System configuration

[0289] 1. User Device

[0290] This refers to devices that allow users to input information and perform emotion recognition, and includes PCs, smartphones, tablets, etc.

[0291] The user inputs information about their hometown, age, ingredients in the refrigerator, food preferences, ingredients they dislike, and emotional information.

[0292] 2. Server

[0293] The condition information and emotion information input by the user are received and analyzed.

[0294] Condition information and emotional information are passed to the generative AI, which is then instructed to generate a recipe.

[0295] 3. Emotion Engine

[0296] This is an engine that recognizes the user's emotional state based on the user's input information.

[0297] Emotion recognition includes the ability to analyze emotions from a user's facial expressions, voice, and text.

[0298] 4. Generative AI

[0299] A recipe is generated based on the condition information and emotion information received from the server.

[0300] It identifies cooking styles based on place of origin and age, takes into account ingredients in the refrigerator, and reflects the user's preferences, disliked ingredients, and emotional information.

[0301] System operation flow

[0302] User operations

[0303] 1. The user launches the app

[0304] The user uses the device to access a dedicated app or website and displays an information input screen.

[0305] 2. Input of condition information and emotion information

[0306] Users enter their hometown (e.g., Tokyo), age group (e.g., 30s), ingredients in the refrigerator (e.g., chicken, carrots, potatoes), food preferences (e.g., easy-to-make dishes, Japanese food), and ingredients they dislike (e.g., celery).

[0307] The user also inputs their own emotional information (e.g., feeling stressed or relaxed), or the emotional information is acquired using the device's camera or microphone.

[0308] Sending data and creating recipes

[0309] 3. Data transmission

[0310] The user's input information and emotion information are sent from the terminal to the server.

[0311] 4. Data Receipt and Analysis

[0312] The server analyzes the received data and extracts the necessary information (place of origin, age, ingredients, preferences, disliked ingredients, and emotional information).

[0313] 5. Instructions for creating recipes

[0314] The server passes the data to the generative AI and requests it to generate a recipe.

[0315] 6. Recipe Generation

[0316] The generative AI identifies the user's cooking style based on their hometown and age, takes into account the ingredients in the refrigerator, and generates recipes based on the user's preferences, dislikes, and emotional information.

[0317] Recipe provided

[0318] 7. Submit your recipe

[0319] The generated recipe is sent from the server to the user's terminal.

[0320] 8. Viewing Recipes

[0321] The generated recipe is displayed on the user's device, and the user can follow it to cook the dish.

[0322] Specific examples

[0323] For example, if User A (30 years old, from Tokyo) has chicken, carrots, and potatoes in the refrigerator and is feeling stressed, the following will happen:

[0324] 1. User A's input

[0325] Birthplace: Tokyo

[0326] Age: 30s

[0327] Ingredients in the refrigerator: chicken, carrots, potatoes

[0328] Preferences: Easy to make dishes, I like Japanese food

[0329] Food I don't like: Celery

[0330] Emotional information: Feeling stressed

[0331] 2. Recipe creation and display

[0332] The server passes the information to the generative AI and instructs it to generate a recipe for "chicken and potatoes," which is effective in reducing stress.

[0333] The generated recipe is sent to User A's terminal via the server.

[0334] User A checks the following recipe on his terminal:

[0335] Ingredients needed: 200g chicken, 1 carrot, 2 potatoes, soy sauce, mirin, sugar

[0336] Cooking Instructions:

[0337] 1. Cut the chicken into bite-sized pieces

[0338] 2. Cut the carrots and potatoes into chunks

[0339] 3. Add oil to a frying pan and fry the chicken.

[0340] 4. Add carrots and potatoes and stir fry

[0341] 5. Season with soy sauce, mirin, and sugar, cover, and simmer.

[0342] Duration: 30 minutes

[0343] Difficulty: Easy

[0344] In this way, User A can obtain the optimal cooking recipe that also takes into account his or her emotional state. The emotion engine makes it possible to provide suggestions that take into account the user's psychological state, allowing for the provision of a more personalized service.

[0345] ---

[0346] The processing flow will be explained below.

[0347] ---

[0348] Step 1:

[0349] The user launches the app. Using their device, the user accesses a dedicated app or website and displays the information input screen.

[0350] Step 2:

[0351] The user inputs condition information and emotional information, such as hometown, generation, ingredients in the refrigerator, food preferences, food dislikes, and emotional information (e.g., feeling stressed or relaxed).

[0352] Step 3:

[0353] The device sends input information and emotion information to the server, which converts the input information into JSON format and sends it to the server via a secure protocol.

[0354] Step 4:

[0355] The server analyzes the received JSON data and extracts necessary information (place of origin, generation, ingredients, preferences, disliked ingredients, and emotional information).

[0356] Step 5:

[0357] The server passes the data to the generative AI, which then passes the extracted information to the generative AI and requests it to generate a recipe.

[0358] Step 6:

[0359] A generative AI generates recipes based on the user's criteria and emotions. The generative AI performs the following process:

[0360] 1. Identify the user's cooking style based on their hometown and age.

[0361] 2. Generate recipes taking into account the ingredients in the user's refrigerator.

[0362] 3. Filter recipes based on the user's likes and dislikes, as well as emotional information.

[0363] For example, if a user is feeling stressed, recipes using ingredients and cooking methods that are effective in reducing stress are suggested.

[0364] Step 7:

[0365] The server formats the generated recipe. The server formats the recipe information to provide the recipe obtained from the generative AI to the user.

[0366] Step 8:

[0367] The server sends the recipe information to the user's device. The formatted recipe information is converted back to JSON format and sent to the user's device.

[0368] Step 9:

[0369] The terminal receives and displays the recipe information. The user's terminal analyzes the received recipe information and displays it on the user interface.

[0370] Step 10:

[0371] The user checks the recipe and starts cooking. The user starts cooking using the displayed recipe.

[0372] ---

[0373] These are the specific operational steps of the system's processing flow. By taking the user's emotional information into account, more personalized recipe suggestions become possible.

[0374] Example 2

[0375] 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."

[0376] Conventional recipe generation systems were able to provide recipes based on user condition information, but had limitations in providing personalized recipes that took into account the user's emotional information. Therefore, a system is needed that provides optimal recipes according to the user's emotional state and maximizes user satisfaction and relaxation effects.

[0377] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0378] In this invention, the server includes means for receiving condition information and emotion information input by the user, means for generating a recipe based on the condition information and emotion information, and means for providing the generated recipe to the user, thereby generating a recipe based on the user's emotion information and providing an optimal cooking recipe according to the user's emotional state.

[0379] "User" refers to an individual who inputs condition information and emotion information to generate a recipe.

[0380] "Condition information" refers to information such as the user's hometown, age group, ingredients they have, food preferences, and ingredients they don't like.

[0381] "Emotion information" is information that indicates the user's emotional state, such as whether the user is feeling stressed or relaxed.

[0382] "Means for receiving" refers to the function or mechanism by which the server receives the condition information and emotion information input by the user.

[0383] "Generation means" refers to the function or mechanism for generating a recipe based on the condition information and emotion information received by the server.

[0384] The "means for providing" refers to a function or mechanism for providing the recipe generated by the generation means to the user.

[0385] "Server" refers to a central control device that receives input information from users, analyzes it, creates recipes, and provides them.

[0386] System Overview

[0387] This invention is a system that receives condition information and emotion information entered by a user, generates recipes based on that information, and provides them to the user. This system has the function of optimizing recipes according to the user's individual conditions as well as their emotional state. This system consists of a user's device, a server, an emotion engine, and a generative AI.

[0388] System configuration

[0389] 1. User Device

[0390] This refers to a device that allows users to input information and perform emotion recognition, and includes general-purpose information terminals such as PCs, smartphones, and tablets. Using this, users input information such as their hometown, age, ingredients in the refrigerator, food preferences, disliked ingredients, and emotional information.

[0391] 2. Server

[0392] Its role is to receive condition information and emotion information entered by the user, analyze it, and pass the results to the generative AI. This analysis is performed using hardware and software such as web servers like Nginx or Apache (registered trademark) and programming languages ​​like Python or Java (registered trademark).

[0393] 3. Emotion Engine

[0394] This engine recognizes the user's emotional state based on user input. Emotion recognition includes the ability to analyze emotions from the user's facial expressions, voice, and text. For example, OpenCV and Microsoft Azure's emotion recognition API are used.

[0395] 4. Generative AI

[0396] Recipes are generated based on condition information and emotional information received from the server. Cooking styles are identified based on place of origin and age, and ingredients in the refrigerator are considered, reflecting the user's preferences, disliked ingredients, and emotional information. Large-scale language models such as GPT-3 are used as generative AI.

[0397] Specific examples

[0398] For example, if User A (30 years old, from Tokyo) has chicken, carrots, and potatoes in his refrigerator and is feeling stressed, the system will behave as follows:

[0399] Example input from User A:

[0400] Birthplace: Tokyo

[0401] Age: 30s

[0402] Ingredients in the refrigerator: chicken, carrots, potatoes

[0403] Preferences: Easy to make dishes, I like Japanese food

[0404] Food I don't like: Celery

[0405] Emotional information: Feeling stressed

[0406] Example prompt sentence:

[0407] "Based on the criteria entered by a user in their 30s from Tokyo, please provide easy-to-make Japanese recipes using chicken, carrots, and potatoes from the refrigerator. The user is feeling stressed, so please suggest dishes that will have a relaxing effect."

[0408] Recipe generation and display:

[0409] The server passes the information to the generative AI and instructs it to generate a recipe for "chicken and potatoes," which is effective in reducing stress.

[0410] The generated recipe is sent to User A's terminal via the server.

[0411] User A checks the following recipe on his terminal:

[0412] Ingredients needed: 200g chicken, 1 carrot, 2 potatoes, soy sauce, mirin, sugar

[0413] Cooking Instructions:

[0414] 1. Cut the chicken into bite-sized pieces

[0415] 2. Cut the carrots and potatoes into chunks

[0416] 3. Add oil to a frying pan and fry the chicken.

[0417] 4. Add carrots and potatoes and stir fry

[0418] 5. Season with soy sauce, mirin, and sugar, cover, and simmer.

[0419] Duration: 30 minutes

[0420] Difficulty: Easy

[0421] In this way, User A can obtain the optimal cooking recipe that also takes into account his or her emotional state. The emotion engine makes it possible to provide suggestions that take into account the user's psychological state, allowing for the provision of a more personalized service.

[0422] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0423] Step 1:

[0424] The user enters information

[0425] Input: The user uses the terminal to input information about their hometown, age, ingredients in the refrigerator, food preferences, food dislikes, and emotional information.

[0426] Data processing and calculation: The user enters the information into the input form and presses the send button.

[0427] Output: The terminal collects the input information and prepares it for transmission.

[0428] Specific actions: The user opens an information entry screen on their device's app or website, enters information into each field, and presses the submit button.

[0429] Step 2:

[0430] Sending data

[0431] Input: Condition and emotion information entered by the user.

[0432] Data processing and calculation: The device compiles the entered information and sends it to the server using a secure communication protocol (e.g., HTTPS).

[0433] Output: The server receives the user's condition information and emotion information.

[0434] Specific operation: The terminal issues a communication request to send the user's information to the server, and the server receives it.

[0435] Step 3:

[0436] Data reception and analysis by the server

[0437] Input: Condition and emotion information sent by the user.

[0438] Data processing and calculation: The server analyzes the received data and extracts each item (place of origin, generation, ingredients, preferences, disliked ingredients, emotional information). Analysis is performed using a JSON parser and specific libraries (e.g., Python pandas).

[0439] Output: Organized user condition and emotion information.

[0440] Specific operation: The server converts the received data into the required format and analyzes it.

[0441] Step 4:

[0442] The server analyzes the emotional information using an emotion engine.

[0443] Input: Organized emotional information.

[0444] Data processing and calculation: The server passes the emotional information to an emotion engine (e.g., OpenCV or Microsoft Azure emotion recognition API) to analyze the emotional state. Specifically, text analysis, voice analysis, and image analysis are performed.

[0445] Output: Parsed emotional state (e.g. stressed, relaxed, etc.).

[0446] Specific operation: The server calls the emotion engine, analyzes the emotional state, and obtains the results.

[0447] Step 5:

[0448] The server instructs the generative AI to generate recipes.

[0449] Input: Organized condition information and analyzed emotion information.

[0450] Data processing and calculation: The server passes data as prompts to the generative AI model and instructs it to generate a recipe. Specifically, the prompts are input into a large-scale language model such as GPT-3.

[0451] Output: The generated recipe.

[0452] Specific operation: The server passes prompts such as "Tokyo," "30s," "chicken, carrots, potatoes," "easy to make dishes, Japanese food," "celery," and "feeling stressed" to the generative AI.

[0453] Step 6:

[0454] Generative AI generates recipes

[0455] Input: The prompt passed by the server.

[0456] Data processing and computation: A generative AI model generates recipes based on prompts, using natural language processing techniques.

[0457] Output: The generated recipe text.

[0458] What happens: A generative AI model (e.g., GPT-3) analyzes the prompt and generates a specific recipe based on it.

[0459] Step 7:

[0460] The server sends the generated recipe to the user's device.

[0461] Input: The generated recipe.

[0462] Data processing and calculation: The server compiles the generated recipes and sends them to the user's device.

[0463] Output: A recipe that can be displayed on the user's device.

[0464] Specific operation: The server sends the generated recipe to the user's device as an HTTP response.

[0465] Step 8:

[0466] User checks the recipe

[0467] Input: The recipe sent by the server.

[0468] Data processing and calculation: The device converts the received recipe into a display format and presents it visually to the user.

[0469] Output: A user-viewable recipe.

[0470] Specific operation: The device displays the received recipe information on the screen so that the user can check it.

[0471] (Application example 2)

[0472] 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."

[0473] Current food delivery services are unable to suggest dishes that take into account the user's emotional state, making it difficult to suggest dishes that match the user's psychological needs and situation. In addition, the lack of personalized dish suggestions based on emotions poses a challenge in increasing user satisfaction.

[0474] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving condition information and emotion information input by the user, generation means for generating a recipe based on the condition information and emotion information, and means for providing the generated recipe to the user. This makes it possible to suggest dishes personalized according to the user's emotional state.

[0475] "Condition information" is information about the user's hometown, age group, ingredients prepared in the device, food preferences, and food dislikes.

[0476] "Emotion information" is information that represents the user's emotional state, and is obtained from facial expressions, voice, text, and the like.

[0477] The "generation means" is a means for generating a recipe based on the condition information and emotion information.

[0478] A "prompt sentence" is an automatically generated sentence that makes a suggestion or a question to the user.

[0479] MODE FOR CARRYING OUT THE INVENTION

[0480] System Overview

[0481] This invention relates to a food delivery service system that provides individually optimized recipes taking into account the user's emotional state. The system uses generative AI to generate recipes based on the user's input of condition information and emotional information, and provides the recipes to the user.

[0482] System configuration

[0483] 1. User Device

[0484] A device that allows users to input information and performs emotion recognition. Specifically, this includes smartphones.

[0485] The user inputs condition information (place of origin, generation, ingredients available on the device, food preferences, and disliked ingredients) and emotional information (facial expression, voice, and text input).

[0486] 2. Server

[0487] The condition information and emotion information input by the user are received and analyzed.

[0488] Condition information and emotion information are passed to the generative AI, and it is instructed to generate a recipe.

[0489] 3. Emotion Engine

[0490] This is an engine that analyzes emotional information based on user input information.

[0491] Emotion recognition includes facial expression recognition, speech analysis, and text analysis (e.g., OpenCV, TENSORFLOW (registered trademark)).

[0492] 4. Generative AI

[0493] A recipe is generated based on the condition information and emotion information received from the server.

[0494] Prompt sentences are generated according to individual conditions and suggestions are made to the user.

[0495] Example of a system

[0496] User operations

[0497] The user launches a dedicated food delivery application on their smartphone and performs the following operations.

[0498] 1. Input of condition information and emotion information

[0499] Users input their hometown, age, ingredients available on the device, food preferences, and disliked ingredients. They can also input their own emotional information or obtain it using the smartphone's camera and microphone.

[0500] Sending data and creating recipes

[0501] 2. Data transmission

[0502] The condition information and emotion information are transmitted from the user terminal to the server.

[0503] 3. Data Analysis

[0504] The server uses an emotion engine to analyze emotional information and passes the data to a generative AI to instruct it on how to generate a recipe.

[0505] Recipe provided

[0506] 4. Recipe Generation

[0507] The generative AI generates recipes and prompts that take into account the user's emotional and conditional information.

[0508] 5. Submit your recipe

[0509] The generated recipe is sent to the user's terminal via the server.

[0510] Specific examples

[0511] For example, if the user is tired (emotional information) and has chicken and potatoes as ingredients, the server will generate the following recipe based on the information received:

[0512] Example prompt sentence:

[0513] "You look tired. How about a nutritious creamed chicken and potato dish? It's easy to make and only takes 30 minutes."

[0514] As described above, personalized recipe suggestions based on emotional information are possible, which can increase user satisfaction.

[0515] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0516] Step 1:

[0517] The user launches a dedicated food delivery app on their smartphone. Through the app's UI, the user inputs condition information (place of origin, age group, ingredients prepared on the device, food preferences, and disliked ingredients). The app also uses the smartphone's camera and microphone to acquire emotional information (e.g., facial expressions and voice). Input information includes place of origin, age group, ingredients, preferences, disliked ingredients, facial expression data, and voice data. This data is then compiled into a single data packet for output.

[0518] Step 2:

[0519] Condition information and emotion information are sent from the terminal to the server. The server receives all data packets entered by the user as input. The data packets are stored in the server as output.

[0520] Step 3:

[0521] The server analyzes the emotional information using an emotion engine. The emotional information (e.g., facial expression data, voice data) stored on the server is used as input. The emotion engine (e.g., OpenCV, TensorFlow) is used to analyze the data and identify the user's emotional state (e.g., tired, stressed, relaxed). The analyzed emotional state information is generated as output.

[0522] Step 4:

[0523] The server passes condition information and emotional information to the generative AI, instructing it to generate the optimal recipe. A dataset containing analyzed emotional state information and condition information (place of origin, age, ingredients, preferences, and disliked ingredients) is used as input. The generative AI identifies the cooking style based on this information and generates a prompt. The optimal recipe and prompt are generated as output.

[0524] Step 5:

[0525] The recipe and prompt text generated by the generative AI are sent from the server to the user's device. The input includes the generated recipe and prompt text. The output is the recipe and prompt text in a format that can be displayed on the user's device.

[0526] Step 6:

[0527] The user terminal displays the received recipe and prompt text. The input includes data (recipe, prompt text) from the server. The output is displayed on the screen in a format that is easy for the user to understand, allowing the user to confirm the suggested dishes and start ordering or cooking as necessary.

[0528] Specific examples

[0529] For example, if the user is tired and has chicken and potatoes, in step 4 the generative AI will generate the following prompt and recipe:

[0530] Example prompt sentence:

[0531] "You look tired. How about a nutritious creamed chicken and potato dish? It's easy to make and only takes 30 minutes."

[0532] 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.

[0533] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0534] 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.

[0535] [Second embodiment]

[0536] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0537] 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.

[0538] 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).

[0539] 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.

[0540] 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.

[0541] 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).

[0542] 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.

[0543] 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.

[0544] 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.

[0545] 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.

[0546] 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.

[0547] 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."

[0548] ---

[0549] System Overview

[0550] This invention relates to a system that uses generative AI to automatically generate optimal cooking recipes based on user-entered condition information and provides them to the user's device. This system can quickly suggest recipes that meet the user's needs and preferences. This system consists of a user's device, a server, and generative AI, and operates as follows:

[0551] System configuration

[0552] 1. User Device

[0553] This refers to the devices through which users input information, including PCs, smartphones, tablets, etc.

[0554] Users input their hometown, age, ingredients in the refrigerator, food preferences, and foods they dislike.

[0555] 2. Server

[0556] The condition information input by the user is received and analyzed.

[0557] Condition information is passed to the generative AI, and it is instructed to generate a recipe.

[0558] 3. Generative AI

[0559] A recipe is generated based on the condition information received from the server.

[0560] It identifies cooking styles based on place of origin and age, takes into account ingredients in the refrigerator, and reflects the user's likes and dislikes.

[0561] System operation flow

[0562] User operations

[0563] 1. The user launches the app

[0564] The user uses the device to access a dedicated app or website.

[0565] 2. Enter condition information

[0566] Users enter their hometown (e.g., Tokyo), age group (e.g., 30s), ingredients in the refrigerator (e.g., chicken, carrots, potatoes), food preferences (e.g., easy-to-make dishes, likes Japanese food), and ingredients they dislike (e.g., celery).

[0567] Sending data and creating recipes

[0568] 3. Data transmission

[0569] The user's input information is sent from the terminal to the server.

[0570] 4. Data Receipt and Analysis

[0571] The server analyzes the received data and extracts the necessary information.

[0572] 5. Instructions for creating recipes

[0573] The server instructs the generative AI to generate a recipe.

[0574] 6. Recipe Generation

[0575] The generative AI identifies the user's cooking style based on their hometown and age, takes into account the ingredients in the refrigerator, and generates recipes based on the user's likes and dislikes.

[0576] Recipe provided

[0577] 7. Submit your recipe

[0578] The generated recipe is sent from the server to the user's terminal.

[0579] 8. Viewing Recipes

[0580] The generated recipe is displayed on the user's device, and the user can follow it to cook the dish.

[0581] Specific examples

[0582] For example, if User A (30 years old, from Tokyo) has chicken, carrots, and potatoes in his refrigerator, the following will happen:

[0583] 1. User A's input

[0584] Birthplace: Tokyo

[0585] Age: 30s

[0586] Ingredients in the refrigerator: chicken, carrots, potatoes

[0587] Preferences: Easy to make dishes, I like Japanese food

[0588] Food I don't like: Celery

[0589] 2. Recipe creation and display

[0590] The server passes the information to the generative AI and instructs it to generate a recipe for "chicken and potatoes."

[0591] The generated recipe is sent to User A's terminal via the server.

[0592] User A checks the following recipe on his terminal:

[0593] Ingredients needed: 200g chicken, 1 carrot, 2 potatoes, soy sauce, mirin, sugar

[0594] Cooking Instructions:

[0595] 1. Cut the chicken into bite-sized pieces

[0596] 2. Cut the carrots and potatoes into chunks

[0597] 3. Add oil to a frying pan and fry the chicken.

[0598] 4. Add carrots and potatoes and stir fry

[0599] 5. Season with soy sauce, mirin, and sugar, cover, and simmer.

[0600] Duration: 30 minutes

[0601] Difficulty: Easy

[0602] In this way, User A can easily obtain cooking recipes that suit his or her preferences. This system allows users to quickly use the best recipes without having to go through complicated searches and information gathering.

[0603] ---

[0604] The processing flow will be explained below.

[0605] ---

[0606] Step 1:

[0607] The user launches the app. The user accesses a dedicated app or website and displays the information input screen.

[0608] Step 2:

[0609] The user inputs condition information, such as hometown, generation, ingredients in the refrigerator, food preferences, and foods they dislike.

[0610] Step 3:

[0611] The device sends the input information to the server, which converts the input condition information into JSON format and sends it to the server via a secure protocol.

[0612] Step 4:

[0613] The server analyzes the received data. The server analyzes the received JSON data and extracts the necessary information (place of origin, generation, ingredients, preferences, and disliked ingredients).

[0614] Step 5:

[0615] The server passes the data to the generative AI, which then passes the extracted information to the generative AI and requests it to generate a recipe.

[0616] Step 6:

[0617] The generative AI generates recipes based on the user's criteria. The generative AI performs the following process:

[0618] 1. Identify the user's cooking style based on their hometown and age.

[0619] 2. Generate recipes that take into account the ingredients you have in your refrigerator.

[0620] 3. Filter recipes based on the user's likes and dislikes.

[0621] Step 7:

[0622] The server formats the generated recipe. The server formats the recipe information to provide the recipe obtained from the generative AI to the user.

[0623] Step 8:

[0624] The server sends the recipe information to the user's device. The formatted recipe information is converted back to JSON format and sent to the user's device.

[0625] Step 9:

[0626] The terminal receives and displays the recipe information. The user's terminal analyzes the received recipe information and displays it on the user interface.

[0627] Step 10:

[0628] The user checks the recipe and starts cooking. The user starts cooking using the displayed recipe.

[0629] ---

[0630] These are the specific steps of the program's processing, which will give you a clearer understanding of how the system works.

[0631] Example 1

[0632] 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."

[0633] In today's busy lifestyles, it is difficult for users to find the perfect recipe based on their hometown, age, the ingredients in their refrigerator, and their preferences and dislikes. Existing recipe websites and apps require users to manually search through vast amounts of information to find the perfect recipe, which is time-consuming and laborious. Furthermore, these websites and apps do not fully consider the user's specific requirements, making it impossible to provide recipes that fully meet the user's needs. Therefore, there is a need for a system that allows users to easily and quickly find recipes that suit them.

[0634] 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.

[0635] In this invention, the server includes means for receiving condition information input by a user, means for generating a prompt sentence based on the condition information, means for generating a recipe using a generative AI model based on the prompt sentence, and means for providing the generated recipe to the user, thereby enabling the user to quickly obtain an optimal recipe based on their hometown, age, available ingredients, food preferences, and disliked ingredients.

[0636] "Means for receiving condition information entered by the user" refers to a function that allows the server to receive information such as place of origin, age, available ingredients, food preferences, and disliked ingredients entered by the user through the terminal.

[0637] "Means for generating prompt sentences" refers to a function that automatically creates sentences (prompt sentences) to give appropriate generation instructions to the generative AI model based on the received user condition information.

[0638] "Means for generating recipes using a generative AI model" refers to a function that uses AI technology to automatically generate cooking recipes that best fit the user's requirements based on the generated prompt text.

[0639] "Means for providing the generated recipe to the user" refers to the function of sending the cooking recipe provided by the generative AI model to the user's device so that the user can view it.

[0640] "Place of origin" refers to the area where the user grew up or lives, and is information that reflects the regional characteristics of the cuisine.

[0641] "Generation" refers to the user's age group, and refers to information that takes into consideration food preferences and nutritional balance according to age.

[0642] "Available ingredients" refers to ingredients currently in the user's refrigerator or kitchen, and information for efficiently using these ingredients.

[0643] "Food preferences" refers to the types of food and seasonings that a user likes, and refers to information that increases the user's satisfaction.

[0644] "Ingredients that the user dislikes" refers to ingredients that the user does not like or wants to avoid due to allergies, etc., and refers to information for generating recipes by excluding these ingredients.

[0645] System Overview

[0646] The system of the present invention automatically generates optimal cooking recipes based on user-entered condition information and provides them to the user's terminal. The system's purpose is to enable users to quickly and accurately obtain recipes that match their hometown, age, ingredients in the refrigerator, and food preferences and dislikes. The operation of the system of the present invention and specific implementation methods are described in detail below.

[0647] Hardware and Software Configuration

[0648] 1. User Device

[0649] The devices used include computers, smartphones, tablets, etc.

[0650] An interface is provided for the user to input condition information.

[0651] Examples: Windows PC, Android smartphone, iOS tablet

[0652] 2. Server

[0653] Receives and analyzes input information from the user.

[0654] A prompt sentence is generated for the generative AI, instructing it to generate a recipe.

[0655] It has the function of providing the generated recipe to the user's terminal.

[0656] Examples: Cloud servers using Amazon Web Services (AWS), Microsoft Azure

[0657] 3. Generative AI

[0658] Based on the prompt received from the server, a recipe that meets the user's requirements is generated.

[0659] Recipes are generated using advanced natural language processing technology.

[0660] Examples: OpenAI's GPT-3 model, Google's BERT model

[0661] Program processing

[0662] When a user enters condition information through an app or website, that information is sent from the device to the server. The server analyzes the received condition information and generates a prompt to pass to the generative AI. This prompt is sent to the generative AI, instructing it to generate a recipe. The generative AI generates an optimal recipe based on the prompt and returns it to the server. The server formats the generated recipe as needed and sends it to the user's device. The user can then check the recipe on their device and cook the dish based on it.

[0663] Specific operation example

[0664] 1. Enter user condition information

[0665] The user accesses the app using a device and enters the following information:

[0666] Birthplace: Tokyo

[0667] Age: 30s

[0668] Ingredients in the refrigerator: chicken, carrots, potatoes

[0669] Preferences: Easy to make dishes, I like Japanese food

[0670] Food I don't like: Celery

[0671] 2. Prompt generation

[0672] The server generates a prompt based on the information it receives, such as:

[0673] "Generate a recipe for a user in their 30s from Tokyo who has chicken, carrots, and potatoes in the fridge, who likes easy-to-make Japanese food, and who doesn't like celery."

[0674] 3. Recipe Generation

[0675] The generative AI model generates a recipe for "chicken and potatoes" based on the prompt it receives. The specific recipe is as follows:

[0676] Ingredients needed: 200g chicken, 1 carrot, 2 potatoes, soy sauce, mirin, sugar

[0677] Cooking Instructions:

[0678] 1. Cut the chicken into bite-sized pieces

[0679] 2. Cut the carrots and potatoes into chunks

[0680] 3. Add oil to a frying pan and fry the chicken.

[0681] 4. Add carrots and potatoes and stir fry

[0682] 5. Season with soy sauce, mirin, and sugar, cover, and simmer.

[0683] Duration: 30 minutes

[0684] Difficulty: Easy

[0685] 4. Providing recipes

[0686] The server receives the generated recipe and sends it to the user's terminal.

[0687] Users can check the recipe on their device and cook the food based on it.

[0688] As described above, this system allows users to easily and quickly find the optimal cooking recipe. This invention significantly reduces the effort required for users to find recipes that suit their preferences and conditions, allowing them to enjoy everyday cooking more efficiently.

[0689] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0690] Step 1:

[0691] The user enters information. Through a dedicated app or website, the user enters their hometown (e.g., Tokyo), age group (e.g., 30s), ingredients in the refrigerator (e.g., chicken, carrots, potatoes), food preferences (e.g., easy-to-make dishes, likes Japanese food), and ingredients they dislike (e.g., celery). This is the input information.

[0692] Step 2:

[0693] The terminal sends information to the server. The condition information entered by the user is sent from the terminal to the server using a secure communication protocol (e.g., HTTPS). The input data here is the condition information entered by the user, and the output data is the condition information sent to the server.

[0694] The user terminal transmits information quickly and securely.

[0695] Step 3:

[0696] The server receives and analyzes the information. The server receives the condition information sent from the terminal and analyzes this data. The input is the received condition information, and the output is the analyzed data. The analysis contents include extraction of place of origin, generation, ingredient list, preferences, and disliked ingredients.

[0697] Step 4:

[0698] The server generates and sends a prompt to the generative AI. Based on the analyzed condition information, the server generates a prompt to pass to the generative AI. The input is the analyzed condition information, and the output is the prompt. For example, a prompt might be generated that reads, "Please generate a recipe for a user in their 30s from Tokyo who has chicken, carrots, and potatoes in their refrigerator, who likes easy-to-make Japanese food, and who doesn't like celery."

[0699] Step 5:

[0700] The generative AI generates a recipe. After receiving a prompt, the generative AI generates a recipe according to the instructions. The input is the prompt, and the output is the generated recipe. Specifically, the AI ​​generates the optimal recipe from a database or existing recipe models, and creates a "chicken and potato stew" recipe as an example.

[0701] Step 6:

[0702] The server receives the generated recipe. The server receives the recipe output from the generative AI. The input is the recipe output from the generative AI, and the output is the recipe received by the server. The server formats the recipe as needed.

[0703] Step 7:

[0704] The server sends the recipe to the terminal. The formatted recipe is sent from the server to the user's terminal. The input data here is the formatted recipe, and the output data is the recipe sent to the user's terminal. The server sends the recipe securely and quickly.

[0705] Step 8:

[0706] The terminal displays the recipe to the user. The user terminal displays the recipe received from the server. The input is the recipe received from the server, and the output is the displayed recipe. The user can use the recipe displayed on the terminal as a reference to cook a dish. Specifically, the necessary ingredients and cooking steps are displayed in detail.

[0707] (Application example 1)

[0708] 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."

[0709] In modern society, many people lead busy lives, leaving them with insufficient time to cook. While there are many food delivery services available on the market, it is not easy to select a menu that matches the ingredients in your refrigerator and your preferences. Furthermore, current systems have limitations in proposing an appropriate delivery menu that takes into account each user's dietary preferences and disliked ingredients. Therefore, there is a need for a food delivery system that allows users to easily order food that matches their preferences.

[0710] 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.

[0711] In this invention, the server includes a means for receiving condition information entered by a user, a generating means for generating a recipe based on the condition information, a means for proposing a delivery menu based on the generated recipe, and a means for providing the proposed delivery menu to the user, thereby enabling the user to easily order an appropriate food delivery menu based on the ingredients in the refrigerator and their preferences.

[0712] definition statement

[0713] The "means for receiving condition information input by the user" is an interface that receives information input by the user, such as place of origin, generation, ingredients in the refrigerator, food preferences, and food dislikes.

[0714] The "generation means for generating a recipe based on the condition information" is a technical means for generating an appropriate cooking recipe based on the condition information input by the user.

[0715] "Means for proposing delivery menus based on generated recipes" refers to technical means for selecting optimal menus from affiliated food delivery services based on generated cooking recipes and proposing them to users.

[0716] "Means for providing users with suggested delivery menus" refers to a system that displays the selected and suggested delivery menus on the user's device and makes them available for ordering.

[0717] "Means for identifying cooking styles based on the user's place of origin and age" refers to technical means for extracting and identifying cooking styles appropriate for a particular region or era by utilizing the user's place of origin and age information.

[0718] MODE FOR CARRYING OUT THE INVENTION

[0719] System Overview

[0720] This system uses generative AI to generate optimal cooking recipes based on user-entered information, and then suggests and provides optimal food delivery menus based on those recipes, allowing users to easily order the optimal menu based on their preferences and the ingredients they have in their refrigerator.

[0721] System configuration

[0722] It consists of the following major hardware and software components:

[0723] 1. User Device

[0724] A device such as a smartphone, tablet, or PC that provides an interface for users to input condition information.

[0725] 2. Server

[0726] The condition information transmitted from the user terminal is received and analyzed.

[0727] It uses generative AI to generate recipes and suggests food delivery menus based on those recipes.

[0728] The proposed delivery menu is provided to the user terminal.

[0729] 3. Generative AI

[0730] Based on the condition information received from the server, a recipe is generated taking into consideration the user's hometown and age, ingredients in the refrigerator, food preferences, and food dislikes.

[0731] Based on the generated recipe, it compares it with the menus of affiliated restaurants and food delivery services to suggest the optimal delivery menu.

[0732] System operation flow

[0733] User operations

[0734] The user launches a dedicated application on their smartphone or computer and enters the following information:

[0735] Birthplace

[0736] era

[0737] Food in the refrigerator

[0738] Food preferences

[0739] Foods I don't like

[0740] Sending data and creating recipes

[0741] The server receives and analyzes the condition information sent by the user. It then passes the data to a generative AI that generates a recipe that meets the conditions. The generative AI then generates the optimal cooking recipe that matches the user's condition information.

[0742] Providing a proposed menu

[0743] Based on the generated recipe, the server selects an appropriate menu from affiliated food delivery services and sends it to the user's device. The user can then check the proposed food delivery menu on their device and place an order.

[0744] Specific examples

[0745] For example, the user enters the following criteria information:

[0746] Birthplace: Tokyo

[0747] Age: 30s

[0748] Ingredients in the refrigerator: chicken, carrots, potatoes

[0749] Preferences: Easy to make dishes, I like Japanese food

[0750] Food I don't like: Celery

[0751] The server receives these conditions and sends the following prompt to the generator AI:

[0752] Generate a cooking recipe based on the ingredients the user has in their refrigerator: chicken, carrots, potatoes; their preferences: easy-to-make dishes; they like Japanese food; and their least favorite ingredient: celery.

[0753] The generative AI uses this prompt to generate a recipe, for example, "chicken and potatoes." Based on this recipe, the system suggests delivery options for "chicken and potatoes" from affiliated Japanese restaurants. Users can check delivery options that include "chicken and potatoes" and place an order on the spot. This allows users to easily use the optimal food delivery service based on their preferences and the ingredients they have in their refrigerator.

[0754] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0755] Program processing steps

[0756] Step 1: User enters criteria information

[0757] Users launch a dedicated application on their smartphone or computer and enter their hometown, age, ingredients in the refrigerator, food preferences, and foods they dislike.

[0758] Input: User's hometown, age, ingredients in the refrigerator, food preferences and dislikes

[0759] Output: Entered condition information

[0760] Step 2: The device sends the condition information to the server

[0761] The terminal transmits the condition information input by the user to the server as a data packet.

[0762] Input: Condition information entered

[0763] Output: Data packet sent to the server

[0764] Step 3: The server receives and parses the condition information

[0765] The server receives the data packet sent from the terminal and analyzes the condition information, which precisely captures and identifies the data sent.

[0766] Input: A data packet containing the condition information entered by the user.

[0767] Output: Parsed condition information

[0768] Step 4: The server sends a prompt to the generative AI.

[0769] The server creates a prompt sentence to send to the generative AI based on the analyzed condition information. The server then sends the created prompt sentence to the generative AI.

[0770] Input: Parsed condition information

[0771] Output: Prompt sent to the generative AI

[0772] Step 5: Generative AI generates recipes

[0773] Based on the prompt received, the generative AI generates a recipe that takes into account the user's hometown, age, ingredients in the refrigerator, and food preferences and dislikes. In this process, the optimal recipe is generated based on the condition information.

[0774] Input: Prompt sent to the generative AI

[0775] Output: The generated recipe

[0776] Step 6: The server receives and parses the generated recipe

[0777] The server receives and analyzes the generated recipes sent back by the generative AI, and determines which food delivery menu items the recipes match.

[0778] Input: Generated recipe

[0779] Output: Menu suggestions adapted for restaurants and delivery services

[0780] Step 7: The server offers a delivery menu

[0781] The server compares the generated recipes with the menus of restaurants and delivery services to select the optimal delivery menu and then suggests the selected delivery menu.

[0782] Input: Generated recipes and menus from partner restaurants and delivery services

[0783] Output: Suggested delivery menu

[0784] Step 8: Your device will display a suggested delivery menu

[0785] The terminal receives the proposed delivery menu sent from the server and displays it to the user, who can then check the menu and place an order.

[0786] Input: Proposed delivery menu sent from the server

[0787] Output: Delivery menu displayed on the device

[0788] Through the above processing steps, users can easily order food delivery menus based on their preferences and the ingredients in their refrigerators.

[0789] 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.

[0790] ---

[0791] System Overview

[0792] This invention relates to a system that uses condition information entered by the user and an emotion recognition engine to provide optimal cooking recipes using generative AI. This system has the function of optimizing recipes according to the user's emotional state as well as their individual conditions. This system is composed of the user's device, a server, an emotion engine, and generative AI, and operates as follows:

[0793] System configuration

[0794] 1. User Device

[0795] This refers to devices that allow users to input information and perform emotion recognition, and includes PCs, smartphones, tablets, etc.

[0796] The user inputs information about their hometown, age, ingredients in the refrigerator, food preferences, ingredients they dislike, and emotional information.

[0797] 2. Server

[0798] The condition information and emotion information input by the user are received and analyzed.

[0799] Condition information and emotional information are passed to the generative AI, which is then instructed to generate a recipe.

[0800] 3. Emotion Engine

[0801] This is an engine that recognizes the user's emotional state based on the user's input information.

[0802] Emotion recognition includes the ability to analyze emotions from a user's facial expressions, voice, and text.

[0803] 4. Generative AI

[0804] A recipe is generated based on the condition information and emotion information received from the server.

[0805] It identifies cooking styles based on place of origin and age, takes into account ingredients in the refrigerator, and reflects the user's preferences, disliked ingredients, and emotional information.

[0806] System operation flow

[0807] User operations

[0808] 1. The user launches the app

[0809] The user uses the device to access a dedicated app or website and displays an information input screen.

[0810] 2. Input of condition information and emotion information

[0811] Users enter their hometown (e.g., Tokyo), age group (e.g., 30s), ingredients in the refrigerator (e.g., chicken, carrots, potatoes), food preferences (e.g., easy-to-make dishes, Japanese food), and ingredients they dislike (e.g., celery).

[0812] The user also inputs their own emotional information (e.g., feeling stressed or relaxed), or the emotional information is acquired using the device's camera or microphone.

[0813] Sending data and creating recipes

[0814] 3. Data transmission

[0815] The user's input information and emotion information are sent from the terminal to the server.

[0816] 4. Data Receipt and Analysis

[0817] The server analyzes the received data and extracts the necessary information (place of origin, age, ingredients, preferences, disliked ingredients, and emotional information).

[0818] 5. Instructions for creating recipes

[0819] The server passes the data to the generative AI and requests it to generate a recipe.

[0820] 6. Recipe Generation

[0821] The generative AI identifies the user's cooking style based on their hometown and age, takes into account the ingredients in the refrigerator, and generates recipes based on the user's preferences, dislikes, and emotional information.

[0822] Recipe provided

[0823] 7. Submit your recipe

[0824] The generated recipe is sent from the server to the user's terminal.

[0825] 8. Viewing Recipes

[0826] The generated recipe is displayed on the user's device, and the user can follow it to cook the dish.

[0827] Specific examples

[0828] For example, if User A (30 years old, from Tokyo) has chicken, carrots, and potatoes in the refrigerator and is feeling stressed, the following will happen:

[0829] 1. User A's input

[0830] Birthplace: Tokyo

[0831] Age: 30s

[0832] Ingredients in the refrigerator: chicken, carrots, potatoes

[0833] Preferences: Easy to make dishes, I like Japanese food

[0834] Food I don't like: Celery

[0835] Emotional information: Feeling stressed

[0836] 2. Recipe creation and display

[0837] The server passes the information to the generative AI and instructs it to generate a recipe for "chicken and potatoes," which is effective in reducing stress.

[0838] The generated recipe is sent to User A's terminal via the server.

[0839] User A checks the following recipe on his terminal:

[0840] Ingredients needed: 200g chicken, 1 carrot, 2 potatoes, soy sauce, mirin, sugar

[0841] Cooking Instructions:

[0842] 1. Cut the chicken into bite-sized pieces

[0843] 2. Cut the carrots and potatoes into chunks

[0844] 3. Add oil to a frying pan and fry the chicken.

[0845] 4. Add carrots and potatoes and stir fry

[0846] 5. Season with soy sauce, mirin, and sugar, cover, and simmer.

[0847] Duration: 30 minutes

[0848] Difficulty: Easy

[0849] In this way, User A can obtain the optimal cooking recipe that also takes into account his or her emotional state. The emotion engine makes it possible to provide suggestions that take into account the user's psychological state, allowing for the provision of a more personalized service.

[0850] ---

[0851] The processing flow will be explained below.

[0852] ---

[0853] Step 1:

[0854] The user launches the app. Using their device, the user accesses a dedicated app or website and displays the information input screen.

[0855] Step 2:

[0856] The user inputs condition information and emotional information, such as hometown, generation, ingredients in the refrigerator, food preferences, food dislikes, and emotional information (e.g., feeling stressed or relaxed).

[0857] Step 3:

[0858] The device sends input information and emotion information to the server, which converts the input information into JSON format and sends it to the server via a secure protocol.

[0859] Step 4:

[0860] The server analyzes the received JSON data and extracts necessary information (place of origin, generation, ingredients, preferences, disliked ingredients, and emotional information).

[0861] Step 5:

[0862] The server passes the data to the generative AI, which then passes the extracted information to the generative AI and requests it to generate a recipe.

[0863] Step 6:

[0864] A generative AI generates recipes based on the user's criteria and emotions. The generative AI performs the following process:

[0865] 1. Identify the user's cooking style based on their hometown and age.

[0866] 2. Generate recipes taking into account the ingredients in the user's refrigerator.

[0867] 3. Filter recipes based on the user's likes and dislikes, as well as emotional information.

[0868] For example, if a user is feeling stressed, recipes using ingredients and cooking methods that are effective in reducing stress are suggested.

[0869] Step 7:

[0870] The server formats the generated recipe. The server formats the recipe information to provide the recipe obtained from the generative AI to the user.

[0871] Step 8:

[0872] The server sends the recipe information to the user's device. The formatted recipe information is converted back to JSON format and sent to the user's device.

[0873] Step 9:

[0874] The terminal receives and displays the recipe information. The user's terminal analyzes the received recipe information and displays it on the user interface.

[0875] Step 10:

[0876] The user checks the recipe and starts cooking. The user starts cooking using the displayed recipe.

[0877] ---

[0878] These are the specific operational steps of the system's processing flow. By taking the user's emotional information into account, more personalized recipe suggestions become possible.

[0879] Example 2

[0880] 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."

[0881] Conventional recipe generation systems were able to provide recipes based on user condition information, but had limitations in providing personalized recipes that took into account the user's emotional information. Therefore, a system is needed that provides optimal recipes according to the user's emotional state and maximizes user satisfaction and relaxation effects.

[0882] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0883] In this invention, the server includes means for receiving condition information and emotion information input by the user, means for generating a recipe based on the condition information and emotion information, and means for providing the generated recipe to the user, thereby generating a recipe based on the user's emotion information and providing an optimal cooking recipe according to the user's emotional state.

[0884] "User" refers to an individual who inputs condition information and emotion information to generate a recipe.

[0885] "Condition information" refers to information such as the user's hometown, age group, ingredients they have, food preferences, and ingredients they don't like.

[0886] "Emotion information" is information that indicates the user's emotional state, such as whether the user is feeling stressed or relaxed.

[0887] "Means for receiving" refers to the function or mechanism by which the server receives the condition information and emotion information input by the user.

[0888] "Generation means" refers to the function or mechanism for generating a recipe based on the condition information and emotion information received by the server.

[0889] The "means for providing" refers to a function or mechanism for providing the recipe generated by the generation means to the user.

[0890] "Server" refers to a central control device that receives input information from users, analyzes it, creates recipes, and provides them.

[0891] System Overview

[0892] This invention is a system that receives condition information and emotion information entered by a user, generates recipes based on that information, and provides them to the user. This system has the function of optimizing recipes according to the user's individual conditions as well as their emotional state. This system consists of a user's device, a server, an emotion engine, and a generative AI.

[0893] System configuration

[0894] 1. User Device

[0895] This refers to a device that allows users to input information and perform emotion recognition, and includes general-purpose information terminals such as PCs, smartphones, and tablets. Using this, users input information such as their hometown, age, ingredients in the refrigerator, food preferences, disliked ingredients, and emotional information.

[0896] 2. Server

[0897] Its role is to receive condition and emotion information entered by the user, analyze it, and pass the results to the generative AI. This analysis is performed using hardware and software such as web servers like Nginx or Apache, and programming languages ​​like Python or Java.

[0898] 3. Emotion Engine

[0899] This engine recognizes the user's emotional state based on user input. Emotion recognition includes the ability to analyze emotions from the user's facial expressions, voice, and text. For example, OpenCV and Microsoft Azure's emotion recognition API are used.

[0900] 4. Generative AI

[0901] Recipes are generated based on condition information and emotional information received from the server. Cooking styles are identified based on place of origin and age, and ingredients in the refrigerator are considered, reflecting the user's preferences, disliked ingredients, and emotional information. Large-scale language models such as GPT-3 are used as generative AI.

[0902] Specific examples

[0903] For example, if User A (30 years old, from Tokyo) has chicken, carrots, and potatoes in his refrigerator and is feeling stressed, the system will behave as follows:

[0904] Example input from User A:

[0905] Birthplace: Tokyo

[0906] Age: 30s

[0907] Ingredients in the refrigerator: chicken, carrots, potatoes

[0908] Preferences: Easy to make dishes, I like Japanese food

[0909] Food I don't like: Celery

[0910] Emotional information: Feeling stressed

[0911] Example prompt sentence:

[0912] "Based on the criteria entered by a user in their 30s from Tokyo, please provide easy-to-make Japanese recipes using chicken, carrots, and potatoes from the refrigerator. The user is feeling stressed, so please suggest dishes that will have a relaxing effect."

[0913] Recipe generation and display:

[0914] The server passes the information to the generative AI and instructs it to generate a recipe for "chicken and potatoes," which is effective in reducing stress.

[0915] The generated recipe is sent to User A's terminal via the server.

[0916] User A checks the following recipe on his terminal:

[0917] Ingredients needed: 200g chicken, 1 carrot, 2 potatoes, soy sauce, mirin, sugar

[0918] Cooking Instructions:

[0919] 1. Cut the chicken into bite-sized pieces

[0920] 2. Cut the carrots and potatoes into chunks

[0921] 3. Add oil to a frying pan and fry the chicken.

[0922] 4. Add carrots and potatoes and stir fry

[0923] 5. Season with soy sauce, mirin, and sugar, cover, and simmer.

[0924] Duration: 30 minutes

[0925] Difficulty: Easy

[0926] In this way, User A can obtain the optimal cooking recipe that also takes into account his or her emotional state. The emotion engine makes it possible to provide suggestions that take into account the user's psychological state, allowing for the provision of a more personalized service.

[0927] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0928] Step 1:

[0929] The user enters information

[0930] Input: The user uses the terminal to input information about their hometown, age, ingredients in the refrigerator, food preferences, food dislikes, and emotional information.

[0931] Data processing and calculation: The user enters the information into the input form and presses the send button.

[0932] Output: The terminal collects the input information and prepares it for transmission.

[0933] Specific actions: The user opens an information entry screen on their device's app or website, enters information into each field, and presses the submit button.

[0934] Step 2:

[0935] Sending data

[0936] Input: Condition and emotion information entered by the user.

[0937] Data processing and calculation: The device compiles the entered information and sends it to the server using a secure communication protocol (e.g., HTTPS).

[0938] Output: The server receives the user's condition information and emotion information.

[0939] Specific operation: The terminal issues a communication request to send the user's information to the server, and the server receives it.

[0940] Step 3:

[0941] Data reception and analysis by the server

[0942] Input: Condition and emotion information sent by the user.

[0943] Data processing and calculation: The server analyzes the received data and extracts each item (place of origin, generation, ingredients, preferences, disliked ingredients, emotional information). Analysis is performed using a JSON parser and specific libraries (e.g., Python pandas).

[0944] Output: Organized user condition and emotion information.

[0945] Specific operation: The server converts the received data into the required format and analyzes it.

[0946] Step 4:

[0947] The server analyzes the emotional information using an emotion engine.

[0948] Input: Organized emotional information.

[0949] Data processing and calculation: The server passes the emotional information to an emotion engine (e.g., OpenCV or Microsoft Azure emotion recognition API) to analyze the emotional state. Specifically, text analysis, voice analysis, and image analysis are performed.

[0950] Output: Parsed emotional state (e.g. stressed, relaxed, etc.).

[0951] Specific operation: The server calls the emotion engine, analyzes the emotional state, and obtains the results.

[0952] Step 5:

[0953] The server instructs the generative AI to generate recipes.

[0954] Input: Organized condition information and analyzed emotion information.

[0955] Data processing and calculation: The server passes data as prompts to the generative AI model and instructs it to generate a recipe. Specifically, the prompts are input into a large-scale language model such as GPT-3.

[0956] Output: The generated recipe.

[0957] Specific operation: The server passes prompts such as "Tokyo," "30s," "chicken, carrots, potatoes," "easy to make dishes, Japanese food," "celery," and "feeling stressed" to the generative AI.

[0958] Step 6:

[0959] Generative AI generates recipes

[0960] Input: The prompt passed by the server.

[0961] Data processing and computation: A generative AI model generates recipes based on prompts, using natural language processing techniques.

[0962] Output: The generated recipe text.

[0963] What happens: A generative AI model (e.g., GPT-3) analyzes the prompt and generates a specific recipe based on it.

[0964] Step 7:

[0965] The server sends the generated recipe to the user's device.

[0966] Input: The generated recipe.

[0967] Data processing and calculation: The server compiles the generated recipes and sends them to the user's device.

[0968] Output: A recipe that can be displayed on the user's device.

[0969] Specific operation: The server sends the generated recipe to the user's device as an HTTP response.

[0970] Step 8:

[0971] User checks the recipe

[0972] Input: The recipe sent by the server.

[0973] Data processing and calculation: The device converts the received recipe into a display format and presents it visually to the user.

[0974] Output: A user-viewable recipe.

[0975] Specific operation: The device displays the received recipe information on the screen so that the user can check it.

[0976] (Application example 2)

[0977] 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."

[0978] Current food delivery services are unable to suggest dishes that take into account the user's emotional state, making it difficult to suggest dishes that match the user's psychological needs and situation. In addition, the lack of personalized dish suggestions based on emotions poses a challenge in increasing user satisfaction.

[0979] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving condition information and emotion information input by the user, generation means for generating a recipe based on the condition information and emotion information, and means for providing the generated recipe to the user. This makes it possible to suggest dishes personalized according to the user's emotional state.

[0980] "Condition information" is information about the user's hometown, age group, ingredients prepared in the device, food preferences, and food dislikes.

[0981] "Emotion information" is information that represents the user's emotional state, and is obtained from facial expressions, voice, text, and the like.

[0982] The "generation means" is a means for generating a recipe based on the condition information and emotion information.

[0983] A "prompt sentence" is an automatically generated sentence that makes a suggestion or a question to the user.

[0984] MODE FOR CARRYING OUT THE INVENTION

[0985] System Overview

[0986] This invention relates to a food delivery service system that provides individually optimized recipes taking into account the user's emotional state. The system uses generative AI to generate recipes based on the user's input of condition information and emotional information, and provides the recipes to the user.

[0987] System configuration

[0988] 1. User Device

[0989] A device that allows users to input information and performs emotion recognition. Specifically, this includes smartphones.

[0990] The user inputs condition information (place of origin, generation, ingredients available on the device, food preferences, and disliked ingredients) and emotional information (facial expression, voice, and text input).

[0991] 2. Server

[0992] The condition information and emotion information input by the user are received and analyzed.

[0993] Condition information and emotion information are passed to the generative AI, and it is instructed to generate a recipe.

[0994] 3. Emotion Engine

[0995] This is an engine that analyzes emotional information based on user input information.

[0996] Emotion recognition includes facial expression recognition, speech analysis, and text analysis (e.g., OpenCV, TensorFlow).

[0997] 4. Generative AI

[0998] A recipe is generated based on the condition information and emotion information received from the server.

[0999] Prompt sentences are generated according to individual conditions and suggestions are made to the user.

[1000] Example of a system

[1001] User operations

[1002] The user launches a dedicated food delivery application on their smartphone and performs the following operations.

[1003] 1. Input of condition information and emotion information

[1004] Users input their hometown, age, ingredients available on the device, food preferences, and disliked ingredients. They can also input their own emotional information or obtain it using the smartphone's camera and microphone.

[1005] Sending data and creating recipes

[1006] 2. Data transmission

[1007] The condition information and emotion information are transmitted from the user terminal to the server.

[1008] 3. Data Analysis

[1009] The server uses an emotion engine to analyze emotional information and passes the data to a generative AI to instruct it on how to generate a recipe.

[1010] Recipe provided

[1011] 4. Recipe Generation

[1012] The generative AI generates recipes and prompts that take into account the user's emotional and conditional information.

[1013] 5. Submit your recipe

[1014] The generated recipe is sent to the user's terminal via the server.

[1015] Specific examples

[1016] For example, if the user is tired (emotional information) and has chicken and potatoes as ingredients, the server will generate the following recipe based on the information received:

[1017] Example prompt sentence:

[1018] "You look tired. How about a nutritious creamed chicken and potato dish? It's easy to make and only takes 30 minutes."

[1019] As described above, personalized recipe suggestions based on emotional information are possible, which can increase user satisfaction.

[1020] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1021] Step 1:

[1022] The user launches a dedicated food delivery app on their smartphone. Through the app's UI, the user inputs condition information (place of origin, age group, ingredients prepared on the device, food preferences, and disliked ingredients). The app also uses the smartphone's camera and microphone to acquire emotional information (e.g., facial expressions and voice). Input information includes place of origin, age group, ingredients, preferences, disliked ingredients, facial expression data, and voice data. This data is then compiled into a single data packet for output.

[1023] Step 2:

[1024] Condition information and emotion information are sent from the terminal to the server. The server receives all data packets entered by the user as input. The data packets are stored in the server as output.

[1025] Step 3:

[1026] The server analyzes the emotional information using an emotion engine. The emotional information (e.g., facial expression data, voice data) stored on the server is used as input. The emotion engine (e.g., OpenCV, TensorFlow) is used to analyze the data and identify the user's emotional state (e.g., tired, stressed, relaxed). The analyzed emotional state information is generated as output.

[1027] Step 4:

[1028] The server passes condition information and emotional information to the generative AI, instructing it to generate the optimal recipe. A dataset containing analyzed emotional state information and condition information (place of origin, age, ingredients, preferences, and disliked ingredients) is used as input. The generative AI identifies the cooking style based on this information and generates a prompt. The optimal recipe and prompt are generated as output.

[1029] Step 5:

[1030] The recipe and prompt text generated by the generative AI are sent from the server to the user's device. The input includes the generated recipe and prompt text. The output is the recipe and prompt text in a format that can be displayed on the user's device.

[1031] Step 6:

[1032] The user terminal displays the received recipe and prompt text. The input includes data (recipe, prompt text) from the server. The output is displayed on the screen in a format that is easy for the user to understand, allowing the user to confirm the suggested dishes and start ordering or cooking as necessary.

[1033] Specific examples

[1034] For example, if the user is tired and has chicken and potatoes, in step 4 the generative AI will generate the following prompt and recipe:

[1035] Example prompt sentence:

[1036] "You look tired. How about a nutritious creamed chicken and potato dish? It's easy to make and only takes 30 minutes."

[1037] 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.

[1038] 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.

[1039] 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.

[1040] [Third embodiment]

[1041] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1042] 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.

[1043] 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).

[1044] 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.

[1045] 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.

[1046] 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).

[1047] 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.

[1048] 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.

[1049] 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.

[1050] 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.

[1051] 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.

[1052] 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."

[1053] ---

[1054] System Overview

[1055] This invention relates to a system that uses generative AI to automatically generate optimal cooking recipes based on user-entered condition information and provides them to the user's device. This system can quickly suggest recipes that meet the user's needs and preferences. This system consists of a user's device, a server, and generative AI, and operates as follows:

[1056] System configuration

[1057] 1. User Device

[1058] This refers to the devices through which users input information, including PCs, smartphones, tablets, etc.

[1059] Users input their hometown, age, ingredients in the refrigerator, food preferences, and foods they dislike.

[1060] 2. Server

[1061] The condition information input by the user is received and analyzed.

[1062] Condition information is passed to the generative AI, and it is instructed to generate a recipe.

[1063] 3. Generative AI

[1064] A recipe is generated based on the condition information received from the server.

[1065] It identifies cooking styles based on place of origin and age, takes into account ingredients in the refrigerator, and reflects the user's likes and dislikes.

[1066] System operation flow

[1067] User operations

[1068] 1. The user launches the app

[1069] The user uses the device to access a dedicated app or website.

[1070] 2. Enter condition information

[1071] Users enter their hometown (e.g., Tokyo), age group (e.g., 30s), ingredients in the refrigerator (e.g., chicken, carrots, potatoes), food preferences (e.g., easy-to-make dishes, likes Japanese food), and ingredients they dislike (e.g., celery).

[1072] Sending data and creating recipes

[1073] 3. Data transmission

[1074] The user's input information is sent from the terminal to the server.

[1075] 4. Data Receipt and Analysis

[1076] The server analyzes the received data and extracts the necessary information.

[1077] 5. Instructions for creating recipes

[1078] The server instructs the generative AI to generate a recipe.

[1079] 6. Recipe Generation

[1080] The generative AI identifies the user's cooking style based on their hometown and age, takes into account the ingredients in the refrigerator, and generates recipes based on the user's likes and dislikes.

[1081] Recipe provided

[1082] 7. Submit your recipe

[1083] The generated recipe is sent from the server to the user's terminal.

[1084] 8. Viewing Recipes

[1085] The generated recipe is displayed on the user's device, and the user can follow it to cook the dish.

[1086] Specific examples

[1087] For example, if User A (30 years old, from Tokyo) has chicken, carrots, and potatoes in his refrigerator, the following will happen:

[1088] 1. User A's input

[1089] Birthplace: Tokyo

[1090] Age: 30s

[1091] Ingredients in the refrigerator: chicken, carrots, potatoes

[1092] Preferences: Easy to make dishes, I like Japanese food

[1093] Food I don't like: Celery

[1094] 2. Recipe creation and display

[1095] The server passes the information to the generative AI and instructs it to generate a recipe for "chicken and potatoes."

[1096] The generated recipe is sent to User A's terminal via the server.

[1097] User A checks the following recipe on his terminal:

[1098] Ingredients needed: 200g chicken, 1 carrot, 2 potatoes, soy sauce, mirin, sugar

[1099] Cooking Instructions:

[1100] 1. Cut the chicken into bite-sized pieces

[1101] 2. Cut the carrots and potatoes into chunks

[1102] 3. Add oil to a frying pan and fry the chicken.

[1103] 4. Add carrots and potatoes and stir fry

[1104] 5. Season with soy sauce, mirin, and sugar, cover, and simmer.

[1105] Duration: 30 minutes

[1106] Difficulty: Easy

[1107] In this way, User A can easily obtain cooking recipes that suit his or her preferences. This system allows users to quickly use the best recipes without having to go through complicated searches and information gathering.

[1108] ---

[1109] The processing flow will be explained below.

[1110] ---

[1111] Step 1:

[1112] The user launches the app. The user accesses a dedicated app or website and displays the information input screen.

[1113] Step 2:

[1114] The user inputs condition information, such as hometown, generation, ingredients in the refrigerator, food preferences, and foods they dislike.

[1115] Step 3:

[1116] The device sends the input information to the server, which converts the input condition information into JSON format and sends it to the server via a secure protocol.

[1117] Step 4:

[1118] The server analyzes the received data. The server analyzes the received JSON data and extracts the necessary information (place of origin, generation, ingredients, preferences, and disliked ingredients).

[1119] Step 5:

[1120] The server passes the data to the generative AI, which then passes the extracted information to the generative AI and requests it to generate a recipe.

[1121] Step 6:

[1122] The generative AI generates recipes based on the user's criteria. The generative AI performs the following process:

[1123] 1. Identify the user's cooking style based on their hometown and age.

[1124] 2. Generate recipes that take into account the ingredients you have in your refrigerator.

[1125] 3. Filter recipes based on the user's likes and dislikes.

[1126] Step 7:

[1127] The server formats the generated recipe. The server formats the recipe information to provide the recipe obtained from the generative AI to the user.

[1128] Step 8:

[1129] The server sends the recipe information to the user's device. The formatted recipe information is converted back to JSON format and sent to the user's device.

[1130] Step 9:

[1131] The terminal receives and displays the recipe information. The user's terminal analyzes the received recipe information and displays it on the user interface.

[1132] Step 10:

[1133] The user checks the recipe and starts cooking. The user starts cooking using the displayed recipe.

[1134] ---

[1135] These are the specific steps of the program's processing, which will give you a clearer understanding of how the system works.

[1136] Example 1

[1137] 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."

[1138] In today's busy lifestyles, it is difficult for users to find the perfect recipe based on their hometown, age, the ingredients in their refrigerator, and their preferences and dislikes. Existing recipe websites and apps require users to manually search through vast amounts of information to find the perfect recipe, which is time-consuming and laborious. Furthermore, these websites and apps do not fully consider the user's specific requirements, making it impossible to provide recipes that fully meet the user's needs. Therefore, there is a need for a system that allows users to easily and quickly find recipes that suit them.

[1139] 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.

[1140] In this invention, the server includes means for receiving condition information input by a user, means for generating a prompt sentence based on the condition information, means for generating a recipe using a generative AI model based on the prompt sentence, and means for providing the generated recipe to the user, thereby enabling the user to quickly obtain an optimal recipe based on their hometown, age, available ingredients, food preferences, and disliked ingredients.

[1141] "Means for receiving condition information entered by the user" refers to a function that allows the server to receive information such as place of origin, age, available ingredients, food preferences, and disliked ingredients entered by the user through the terminal.

[1142] "Means for generating prompt sentences" refers to a function that automatically creates sentences (prompt sentences) to give appropriate generation instructions to the generative AI model based on the received user condition information.

[1143] "Means for generating recipes using a generative AI model" refers to a function that uses AI technology to automatically generate cooking recipes that best fit the user's requirements based on the generated prompt text.

[1144] "Means for providing the generated recipe to the user" refers to the function of sending the cooking recipe provided by the generative AI model to the user's device so that the user can view it.

[1145] "Place of origin" refers to the area where the user grew up or lives, and is information that reflects the regional characteristics of the cuisine.

[1146] "Generation" refers to the user's age group, and refers to information that takes into consideration food preferences and nutritional balance according to age.

[1147] "Available ingredients" refers to ingredients currently in the user's refrigerator or kitchen, and information for efficiently using these ingredients.

[1148] "Food preferences" refers to the types of food and seasonings that a user likes, and refers to information that increases the user's satisfaction.

[1149] "Ingredients that the user dislikes" refers to ingredients that the user does not like or wants to avoid due to allergies, etc., and refers to information for generating recipes by excluding these ingredients.

[1150] System Overview

[1151] The system of the present invention automatically generates optimal cooking recipes based on user-entered condition information and provides them to the user's terminal. The system's purpose is to enable users to quickly and accurately obtain recipes that match their hometown, age, ingredients in the refrigerator, and food preferences and dislikes. The operation of the system of the present invention and specific implementation methods are described in detail below.

[1152] Hardware and Software Configuration

[1153] 1. User Device

[1154] The devices used include computers, smartphones, tablets, etc.

[1155] An interface is provided for the user to input condition information.

[1156] Examples: Windows PC, Android smartphone, iOS tablet

[1157] 2. Server

[1158] Receives and analyzes input information from the user.

[1159] A prompt sentence is generated for the generative AI, instructing it to generate a recipe.

[1160] It has the function of providing the generated recipe to the user's terminal.

[1161] Examples: Cloud servers using Amazon Web Services (AWS), Microsoft Azure

[1162] 3. Generative AI

[1163] Based on the prompt received from the server, a recipe that meets the user's requirements is generated.

[1164] Recipes are generated using advanced natural language processing technology.

[1165] Examples: OpenAI's GPT-3 model, Google's BERT model

[1166] Program processing

[1167] When a user enters condition information through an app or website, that information is sent from the device to the server. The server analyzes the received condition information and generates a prompt to pass to the generative AI. This prompt is sent to the generative AI, instructing it to generate a recipe. The generative AI generates an optimal recipe based on the prompt and returns it to the server. The server formats the generated recipe as needed and sends it to the user's device. The user can then check the recipe on their device and cook the dish based on it.

[1168] Specific operation example

[1169] 1. Enter user condition information

[1170] The user accesses the app using a device and enters the following information:

[1171] Birthplace: Tokyo

[1172] Age: 30s

[1173] Ingredients in the refrigerator: chicken, carrots, potatoes

[1174] Preferences: Easy to make dishes, I like Japanese food

[1175] Food I don't like: Celery

[1176] 2. Prompt generation

[1177] The server generates a prompt based on the information it receives, such as:

[1178] "Generate a recipe for a user in their 30s from Tokyo who has chicken, carrots, and potatoes in the fridge, who likes easy-to-make Japanese food, and who doesn't like celery."

[1179] 3. Recipe Generation

[1180] The generative AI model generates a recipe for "chicken and potatoes" based on the prompt it receives. The specific recipe is as follows:

[1181] Ingredients needed: 200g chicken, 1 carrot, 2 potatoes, soy sauce, mirin, sugar

[1182] Cooking Instructions:

[1183] 1. Cut the chicken into bite-sized pieces

[1184] 2. Cut the carrots and potatoes into chunks

[1185] 3. Add oil to a frying pan and fry the chicken.

[1186] 4. Add carrots and potatoes and stir fry

[1187] 5. Season with soy sauce, mirin, and sugar, cover, and simmer.

[1188] Duration: 30 minutes

[1189] Difficulty: Easy

[1190] 4. Providing recipes

[1191] The server receives the generated recipe and sends it to the user's terminal.

[1192] Users can check the recipe on their device and cook the food based on it.

[1193] As described above, this system allows users to easily and quickly find the optimal cooking recipe. This invention significantly reduces the effort required for users to find recipes that suit their preferences and conditions, allowing them to enjoy everyday cooking more efficiently.

[1194] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1195] Step 1:

[1196] The user enters information. Through a dedicated app or website, the user enters their hometown (e.g., Tokyo), age group (e.g., 30s), ingredients in the refrigerator (e.g., chicken, carrots, potatoes), food preferences (e.g., easy-to-make dishes, likes Japanese food), and ingredients they dislike (e.g., celery). This is the input information.

[1197] Step 2:

[1198] The terminal sends information to the server. The condition information entered by the user is sent from the terminal to the server using a secure communication protocol (e.g., HTTPS). The input data here is the condition information entered by the user, and the output data is the condition information sent to the server.

[1199] The user terminal transmits information quickly and securely.

[1200] Step 3:

[1201] The server receives and analyzes the information. The server receives the condition information sent from the terminal and analyzes this data. The input is the received condition information, and the output is the analyzed data. The analysis contents include extraction of place of origin, generation, ingredient list, preferences, and disliked ingredients.

[1202] Step 4:

[1203] The server generates and sends a prompt to the generative AI. Based on the analyzed condition information, the server generates a prompt to pass to the generative AI. The input is the analyzed condition information, and the output is the prompt. For example, a prompt might be generated that reads, "Please generate a recipe for a user in their 30s from Tokyo who has chicken, carrots, and potatoes in their refrigerator, who likes easy-to-make Japanese food, and who doesn't like celery."

[1204] Step 5:

[1205] The generative AI generates a recipe. After receiving a prompt, the generative AI generates a recipe according to the instructions. The input is the prompt, and the output is the generated recipe. Specifically, the AI ​​generates the optimal recipe from a database or existing recipe models, and creates a "chicken and potato stew" recipe as an example.

[1206] Step 6:

[1207] The server receives the generated recipe. The server receives the recipe output from the generative AI. The input is the recipe output from the generative AI, and the output is the recipe received by the server. The server formats the recipe as needed.

[1208] Step 7:

[1209] The server sends the recipe to the terminal. The formatted recipe is sent from the server to the user's terminal. The input data here is the formatted recipe, and the output data is the recipe sent to the user's terminal. The server sends the recipe securely and quickly.

[1210] Step 8:

[1211] The terminal displays the recipe to the user. The user terminal displays the recipe received from the server. The input is the recipe received from the server, and the output is the displayed recipe. The user can use the recipe displayed on the terminal as a reference to cook a dish. Specifically, the necessary ingredients and cooking steps are displayed in detail.

[1212] (Application example 1)

[1213] 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."

[1214] In modern society, many people lead busy lives, leaving them with insufficient time to cook. While there are many food delivery services available on the market, it is not easy to select a menu that matches the ingredients in your refrigerator and your preferences. Furthermore, current systems have limitations in proposing an appropriate delivery menu that takes into account each user's dietary preferences and disliked ingredients. Therefore, there is a need for a food delivery system that allows users to easily order food that matches their preferences.

[1215] 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.

[1216] In this invention, the server includes a means for receiving condition information entered by a user, a generating means for generating a recipe based on the condition information, a means for proposing a delivery menu based on the generated recipe, and a means for providing the proposed delivery menu to the user, thereby enabling the user to easily order an appropriate food delivery menu based on the ingredients in the refrigerator and their preferences.

[1217] definition statement

[1218] The "means for receiving condition information input by the user" is an interface that receives information input by the user, such as place of origin, generation, ingredients in the refrigerator, food preferences, and food dislikes.

[1219] The "generation means for generating a recipe based on the condition information" is a technical means for generating an appropriate cooking recipe based on the condition information input by the user.

[1220] "Means for proposing delivery menus based on generated recipes" refers to technical means for selecting optimal menus from affiliated food delivery services based on generated cooking recipes and proposing them to users.

[1221] "Means for providing users with suggested delivery menus" refers to a system that displays the selected and suggested delivery menus on the user's device and makes them available for ordering.

[1222] "Means for identifying cooking styles based on the user's place of origin and age" refers to technical means for extracting and identifying cooking styles appropriate for a particular region or era by utilizing the user's place of origin and age information.

[1223] MODE FOR CARRYING OUT THE INVENTION

[1224] System Overview

[1225] This system uses generative AI to generate optimal cooking recipes based on user-entered information, and then suggests and provides optimal food delivery menus based on those recipes, allowing users to easily order the optimal menu based on their preferences and the ingredients they have in their refrigerator.

[1226] System configuration

[1227] It consists of the following major hardware and software components:

[1228] 1. User Device

[1229] A device such as a smartphone, tablet, or PC that provides an interface for users to input condition information.

[1230] 2. Server

[1231] The condition information transmitted from the user terminal is received and analyzed.

[1232] It uses generative AI to generate recipes and suggests food delivery menus based on those recipes.

[1233] The proposed delivery menu is provided to the user terminal.

[1234] 3. Generative AI

[1235] Based on the condition information received from the server, a recipe is generated taking into consideration the user's hometown and age, ingredients in the refrigerator, food preferences, and food dislikes.

[1236] Based on the generated recipe, it compares it with the menus of affiliated restaurants and food delivery services to suggest the optimal delivery menu.

[1237] System operation flow

[1238] User operations

[1239] The user launches a dedicated application on their smartphone or computer and enters the following information:

[1240] Birthplace

[1241] era

[1242] Food in the refrigerator

[1243] Food preferences

[1244] Foods I don't like

[1245] Sending data and creating recipes

[1246] The server receives and analyzes the condition information sent by the user. It then passes the data to a generative AI that generates a recipe that meets the conditions. The generative AI then generates the optimal cooking recipe that matches the user's condition information.

[1247] Providing a proposed menu

[1248] Based on the generated recipe, the server selects an appropriate menu from affiliated food delivery services and sends it to the user's device. The user can then check the proposed food delivery menu on their device and place an order.

[1249] Specific examples

[1250] For example, the user enters the following criteria information:

[1251] Birthplace: Tokyo

[1252] Age: 30s

[1253] Ingredients in the refrigerator: chicken, carrots, potatoes

[1254] Preferences: Easy to make dishes, I like Japanese food

[1255] Food I don't like: Celery

[1256] The server receives these conditions and sends the following prompt to the generator AI:

[1257] Generate a cooking recipe based on the ingredients the user has in their refrigerator: chicken, carrots, potatoes; their preferences: easy-to-make dishes; they like Japanese food; and their least favorite ingredient: celery.

[1258] The generative AI uses this prompt to generate a recipe, for example, "chicken and potatoes." Based on this recipe, the system suggests delivery options for "chicken and potatoes" from affiliated Japanese restaurants. Users can check delivery options that include "chicken and potatoes" and place an order on the spot. This allows users to easily use the optimal food delivery service based on their preferences and the ingredients they have in their refrigerator.

[1259] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1260] Program processing steps

[1261] Step 1: User enters criteria information

[1262] Users launch a dedicated application on their smartphone or computer and enter their hometown, age, ingredients in the refrigerator, food preferences, and foods they dislike.

[1263] Input: User's hometown, age, ingredients in the refrigerator, food preferences and dislikes

[1264] Output: Entered condition information

[1265] Step 2: The device sends the condition information to the server

[1266] The terminal transmits the condition information input by the user to the server as a data packet.

[1267] Input: Condition information entered

[1268] Output: Data packet sent to the server

[1269] Step 3: The server receives and parses the condition information

[1270] The server receives the data packet sent from the terminal and analyzes the condition information, which precisely captures and identifies the data sent.

[1271] Input: A data packet containing the condition information entered by the user.

[1272] Output: Parsed condition information

[1273] Step 4: The server sends a prompt to the generative AI.

[1274] The server creates a prompt sentence to send to the generative AI based on the analyzed condition information. The server then sends the created prompt sentence to the generative AI.

[1275] Input: Parsed condition information

[1276] Output: Prompt sent to the generative AI

[1277] Step 5: Generative AI generates recipes

[1278] Based on the prompt received, the generative AI generates a recipe that takes into account the user's hometown, age, ingredients in the refrigerator, and food preferences and dislikes. In this process, the optimal recipe is generated based on the condition information.

[1279] Input: Prompt sent to the generative AI

[1280] Output: The generated recipe

[1281] Step 6: The server receives and parses the generated recipe

[1282] The server receives and analyzes the generated recipes sent back by the generative AI, and determines which food delivery menu items the recipes match.

[1283] Input: Generated recipe

[1284] Output: Menu suggestions adapted for restaurants and delivery services

[1285] Step 7: The server offers a delivery menu

[1286] The server compares the generated recipes with the menus of restaurants and delivery services to select the optimal delivery menu and then suggests the selected delivery menu.

[1287] Input: Generated recipes and menus from partner restaurants and delivery services

[1288] Output: Suggested delivery menu

[1289] Step 8: Your device will display a suggested delivery menu

[1290] The terminal receives the proposed delivery menu sent from the server and displays it to the user, who can then check the menu and place an order.

[1291] Input: Proposed delivery menu sent from the server

[1292] Output: Delivery menu displayed on the device

[1293] Through the above processing steps, users can easily order food delivery menus based on their preferences and the ingredients in their refrigerators.

[1294] 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.

[1295] ---

[1296] System Overview

[1297] This invention relates to a system that uses condition information entered by the user and an emotion recognition engine to provide optimal cooking recipes using generative AI. This system has the function of optimizing recipes according to the user's emotional state as well as their individual conditions. This system is composed of the user's device, a server, an emotion engine, and generative AI, and operates as follows:

[1298] System configuration

[1299] 1. User Device

[1300] This refers to devices that allow users to input information and perform emotion recognition, and includes PCs, smartphones, tablets, etc.

[1301] The user inputs information about their hometown, age, ingredients in the refrigerator, food preferences, ingredients they dislike, and emotional information.

[1302] 2. Server

[1303] The condition information and emotion information input by the user are received and analyzed.

[1304] Condition information and emotional information are passed to the generative AI, which is then instructed to generate a recipe.

[1305] 3. Emotion Engine

[1306] This is an engine that recognizes the user's emotional state based on the user's input information.

[1307] Emotion recognition includes the ability to analyze emotions from a user's facial expressions, voice, and text.

[1308] 4. Generative AI

[1309] A recipe is generated based on the condition information and emotion information received from the server.

[1310] It identifies cooking styles based on place of origin and age, takes into account ingredients in the refrigerator, and reflects the user's preferences, disliked ingredients, and emotional information.

[1311] System operation flow

[1312] User operations

[1313] 1. The user launches the app

[1314] The user uses the device to access a dedicated app or website and displays an information input screen.

[1315] 2. Input of condition information and emotion information

[1316] Users enter their hometown (e.g., Tokyo), age group (e.g., 30s), ingredients in the refrigerator (e.g., chicken, carrots, potatoes), food preferences (e.g., easy-to-make dishes, Japanese food), and ingredients they dislike (e.g., celery).

[1317] The user also inputs their own emotional information (e.g., feeling stressed or relaxed), or the emotional information is acquired using the device's camera or microphone.

[1318] Sending data and creating recipes

[1319] 3. Data transmission

[1320] The user's input information and emotion information are sent from the terminal to the server.

[1321] 4. Data Receipt and Analysis

[1322] The server analyzes the received data and extracts the necessary information (place of origin, age, ingredients, preferences, disliked ingredients, and emotional information).

[1323] 5. Instructions for creating recipes

[1324] The server passes the data to the generative AI and requests it to generate a recipe.

[1325] 6. Recipe Generation

[1326] The generative AI identifies the user's cooking style based on their hometown and age, takes into account the ingredients in the refrigerator, and generates recipes based on the user's preferences, dislikes, and emotional information.

[1327] Recipe provided

[1328] 7. Submit your recipe

[1329] The generated recipe is sent from the server to the user's terminal.

[1330] 8. Viewing Recipes

[1331] The generated recipe is displayed on the user's device, and the user can follow it to cook the dish.

[1332] Specific examples

[1333] For example, if User A (30 years old, from Tokyo) has chicken, carrots, and potatoes in the refrigerator and is feeling stressed, the following will happen:

[1334] 1. User A's input

[1335] Birthplace: Tokyo

[1336] Age: 30s

[1337] Ingredients in the refrigerator: chicken, carrots, potatoes

[1338] Preferences: Easy to make dishes, I like Japanese food

[1339] Food I don't like: Celery

[1340] Emotional information: Feeling stressed

[1341] 2. Recipe creation and display

[1342] The server passes the information to the generative AI and instructs it to generate a recipe for "chicken and potatoes," which is effective in reducing stress.

[1343] The generated recipe is sent to User A's terminal via the server.

[1344] User A checks the following recipe on his terminal:

[1345] Ingredients needed: 200g chicken, 1 carrot, 2 potatoes, soy sauce, mirin, sugar

[1346] Cooking Instructions:

[1347] 1. Cut the chicken into bite-sized pieces

[1348] 2. Cut the carrots and potatoes into chunks

[1349] 3. Add oil to a frying pan and fry the chicken.

[1350] 4. Add carrots and potatoes and stir fry

[1351] 5. Season with soy sauce, mirin, and sugar, cover, and simmer.

[1352] Duration: 30 minutes

[1353] Difficulty: Easy

[1354] In this way, User A can obtain the optimal cooking recipe that also takes into account his or her emotional state. The emotion engine makes it possible to provide suggestions that take into account the user's psychological state, allowing for the provision of a more personalized service.

[1355] ---

[1356] The processing flow will be explained below.

[1357] ---

[1358] Step 1:

[1359] The user launches the app. Using their device, the user accesses a dedicated app or website and displays the information input screen.

[1360] Step 2:

[1361] The user inputs condition information and emotional information, such as hometown, generation, ingredients in the refrigerator, food preferences, food dislikes, and emotional information (e.g., feeling stressed or relaxed).

[1362] Step 3:

[1363] The device sends input information and emotion information to the server, which converts the input information into JSON format and sends it to the server via a secure protocol.

[1364] Step 4:

[1365] The server analyzes the received JSON data and extracts necessary information (place of origin, generation, ingredients, preferences, disliked ingredients, and emotional information).

[1366] Step 5:

[1367] The server passes the data to the generative AI, which then passes the extracted information to the generative AI and requests it to generate a recipe.

[1368] Step 6:

[1369] A generative AI generates recipes based on the user's criteria and emotions. The generative AI performs the following process:

[1370] 1. Identify the user's cooking style based on their hometown and age.

[1371] 2. Generate recipes taking into account the ingredients in the user's refrigerator.

[1372] 3. Filter recipes based on the user's likes and dislikes, as well as emotional information.

[1373] For example, if a user is feeling stressed, recipes using ingredients and cooking methods that are effective in reducing stress are suggested.

[1374] Step 7:

[1375] The server formats the generated recipe. The server formats the recipe information to provide the recipe obtained from the generative AI to the user.

[1376] Step 8:

[1377] The server sends the recipe information to the user's device. The formatted recipe information is converted back to JSON format and sent to the user's device.

[1378] Step 9:

[1379] The terminal receives and displays the recipe information. The user's terminal analyzes the received recipe information and displays it on the user interface.

[1380] Step 10:

[1381] The user checks the recipe and starts cooking. The user starts cooking using the displayed recipe.

[1382] ---

[1383] These are the specific operational steps of the system's processing flow. By taking the user's emotional information into account, more personalized recipe suggestions become possible.

[1384] Example 2

[1385] 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."

[1386] Conventional recipe generation systems were able to provide recipes based on user condition information, but had limitations in providing personalized recipes that took into account the user's emotional information. Therefore, a system is needed that provides optimal recipes according to the user's emotional state and maximizes user satisfaction and relaxation effects.

[1387] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1388] In this invention, the server includes means for receiving condition information and emotion information input by the user, means for generating a recipe based on the condition information and emotion information, and means for providing the generated recipe to the user, thereby generating a recipe based on the user's emotion information and providing an optimal cooking recipe according to the user's emotional state.

[1389] "User" refers to an individual who inputs condition information and emotion information to generate a recipe.

[1390] "Condition information" refers to information such as the user's hometown, age group, ingredients they have, food preferences, and ingredients they don't like.

[1391] "Emotion information" is information that indicates the user's emotional state, such as whether the user is feeling stressed or relaxed.

[1392] "Means for receiving" refers to the function or mechanism by which the server receives the condition information and emotion information input by the user.

[1393] "Generation means" refers to the function or mechanism for generating a recipe based on the condition information and emotion information received by the server.

[1394] The "means for providing" refers to a function or mechanism for providing the recipe generated by the generation means to the user.

[1395] "Server" refers to a central control device that receives input information from users, analyzes it, creates recipes, and provides them.

[1396] System Overview

[1397] This invention is a system that receives condition information and emotion information entered by a user, generates recipes based on that information, and provides them to the user. This system has the function of optimizing recipes according to the user's individual conditions as well as their emotional state. This system consists of a user's device, a server, an emotion engine, and a generative AI.

[1398] System configuration

[1399] 1. User Device

[1400] This refers to a device that allows users to input information and perform emotion recognition, and includes general-purpose information terminals such as PCs, smartphones, and tablets. Using this, users input information such as their hometown, age, ingredients in the refrigerator, food preferences, disliked ingredients, and emotional information.

[1401] 2. Server

[1402] Its role is to receive condition and emotion information entered by the user, analyze it, and pass the results to the generative AI. This analysis is performed using hardware and software such as web servers like Nginx or Apache, and programming languages ​​like Python or Java.

[1403] 3. Emotion Engine

[1404] This engine recognizes the user's emotional state based on user input. Emotion recognition includes the ability to analyze emotions from the user's facial expressions, voice, and text. For example, OpenCV and Microsoft Azure's emotion recognition API are used.

[1405] 4. Generative AI

[1406] Recipes are generated based on condition information and emotional information received from the server. Cooking styles are identified based on place of origin and age, and ingredients in the refrigerator are considered, reflecting the user's preferences, disliked ingredients, and emotional information. Large-scale language models such as GPT-3 are used as generative AI.

[1407] Specific examples

[1408] For example, if User A (30 years old, from Tokyo) has chicken, carrots, and potatoes in his refrigerator and is feeling stressed, the system will behave as follows:

[1409] Example input from User A:

[1410] Birthplace: Tokyo

[1411] Age: 30s

[1412] Ingredients in the refrigerator: chicken, carrots, potatoes

[1413] Preferences: Easy to make dishes, I like Japanese food

[1414] Food I don't like: Celery

[1415] Emotional information: Feeling stressed

[1416] Example prompt sentence:

[1417] "Based on the criteria entered by a user in their 30s from Tokyo, please provide easy-to-make Japanese recipes using chicken, carrots, and potatoes from the refrigerator. The user is feeling stressed, so please suggest dishes that will have a relaxing effect."

[1418] Recipe generation and display:

[1419] The server passes the information to the generative AI and instructs it to generate a recipe for "chicken and potatoes," which is effective in reducing stress.

[1420] The generated recipe is sent to User A's terminal via the server.

[1421] User A checks the following recipe on his terminal:

[1422] Ingredients needed: 200g chicken, 1 carrot, 2 potatoes, soy sauce, mirin, sugar

[1423] Cooking Instructions:

[1424] 1. Cut the chicken into bite-sized pieces

[1425] 2. Cut the carrots and potatoes into chunks

[1426] 3. Add oil to a frying pan and fry the chicken.

[1427] 4. Add carrots and potatoes and stir fry

[1428] 5. Season with soy sauce, mirin, and sugar, cover, and simmer.

[1429] Duration: 30 minutes

[1430] Difficulty: Easy

[1431] In this way, User A can obtain the optimal cooking recipe that also takes into account his or her emotional state. The emotion engine makes it possible to provide suggestions that take into account the user's psychological state, allowing for the provision of a more personalized service.

[1432] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1433] Step 1:

[1434] The user enters information

[1435] Input: The user uses the terminal to input information about their hometown, age, ingredients in the refrigerator, food preferences, food dislikes, and emotional information.

[1436] Data processing and calculation: The user enters the information into the input form and presses the send button.

[1437] Output: The terminal collects the input information and prepares it for transmission.

[1438] Specific actions: The user opens an information entry screen on their device's app or website, enters information into each field, and presses the submit button.

[1439] Step 2:

[1440] Sending data

[1441] Input: Condition and emotion information entered by the user.

[1442] Data processing and calculation: The device compiles the entered information and sends it to the server using a secure communication protocol (e.g., HTTPS).

[1443] Output: The server receives the user's condition information and emotion information.

[1444] Specific operation: The terminal issues a communication request to send the user's information to the server, and the server receives it.

[1445] Step 3:

[1446] Data reception and analysis by the server

[1447] Input: Condition and emotion information sent by the user.

[1448] Data processing and calculation: The server analyzes the received data and extracts each item (place of origin, generation, ingredients, preferences, disliked ingredients, emotional information). Analysis is performed using a JSON parser and specific libraries (e.g., Python pandas).

[1449] Output: Organized user condition and emotion information.

[1450] Specific operation: The server converts the received data into the required format and analyzes it.

[1451] Step 4:

[1452] The server analyzes the emotional information using an emotion engine.

[1453] Input: Organized emotional information.

[1454] Data processing and calculation: The server passes the emotional information to an emotion engine (e.g., OpenCV or Microsoft Azure emotion recognition API) to analyze the emotional state. Specifically, text analysis, voice analysis, and image analysis are performed.

[1455] Output: Parsed emotional state (e.g. stressed, relaxed, etc.).

[1456] Specific operation: The server calls the emotion engine, analyzes the emotional state, and obtains the results.

[1457] Step 5:

[1458] The server instructs the generative AI to generate recipes.

[1459] Input: Organized condition information and analyzed emotion information.

[1460] Data processing and calculation: The server passes data as prompts to the generative AI model and instructs it to generate a recipe. Specifically, the prompts are input into a large-scale language model such as GPT-3.

[1461] Output: The generated recipe.

[1462] Specific operation: The server passes prompts such as "Tokyo," "30s," "chicken, carrots, potatoes," "easy to make dishes, Japanese food," "celery," and "feeling stressed" to the generative AI.

[1463] Step 6:

[1464] Generative AI generates recipes

[1465] Input: The prompt passed by the server.

[1466] Data processing and computation: A generative AI model generates recipes based on prompts, using natural language processing techniques.

[1467] Output: The generated recipe text.

[1468] What happens: A generative AI model (e.g., GPT-3) analyzes the prompt and generates a specific recipe based on it.

[1469] Step 7:

[1470] The server sends the generated recipe to the user's device.

[1471] Input: The generated recipe.

[1472] Data processing and calculation: The server compiles the generated recipes and sends them to the user's device.

[1473] Output: A recipe that can be displayed on the user's device.

[1474] Specific operation: The server sends the generated recipe to the user's device as an HTTP response.

[1475] Step 8:

[1476] User checks the recipe

[1477] Input: The recipe sent by the server.

[1478] Data processing and calculation: The device converts the received recipe into a display format and presents it visually to the user.

[1479] Output: A user-viewable recipe.

[1480] Specific operation: The device displays the received recipe information on the screen so that the user can check it.

[1481] (Application example 2)

[1482] 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."

[1483] Current food delivery services are unable to suggest dishes that take into account the user's emotional state, making it difficult to suggest dishes that match the user's psychological needs and situation. In addition, the lack of personalized dish suggestions based on emotions poses a challenge in increasing user satisfaction.

[1484] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving condition information and emotion information input by the user, generation means for generating a recipe based on the condition information and emotion information, and means for providing the generated recipe to the user. This makes it possible to suggest dishes personalized according to the user's emotional state.

[1485] "Condition information" is information about the user's hometown, age group, ingredients prepared in the device, food preferences, and food dislikes.

[1486] "Emotion information" is information that represents the user's emotional state, and is obtained from facial expressions, voice, text, and the like.

[1487] The "generation means" is a means for generating a recipe based on the condition information and emotion information.

[1488] A "prompt sentence" is an automatically generated sentence that makes a suggestion or a question to the user.

[1489] MODE FOR CARRYING OUT THE INVENTION

[1490] System Overview

[1491] This invention relates to a food delivery service system that provides individually optimized recipes taking into account the user's emotional state. The system uses generative AI to generate recipes based on the user's input of condition information and emotional information, and provides the recipes to the user.

[1492] System configuration

[1493] 1. User Device

[1494] A device that allows users to input information and performs emotion recognition. Specifically, this includes smartphones.

[1495] The user inputs condition information (place of origin, generation, ingredients available on the device, food preferences, and disliked ingredients) and emotional information (facial expression, voice, and text input).

[1496] 2. Server

[1497] The condition information and emotion information input by the user are received and analyzed.

[1498] Condition information and emotion information are passed to the generative AI, and it is instructed to generate a recipe.

[1499] 3. Emotion Engine

[1500] This is an engine that analyzes emotional information based on user input information.

[1501] Emotion recognition includes facial expression recognition, speech analysis, and text analysis (e.g., OpenCV, TensorFlow).

[1502] 4. Generative AI

[1503] A recipe is generated based on the condition information and emotion information received from the server.

[1504] Prompt sentences are generated according to individual conditions and suggestions are made to the user.

[1505] Example of a system

[1506] User operations

[1507] The user launches a dedicated food delivery application on their smartphone and performs the following operations.

[1508] 1. Input of condition information and emotion information

[1509] Users input their hometown, age, ingredients available on the device, food preferences, and disliked ingredients. They can also input their own emotional information or obtain it using the smartphone's camera and microphone.

[1510] Sending data and creating recipes

[1511] 2. Data transmission

[1512] The condition information and emotion information are transmitted from the user terminal to the server.

[1513] 3. Data Analysis

[1514] The server uses an emotion engine to analyze emotional information and passes the data to a generative AI to instruct it on how to generate a recipe.

[1515] Recipe provided

[1516] 4. Recipe Generation

[1517] The generative AI generates recipes and prompts that take into account the user's emotional and conditional information.

[1518] 5. Submit your recipe

[1519] The generated recipe is sent to the user's terminal via the server.

[1520] Specific examples

[1521] For example, if the user is tired (emotional information) and has chicken and potatoes as ingredients, the server will generate the following recipe based on the information received:

[1522] Example prompt sentence:

[1523] "You look tired. How about a nutritious creamed chicken and potato dish? It's easy to make and only takes 30 minutes."

[1524] As described above, personalized recipe suggestions based on emotional information are possible, which can increase user satisfaction.

[1525] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1526] Step 1:

[1527] The user launches a dedicated food delivery app on their smartphone. Through the app's UI, the user inputs condition information (place of origin, age group, ingredients prepared on the device, food preferences, and disliked ingredients). The app also uses the smartphone's camera and microphone to acquire emotional information (e.g., facial expressions and voice). Input information includes place of origin, age group, ingredients, preferences, disliked ingredients, facial expression data, and voice data. This data is then compiled into a single data packet for output.

[1528] Step 2:

[1529] Condition information and emotion information are sent from the terminal to the server. The server receives all data packets entered by the user as input. The data packets are stored in the server as output.

[1530] Step 3:

[1531] The server analyzes the emotional information using an emotion engine. The emotional information (e.g., facial expression data, voice data) stored on the server is used as input. The emotion engine (e.g., OpenCV, TensorFlow) is used to analyze the data and identify the user's emotional state (e.g., tired, stressed, relaxed). The analyzed emotional state information is generated as output.

[1532] Step 4:

[1533] The server passes condition information and emotional information to the generative AI, instructing it to generate the optimal recipe. A dataset containing analyzed emotional state information and condition information (place of origin, age, ingredients, preferences, and disliked ingredients) is used as input. The generative AI identifies the cooking style based on this information and generates a prompt. The optimal recipe and prompt are generated as output.

[1534] Step 5:

[1535] The recipe and prompt text generated by the generative AI are sent from the server to the user's device. The input includes the generated recipe and prompt text. The output is the recipe and prompt text in a format that can be displayed on the user's device.

[1536] Step 6:

[1537] The user terminal displays the received recipe and prompt text. The input includes data (recipe, prompt text) from the server. The output is displayed on the screen in a format that is easy for the user to understand, allowing the user to confirm the suggested dishes and start ordering or cooking as necessary.

[1538] Specific examples

[1539] For example, if the user is tired and has chicken and potatoes, in step 4 the generative AI will generate the following prompt and recipe:

[1540] Example prompt sentence:

[1541] "You look tired. How about a nutritious creamed chicken and potato dish? It's easy to make and only takes 30 minutes."

[1542] 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.

[1543] 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.

[1544] 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.

[1545] [Fourth embodiment]

[1546] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1547] 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.

[1548] 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).

[1549] 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.

[1550] 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.

[1551] 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).

[1552] 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.

[1553] 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.

[1554] 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.

[1555] 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.

[1556] 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.

[1557] 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.

[1558] 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."

[1559] ---

[1560] System Overview

[1561] This invention relates to a system that uses generative AI to automatically generate optimal cooking recipes based on user-entered condition information and provides them to the user's device. This system can quickly suggest recipes that meet the user's needs and preferences. This system consists of a user's device, a server, and generative AI, and operates as follows:

[1562] System configuration

[1563] 1. User Device

[1564] This refers to the devices through which users input information, including PCs, smartphones, tablets, etc.

[1565] Users input their hometown, age, ingredients in the refrigerator, food preferences, and foods they dislike.

[1566] 2. Server

[1567] The condition information input by the user is received and analyzed.

[1568] Condition information is passed to the generative AI, and it is instructed to generate a recipe.

[1569] 3. Generative AI

[1570] A recipe is generated based on the condition information received from the server.

[1571] It identifies cooking styles based on place of origin and age, takes into account ingredients in the refrigerator, and reflects the user's likes and dislikes.

[1572] System operation flow

[1573] User operations

[1574] 1. The user launches the app

[1575] The user uses the device to access a dedicated app or website.

[1576] 2. Enter condition information

[1577] Users enter their hometown (e.g., Tokyo), age group (e.g., 30s), ingredients in the refrigerator (e.g., chicken, carrots, potatoes), food preferences (e.g., easy-to-make dishes, likes Japanese food), and ingredients they dislike (e.g., celery).

[1578] Sending data and creating recipes

[1579] 3. Data transmission

[1580] The user's input information is sent from the terminal to the server.

[1581] 4. Data Receipt and Analysis

[1582] The server analyzes the received data and extracts the necessary information.

[1583] 5. Instructions for creating recipes

[1584] The server instructs the generative AI to generate a recipe.

[1585] 6. Recipe Generation

[1586] The generative AI identifies the user's cooking style based on their hometown and age, takes into account the ingredients in the refrigerator, and generates recipes based on the user's likes and dislikes.

[1587] Recipe provided

[1588] 7. Submit your recipe

[1589] The generated recipe is sent from the server to the user's terminal.

[1590] 8. Viewing Recipes

[1591] The generated recipe is displayed on the user's device, and the user can follow it to cook the dish.

[1592] Specific examples

[1593] For example, if User A (30 years old, from Tokyo) has chicken, carrots, and potatoes in his refrigerator, the following will happen:

[1594] 1. User A's input

[1595] Birthplace: Tokyo

[1596] Age: 30s

[1597] Ingredients in the refrigerator: chicken, carrots, potatoes

[1598] Preferences: Easy to make dishes, I like Japanese food

[1599] Food I don't like: Celery

[1600] 2. Recipe creation and display

[1601] The server passes the information to the generative AI and instructs it to generate a recipe for "chicken and potatoes."

[1602] The generated recipe is sent to User A's terminal via the server.

[1603] User A checks the following recipe on his terminal:

[1604] Ingredients needed: 200g chicken, 1 carrot, 2 potatoes, soy sauce, mirin, sugar

[1605] Cooking Instructions:

[1606] 1. Cut the chicken into bite-sized pieces

[1607] 2. Cut the carrots and potatoes into chunks

[1608] 3. Add oil to a frying pan and fry the chicken.

[1609] 4. Add carrots and potatoes and stir fry

[1610] 5. Season with soy sauce, mirin, and sugar, cover, and simmer.

[1611] Duration: 30 minutes

[1612] Difficulty: Easy

[1613] In this way, User A can easily obtain cooking recipes that suit his or her preferences. This system allows users to quickly use the best recipes without having to go through complicated searches and information gathering.

[1614] ---

[1615] The processing flow will be explained below.

[1616] ---

[1617] Step 1:

[1618] The user launches the app. The user accesses a dedicated app or website and displays the information input screen.

[1619] Step 2:

[1620] The user inputs condition information, such as hometown, generation, ingredients in the refrigerator, food preferences, and foods they dislike.

[1621] Step 3:

[1622] The device sends the input information to the server, which converts the input condition information into JSON format and sends it to the server via a secure protocol.

[1623] Step 4:

[1624] The server analyzes the received data. The server analyzes the received JSON data and extracts the necessary information (place of origin, generation, ingredients, preferences, and disliked ingredients).

[1625] Step 5:

[1626] The server passes the data to the generative AI, which then passes the extracted information to the generative AI and requests it to generate a recipe.

[1627] Step 6:

[1628] The generative AI generates recipes based on the user's criteria. The generative AI performs the following process:

[1629] 1. Identify the user's cooking style based on their hometown and age.

[1630] 2. Generate recipes that take into account the ingredients you have in your refrigerator.

[1631] 3. Filter recipes based on the user's likes and dislikes.

[1632] Step 7:

[1633] The server formats the generated recipe. The server formats the recipe information to provide the recipe obtained from the generative AI to the user.

[1634] Step 8:

[1635] The server sends the recipe information to the user's device. The formatted recipe information is converted back to JSON format and sent to the user's device.

[1636] Step 9:

[1637] The terminal receives and displays the recipe information. The user's terminal analyzes the received recipe information and displays it on the user interface.

[1638] Step 10:

[1639] The user checks the recipe and starts cooking. The user starts cooking using the displayed recipe.

[1640] ---

[1641] These are the specific steps of the program's processing, which will give you a clearer understanding of how the system works.

[1642] Example 1

[1643] 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."

[1644] In today's busy lifestyles, it is difficult for users to find the perfect recipe based on their hometown, age, the ingredients in their refrigerator, and their preferences and dislikes. Existing recipe websites and apps require users to manually search through vast amounts of information to find the perfect recipe, which is time-consuming and laborious. Furthermore, these websites and apps do not fully consider the user's specific requirements, making it impossible to provide recipes that fully meet the user's needs. Therefore, there is a need for a system that allows users to easily and quickly find recipes that suit them.

[1645] 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.

[1646] In this invention, the server includes means for receiving condition information input by a user, means for generating a prompt sentence based on the condition information, means for generating a recipe using a generative AI model based on the prompt sentence, and means for providing the generated recipe to the user, thereby enabling the user to quickly obtain an optimal recipe based on their hometown, age, available ingredients, food preferences, and disliked ingredients.

[1647] "Means for receiving condition information entered by the user" refers to a function that allows the server to receive information such as place of origin, age, available ingredients, food preferences, and disliked ingredients entered by the user through the terminal.

[1648] "Means for generating prompt sentences" refers to a function that automatically creates sentences (prompt sentences) to give appropriate generation instructions to the generative AI model based on the received user condition information.

[1649] "Means for generating recipes using a generative AI model" refers to a function that uses AI technology to automatically generate cooking recipes that best fit the user's requirements based on the generated prompt text.

[1650] "Means for providing the generated recipe to the user" refers to the function of sending the cooking recipe provided by the generative AI model to the user's device so that the user can view it.

[1651] "Place of origin" refers to the area where the user grew up or lives, and is information that reflects the regional characteristics of the cuisine.

[1652] "Generation" refers to the user's age group, and refers to information that takes into consideration food preferences and nutritional balance according to age.

[1653] "Available ingredients" refers to ingredients currently in the user's refrigerator or kitchen, and information for efficiently using these ingredients.

[1654] "Food preferences" refers to the types of food and seasonings that a user likes, and refers to information that increases the user's satisfaction.

[1655] "Ingredients that the user dislikes" refers to ingredients that the user does not like or wants to avoid due to allergies, etc., and refers to information for generating recipes by excluding these ingredients.

[1656] System Overview

[1657] The system of the present invention automatically generates optimal cooking recipes based on user-entered condition information and provides them to the user's terminal. The system's purpose is to enable users to quickly and accurately obtain recipes that match their hometown, age, ingredients in the refrigerator, and food preferences and dislikes. The operation of the system of the present invention and specific implementation methods are described in detail below.

[1658] Hardware and Software Configuration

[1659] 1. User Device

[1660] The devices used include computers, smartphones, tablets, etc.

[1661] An interface is provided for the user to input condition information.

[1662] Examples: Windows PC, Android smartphone, iOS tablet

[1663] 2. Server

[1664] Receives and analyzes input information from the user.

[1665] A prompt sentence is generated for the generative AI, instructing it to generate a recipe.

[1666] It has the function of providing the generated recipe to the user's terminal.

[1667] Examples: Cloud servers using Amazon Web Services (AWS), Microsoft Azure

[1668] 3. Generative AI

[1669] Based on the prompt received from the server, a recipe that meets the user's requirements is generated.

[1670] Recipes are generated using advanced natural language processing technology.

[1671] Examples: OpenAI's GPT-3 model, Google's BERT model

[1672] Program processing

[1673] When a user enters condition information through an app or website, that information is sent from the device to the server. The server analyzes the received condition information and generates a prompt to pass to the generative AI. This prompt is sent to the generative AI, instructing it to generate a recipe. The generative AI generates an optimal recipe based on the prompt and returns it to the server. The server formats the generated recipe as needed and sends it to the user's device. The user can then check the recipe on their device and cook the dish based on it.

[1674] Specific operation example

[1675] 1. Enter user condition information

[1676] The user accesses the app using a device and enters the following information:

[1677] Birthplace: Tokyo

[1678] Age: 30s

[1679] Ingredients in the refrigerator: chicken, carrots, potatoes

[1680] Preferences: Easy to make dishes, I like Japanese food

[1681] Food I don't like: Celery

[1682] 2. Prompt generation

[1683] The server generates a prompt based on the information it receives, such as:

[1684] "Generate a recipe for a user in their 30s from Tokyo who has chicken, carrots, and potatoes in the fridge, who likes easy-to-make Japanese food, and who doesn't like celery."

[1685] 3. Recipe Generation

[1686] The generative AI model generates a recipe for "chicken and potatoes" based on the prompt it receives. The specific recipe is as follows:

[1687] Ingredients needed: 200g chicken, 1 carrot, 2 potatoes, soy sauce, mirin, sugar

[1688] Cooking Instructions:

[1689] 1. Cut the chicken into bite-sized pieces

[1690] 2. Cut the carrots and potatoes into chunks

[1691] 3. Add oil to a frying pan and fry the chicken.

[1692] 4. Add carrots and potatoes and stir fry

[1693] 5. Season with soy sauce, mirin, and sugar, cover, and simmer.

[1694] Duration: 30 minutes

[1695] Difficulty: Easy

[1696] 4. Providing recipes

[1697] The server receives the generated recipe and sends it to the user's terminal.

[1698] Users can check the recipe on their device and cook the food based on it.

[1699] As described above, this system allows users to easily and quickly find the optimal cooking recipe. This invention significantly reduces the effort required for users to find recipes that suit their preferences and conditions, allowing them to enjoy everyday cooking more efficiently.

[1700] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1701] Step 1:

[1702] The user enters information. Through a dedicated app or website, the user enters their hometown (e.g., Tokyo), age group (e.g., 30s), ingredients in the refrigerator (e.g., chicken, carrots, potatoes), food preferences (e.g., easy-to-make dishes, likes Japanese food), and ingredients they dislike (e.g., celery). This is the input information.

[1703] Step 2:

[1704] The terminal sends information to the server. The condition information entered by the user is sent from the terminal to the server using a secure communication protocol (e.g., HTTPS). The input data here is the condition information entered by the user, and the output data is the condition information sent to the server.

[1705] The user terminal transmits information quickly and securely.

[1706] Step 3:

[1707] The server receives and analyzes the information. The server receives the condition information sent from the terminal and analyzes this data. The input is the received condition information, and the output is the analyzed data. The analysis contents include extraction of place of origin, generation, ingredient list, preferences, and disliked ingredients.

[1708] Step 4:

[1709] The server generates and sends a prompt to the generative AI. Based on the analyzed condition information, the server generates a prompt to pass to the generative AI. The input is the analyzed condition information, and the output is the prompt. For example, a prompt might be generated that reads, "Please generate a recipe for a user in their 30s from Tokyo who has chicken, carrots, and potatoes in their refrigerator, who likes easy-to-make Japanese food, and who doesn't like celery."

[1710] Step 5:

[1711] The generative AI generates a recipe. After receiving a prompt, the generative AI generates a recipe according to the instructions. The input is the prompt, and the output is the generated recipe. Specifically, the AI ​​generates the optimal recipe from a database or existing recipe models, and creates a "chicken and potato stew" recipe as an example.

[1712] Step 6:

[1713] The server receives the generated recipe. The server receives the recipe output from the generative AI. The input is the recipe output from the generative AI, and the output is the recipe received by the server. The server formats the recipe as needed.

[1714] Step 7:

[1715] The server sends the recipe to the terminal. The formatted recipe is sent from the server to the user's terminal. The input data here is the formatted recipe, and the output data is the recipe sent to the user's terminal. The server sends the recipe securely and quickly.

[1716] Step 8:

[1717] The terminal displays the recipe to the user. The user terminal displays the recipe received from the server. The input is the recipe received from the server, and the output is the displayed recipe. The user can use the recipe displayed on the terminal as a reference to cook a dish. Specifically, the necessary ingredients and cooking steps are displayed in detail.

[1718] (Application example 1)

[1719] 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."

[1720] In modern society, many people lead busy lives, leaving them with insufficient time to cook. While there are many food delivery services available on the market, it is not easy to select a menu that matches the ingredients in your refrigerator and your preferences. Furthermore, current systems have limitations in proposing an appropriate delivery menu that takes into account each user's dietary preferences and disliked ingredients. Therefore, there is a need for a food delivery system that allows users to easily order food that matches their preferences.

[1721] 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.

[1722] In this invention, the server includes a means for receiving condition information entered by a user, a generating means for generating a recipe based on the condition information, a means for proposing a delivery menu based on the generated recipe, and a means for providing the proposed delivery menu to the user, thereby enabling the user to easily order an appropriate food delivery menu based on the ingredients in the refrigerator and their preferences.

[1723] definition statement

[1724] The "means for receiving condition information input by the user" is an interface that receives information input by the user, such as place of origin, generation, ingredients in the refrigerator, food preferences, and food dislikes.

[1725] The "generation means for generating a recipe based on the condition information" is a technical means for generating an appropriate cooking recipe based on the condition information input by the user.

[1726] "Means for proposing delivery menus based on generated recipes" refers to technical means for selecting optimal menus from affiliated food delivery services based on generated cooking recipes and proposing them to users.

[1727] "Means for providing users with suggested delivery menus" refers to a system that displays the selected and suggested delivery menus on the user's device and makes them available for ordering.

[1728] "Means for identifying cooking styles based on the user's place of origin and age" refers to technical means for extracting and identifying cooking styles appropriate for a particular region or era by utilizing the user's place of origin and age information.

[1729] MODE FOR CARRYING OUT THE INVENTION

[1730] System Overview

[1731] This system uses generative AI to generate optimal cooking recipes based on user-entered information, and then suggests and provides optimal food delivery menus based on those recipes, allowing users to easily order the optimal menu based on their preferences and the ingredients they have in their refrigerator.

[1732] System configuration

[1733] It consists of the following major hardware and software components:

[1734] 1. User Device

[1735] A device such as a smartphone, tablet, or PC that provides an interface for users to input condition information.

[1736] 2. Server

[1737] The condition information transmitted from the user terminal is received and analyzed.

[1738] It uses generative AI to generate recipes and suggests food delivery menus based on those recipes.

[1739] The proposed delivery menu is provided to the user terminal.

[1740] 3. Generative AI

[1741] Based on the condition information received from the server, a recipe is generated taking into consideration the user's hometown and age, ingredients in the refrigerator, food preferences, and food dislikes.

[1742] Based on the generated recipe, it compares it with the menus of affiliated restaurants and food delivery services to suggest the optimal delivery menu.

[1743] System operation flow

[1744] User operations

[1745] The user launches a dedicated application on their smartphone or computer and enters the following information:

[1746] Birthplace

[1747] era

[1748] Food in the refrigerator

[1749] Food preferences

[1750] Foods I don't like

[1751] Sending data and creating recipes

[1752] The server receives and analyzes the condition information sent by the user. It then passes the data to a generative AI that generates a recipe that meets the conditions. The generative AI then generates the optimal cooking recipe that matches the user's condition information.

[1753] Providing a proposed menu

[1754] Based on the generated recipe, the server selects an appropriate menu from affiliated food delivery services and sends it to the user's device. The user can then check the proposed food delivery menu on their device and place an order.

[1755] Specific examples

[1756] For example, the user enters the following criteria information:

[1757] Birthplace: Tokyo

[1758] Age: 30s

[1759] Ingredients in the refrigerator: chicken, carrots, potatoes

[1760] Preferences: Easy to make dishes, I like Japanese food

[1761] Food I don't like: Celery

[1762] The server receives these conditions and sends the following prompt to the generator AI:

[1763] Generate a cooking recipe based on the ingredients the user has in their refrigerator: chicken, carrots, potatoes; their preferences: easy-to-make dishes; they like Japanese food; and their least favorite ingredient: celery.

[1764] The generative AI uses this prompt to generate a recipe, for example, "chicken and potatoes." Based on this recipe, the system suggests delivery options for "chicken and potatoes" from affiliated Japanese restaurants. Users can check delivery options that include "chicken and potatoes" and place an order on the spot. This allows users to easily use the optimal food delivery service based on their preferences and the ingredients they have in their refrigerator.

[1765] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1766] Program processing steps

[1767] Step 1: User enters criteria information

[1768] Users launch a dedicated application on their smartphone or computer and enter their hometown, age, ingredients in the refrigerator, food preferences, and foods they dislike.

[1769] Input: User's hometown, age, ingredients in the refrigerator, food preferences and dislikes

[1770] Output: Entered condition information

[1771] Step 2: The device sends the condition information to the server

[1772] The terminal transmits the condition information input by the user to the server as a data packet.

[1773] Input: Condition information entered

[1774] Output: Data packet sent to the server

[1775] Step 3: The server receives and parses the condition information

[1776] The server receives the data packet sent from the terminal and analyzes the condition information, which precisely captures and identifies the data sent.

[1777] Input: A data packet containing the condition information entered by the user.

[1778] Output: Parsed condition information

[1779] Step 4: The server sends a prompt to the generative AI.

[1780] The server creates a prompt sentence to send to the generative AI based on the analyzed condition information. The server then sends the created prompt sentence to the generative AI.

[1781] Input: Parsed condition information

[1782] Output: Prompt sent to the generative AI

[1783] Step 5: Generative AI generates recipes

[1784] Based on the prompt received, the generative AI generates a recipe that takes into account the user's hometown, age, ingredients in the refrigerator, and food preferences and dislikes. In this process, the optimal recipe is generated based on the condition information.

[1785] Input: Prompt sent to the generative AI

[1786] Output: The generated recipe

[1787] Step 6: The server receives and parses the generated recipe

[1788] The server receives and analyzes the generated recipes sent back by the generative AI, and determines which food delivery menu items the recipes match.

[1789] Input: Generated recipe

[1790] Output: Menu suggestions adapted for restaurants and delivery services

[1791] Step 7: The server offers a delivery menu

[1792] The server compares the generated recipes with the menus of restaurants and delivery services to select the optimal delivery menu and then suggests the selected delivery menu.

[1793] Input: Generated recipes and menus from partner restaurants and delivery services

[1794] Output: Suggested delivery menu

[1795] Step 8: Your device will display a suggested delivery menu

[1796] The terminal receives the proposed delivery menu sent from the server and displays it to the user, who can then check the menu and place an order.

[1797] Input: Proposed delivery menu sent from the server

[1798] Output: Delivery menu displayed on the device

[1799] Through the above processing steps, users can easily order food delivery menus based on their preferences and the ingredients in their refrigerators.

[1800] 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.

[1801] ---

[1802] System Overview

[1803] This invention relates to a system that uses condition information entered by the user and an emotion recognition engine to provide optimal cooking recipes using generative AI. This system has the function of optimizing recipes according to the user's emotional state as well as their individual conditions. This system is composed of the user's device, a server, an emotion engine, and generative AI, and operates as follows:

[1804] System configuration

[1805] 1. User Device

[1806] This refers to devices that allow users to input information and perform emotion recognition, and includes PCs, smartphones, tablets, etc.

[1807] The user inputs information about their hometown, age, ingredients in the refrigerator, food preferences, ingredients they dislike, and emotional information.

[1808] 2. Server

[1809] The condition information and emotion information input by the user are received and analyzed.

[1810] Condition information and emotional information are passed to the generative AI, which is then instructed to generate a recipe.

[1811] 3. Emotion Engine

[1812] This is an engine that recognizes the user's emotional state based on the user's input information.

[1813] Emotion recognition includes the ability to analyze emotions from a user's facial expressions, voice, and text.

[1814] 4. Generative AI

[1815] A recipe is generated based on the condition information and emotion information received from the server.

[1816] It identifies cooking styles based on place of origin and age, takes into account ingredients in the refrigerator, and reflects the user's preferences, disliked ingredients, and emotional information.

[1817] System operation flow

[1818] User operations

[1819] 1. The user launches the app

[1820] The user uses the device to access a dedicated app or website and displays an information input screen.

[1821] 2. Input of condition information and emotion information

[1822] Users enter their hometown (e.g., Tokyo), age group (e.g., 30s), ingredients in the refrigerator (e.g., chicken, carrots, potatoes), food preferences (e.g., easy-to-make dishes, Japanese food), and ingredients they dislike (e.g., celery).

[1823] The user also inputs their own emotional information (e.g., feeling stressed or relaxed), or the emotional information is acquired using the device's camera or microphone.

[1824] Sending data and creating recipes

[1825] 3. Data transmission

[1826] The user's input information and emotion information are sent from the terminal to the server.

[1827] 4. Data Receipt and Analysis

[1828] The server analyzes the received data and extracts the necessary information (place of origin, age, ingredients, preferences, disliked ingredients, and emotional information).

[1829] 5. Instructions for creating recipes

[1830] The server passes the data to the generative AI and requests it to generate a recipe.

[1831] 6. Recipe Generation

[1832] The generative AI identifies the user's cooking style based on their hometown and age, takes into account the ingredients in the refrigerator, and generates recipes based on the user's preferences, dislikes, and emotional information.

[1833] Recipe provided

[1834] 7. Submit your recipe

[1835] The generated recipe is sent from the server to the user's terminal.

[1836] 8. Viewing Recipes

[1837] The generated recipe is displayed on the user's device, and the user can follow it to cook the dish.

[1838] Specific examples

[1839] For example, if User A (30 years old, from Tokyo) has chicken, carrots, and potatoes in the refrigerator and is feeling stressed, the following will happen:

[1840] 1. User A's input

[1841] Birthplace: Tokyo

[1842] Age: 30s

[1843] Ingredients in the refrigerator: chicken, carrots, potatoes

[1844] Preferences: Easy to make dishes, I like Japanese food

[1845] Food I don't like: Celery

[1846] Emotional information: Feeling stressed

[1847] 2. Recipe creation and display

[1848] The server passes the information to the generative AI and instructs it to generate a recipe for "chicken and potatoes," which is effective in reducing stress.

[1849] The generated recipe is sent to User A's terminal via the server.

[1850] User A checks the following recipe on his terminal:

[1851] Ingredients needed: 200g chicken, 1 carrot, 2 potatoes, soy sauce, mirin, sugar

[1852] Cooking Instructions:

[1853] 1. Cut the chicken into bite-sized pieces

[1854] 2. Cut the carrots and potatoes into chunks

[1855] 3. Add oil to a frying pan and fry the chicken.

[1856] 4. Add carrots and potatoes and stir fry

[1857] 5. Season with soy sauce, mirin, and sugar, cover, and simmer.

[1858] Duration: 30 minutes

[1859] Difficulty: Easy

[1860] In this way, User A can obtain the optimal cooking recipe that also takes into account his or her emotional state. The emotion engine makes it possible to provide suggestions that take into account the user's psychological state, allowing for the provision of a more personalized service.

[1861] ---

[1862] The processing flow will be explained below.

[1863] ---

[1864] Step 1:

[1865] The user launches the app. Using their device, the user accesses a dedicated app or website and displays the information input screen.

[1866] Step 2:

[1867] The user inputs condition information and emotional information, such as hometown, generation, ingredients in the refrigerator, food preferences, food dislikes, and emotional information (e.g., feeling stressed or relaxed).

[1868] Step 3:

[1869] The device sends input information and emotion information to the server, which converts the input information into JSON format and sends it to the server via a secure protocol.

[1870] Step 4:

[1871] The server analyzes the received JSON data and extracts necessary information (place of origin, generation, ingredients, preferences, disliked ingredients, and emotional information).

[1872] Step 5:

[1873] The server passes the data to the generative AI, which then passes the extracted information to the generative AI and requests it to generate a recipe.

[1874] Step 6:

[1875] A generative AI generates recipes based on the user's criteria and emotions. The generative AI performs the following process:

[1876] 1. Identify the user's cooking style based on their hometown and age.

[1877] 2. Generate recipes taking into account the ingredients in the user's refrigerator.

[1878] 3. Filter recipes based on the user's likes and dislikes, as well as emotional information.

[1879] For example, if a user is feeling stressed, recipes using ingredients and cooking methods that are effective in reducing stress are suggested.

[1880] Step 7:

[1881] The server formats the generated recipe. The server formats the recipe information to provide the recipe obtained from the generative AI to the user.

[1882] Step 8:

[1883] The server sends the recipe information to the user's device. The formatted recipe information is converted back to JSON format and sent to the user's device.

[1884] Step 9:

[1885] The terminal receives and displays the recipe information. The user's terminal analyzes the received recipe information and displays it on the user interface.

[1886] Step 10:

[1887] The user checks the recipe and starts cooking. The user starts cooking using the displayed recipe.

[1888] ---

[1889] These are the specific operational steps of the system's processing flow. By taking the user's emotional information into account, more personalized recipe suggestions become possible.

[1890] Example 2

[1891] 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."

[1892] Conventional recipe generation systems were able to provide recipes based on user condition information, but had limitations in providing personalized recipes that took into account the user's emotional information. Therefore, a system is needed that provides optimal recipes according to the user's emotional state and maximizes user satisfaction and relaxation effects.

[1893] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1894] In this invention, the server includes means for receiving condition information and emotion information input by the user, means for generating a recipe based on the condition information and emotion information, and means for providing the generated recipe to the user, thereby generating a recipe based on the user's emotion information and providing an optimal cooking recipe according to the user's emotional state.

[1895] "User" refers to an individual who inputs condition information and emotion information to generate a recipe.

[1896] "Condition information" refers to information such as the user's hometown, age group, ingredients they have, food preferences, and ingredients they don't like.

[1897] "Emotion information" is information that indicates the user's emotional state, such as whether the user is feeling stressed or relaxed.

[1898] "Means for receiving" refers to the function or mechanism by which the server receives the condition information and emotion information input by the user.

[1899] "Generation means" refers to the function or mechanism for generating a recipe based on the condition information and emotion information received by the server.

[1900] The "means for providing" refers to a function or mechanism for providing the recipe generated by the generation means to the user.

[1901] "Server" refers to a central control device that receives input information from users, analyzes it, creates recipes, and provides them.

[1902] System Overview

[1903] This invention is a system that receives condition information and emotion information entered by a user, generates recipes based on that information, and provides them to the user. This system has the function of optimizing recipes according to the user's individual conditions as well as their emotional state. This system consists of a user's device, a server, an emotion engine, and a generative AI.

[1904] System configuration

[1905] 1. User Device

[1906] This refers to a device that allows users to input information and perform emotion recognition, and includes general-purpose information terminals such as PCs, smartphones, and tablets. Using this, users input information such as their hometown, age, ingredients in the refrigerator, food preferences, disliked ingredients, and emotional information.

[1907] 2. Server

[1908] Its role is to receive condition and emotion information entered by the user, analyze it, and pass the results to the generative AI. This analysis is performed using hardware and software such as web servers like Nginx or Apache, and programming languages ​​like Python or Java.

[1909] 3. Emotion Engine

[1910] This engine recognizes the user's emotional state based on user input. Emotion recognition includes the ability to analyze emotions from the user's facial expressions, voice, and text. For example, OpenCV and Microsoft Azure's emotion recognition API are used.

[1911] 4. Generative AI

[1912] Recipes are generated based on condition information and emotional information received from the server. Cooking styles are identified based on place of origin and age, and ingredients in the refrigerator are considered, reflecting the user's preferences, disliked ingredients, and emotional information. Large-scale language models such as GPT-3 are used as generative AI.

[1913] Specific examples

[1914] For example, if User A (30 years old, from Tokyo) has chicken, carrots, and potatoes in his refrigerator and is feeling stressed, the system will behave as follows:

[1915] Example input from User A:

[1916] Birthplace: Tokyo

[1917] Age: 30s

[1918] Ingredients in the refrigerator: chicken, carrots, potatoes

[1919] Preferences: Easy to make dishes, I like Japanese food

[1920] Food I don't like: Celery

[1921] Emotional information: Feeling stressed

[1922] Example prompt sentence:

[1923] "Based on the criteria entered by a user in their 30s from Tokyo, please provide easy-to-make Japanese recipes using chicken, carrots, and potatoes from the refrigerator. The user is feeling stressed, so please suggest dishes that will have a relaxing effect."

[1924] Recipe generation and display:

[1925] The server passes the information to the generative AI and instructs it to generate a recipe for "chicken and potatoes," which is effective in reducing stress.

[1926] The generated recipe is sent to User A's terminal via the server.

[1927] User A checks the following recipe on his terminal:

[1928] Ingredients needed: 200g chicken, 1 carrot, 2 potatoes, soy sauce, mirin, sugar

[1929] Cooking Instructions:

[1930] 1. Cut the chicken into bite-sized pieces

[1931] 2. Cut the carrots and potatoes into chunks

[1932] 3. Add oil to a frying pan and fry the chicken.

[1933] 4. Add carrots and potatoes and stir fry

[1934] 5. Season with soy sauce, mirin, and sugar, cover, and simmer.

[1935] Duration: 30 minutes

[1936] Difficulty: Easy

[1937] In this way, User A can obtain the optimal cooking recipe that also takes into account his or her emotional state. The emotion engine makes it possible to provide suggestions that take into account the user's psychological state, allowing for the provision of a more personalized service.

[1938] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1939] Step 1:

[1940] The user enters information

[1941] Input: The user uses the terminal to input information about their hometown, age, ingredients in the refrigerator, food preferences, food dislikes, and emotional information.

[1942] Data processing and calculation: The user enters the information into the input form and presses the send button.

[1943] Output: The terminal collects the input information and prepares it for transmission.

[1944] Specific actions: The user opens an information entry screen on their device's app or website, enters information into each field, and presses the submit button.

[1945] Step 2:

[1946] Sending data

[1947] Input: Condition and emotion information entered by the user.

[1948] Data processing and calculation: The device compiles the entered information and sends it to the server using a secure communication protocol (e.g., HTTPS).

[1949] Output: The server receives the user's condition information and emotion information.

[1950] Specific operation: The terminal issues a communication request to send the user's information to the server, and the server receives it.

[1951] Step 3:

[1952] Data reception and analysis by the server

[1953] Input: Condition and emotion information sent by the user.

[1954] Data processing and calculation: The server analyzes the received data and extracts each item (place of origin, generation, ingredients, preferences, disliked ingredients, emotional information). Analysis is performed using a JSON parser and specific libraries (e.g., Python pandas).

[1955] Output: Organized user condition and emotion information.

[1956] Specific operation: The server converts the received data into the required format and analyzes it.

[1957] Step 4:

[1958] The server analyzes the emotional information using an emotion engine.

[1959] Input: Organized emotional information.

[1960] Data processing and calculation: The server passes the emotional information to an emotion engine (e.g., OpenCV or Microsoft Azure emotion recognition API) to analyze the emotional state. Specifically, text analysis, voice analysis, and image analysis are performed.

[1961] Output: Parsed emotional state (e.g. stressed, relaxed, etc.).

[1962] Specific operation: The server calls the emotion engine, analyzes the emotional state, and obtains the results.

[1963] Step 5:

[1964] The server instructs the generative AI to generate recipes.

[1965] Input: Organized condition information and analyzed emotion information.

[1966] Data processing and calculation: The server passes data as prompts to the generative AI model and instructs it to generate a recipe. Specifically, the prompts are input into a large-scale language model such as GPT-3.

[1967] Output: The generated recipe.

[1968] Specific operation: The server passes prompts such as "Tokyo," "30s," "chicken, carrots, potatoes," "easy to make dishes, Japanese food," "celery," and "feeling stressed" to the generative AI.

[1969] Step 6:

[1970] Generative AI generates recipes

[1971] Input: The prompt passed by the server.

[1972] Data processing and computation: A generative AI model generates recipes based on prompts, using natural language processing techniques.

[1973] Output: The generated recipe text.

[1974] What happens: A generative AI model (e.g., GPT-3) analyzes the prompt and generates a specific recipe based on it.

[1975] Step 7:

[1976] The server sends the generated recipe to the user's device.

[1977] Input: The generated recipe.

[1978] Data processing and calculation: The server compiles the generated recipes and sends them to the user's device.

[1979] Output: A recipe that can be displayed on the user's device.

[1980] Specific operation: The server sends the generated recipe to the user's device as an HTTP response.

[1981] Step 8:

[1982] User checks the recipe

[1983] Input: The recipe sent by the server.

[1984] Data processing and calculation: The device converts the received recipe into a display format and presents it visually to the user.

[1985] Output: A user-viewable recipe.

[1986] Specific operation: The device displays the received recipe information on the screen so that the user can check it.

[1987] (Application example 2)

[1988] 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."

[1989] Current food delivery services are unable to suggest dishes that take into account the user's emotional state, making it difficult to suggest dishes that match the user's psychological needs and situation. In addition, the lack of personalized dish suggestions based on emotions poses a challenge in increasing user satisfaction.

[1990] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving condition information and emotion information input by the user, generation means for generating a recipe based on the condition information and emotion information, and means for providing the generated recipe to the user. This makes it possible to suggest dishes personalized according to the user's emotional state.

[1991] "Condition information" is information about the user's hometown, age group, ingredients prepared in the device, food preferences, and food dislikes.

[1992] "Emotion information" is information that represents the user's emotional state, and is obtained from facial expressions, voice, text, and the like.

[1993] The "generation means" is a means for generating a recipe based on the condition information and emotion information.

[1994] A "prompt sentence" is an automatically generated sentence that makes a suggestion or a question to the user.

[1995] MODE FOR CARRYING OUT THE INVENTION

[1996] System Overview

[1997] This invention relates to a food delivery service system that provides individually optimized recipes taking into account the user's emotional state. The system uses generative AI to generate recipes based on the user's input of condition information and emotional information, and provides the recipes to the user.

[1998] System configuration

[1999] 1. User Device

[2000] A device that allows users to input information and performs emotion recognition. Specifically, this includes smartphones.

[2001] The user inputs condition information (place of origin, generation, ingredients available on the device, food preferences, and disliked ingredients) and emotional information (facial expression, voice, and text input).

[2002] 2. Server

[2003] The condition information and emotion information input by the user are received and analyzed.

[2004] Condition information and emotion information are passed to the generative AI, and it is instructed to generate a recipe.

[2005] 3. Emotion Engine

[2006] This is an engine that analyzes emotional information based on user input information.

[2007] Emotion recognition includes facial expression recognition, speech analysis, and text analysis (e.g., OpenCV, TensorFlow).

[2008] 4. Generative AI

[2009] A recipe is generated based on the condition information and emotion information received from the server.

[2010] Prompt sentences are generated according to individual conditions and suggestions are made to the user.

[2011] Example of a system

[2012] User operations

[2013] The user launches a dedicated food delivery application on their smartphone and performs the following operations.

[2014] 1. Input of condition information and emotion information

[2015] Users input their hometown, age, ingredients available on the device, food preferences, and disliked ingredients. They can also input their own emotional information or obtain it using the smartphone's camera and microphone.

[2016] Sending data and creating recipes

[2017] 2. Data transmission

[2018] The condition information and emotion information are transmitted from the user terminal to the server.

[2019] 3. Data Analysis

[2020] The server uses an emotion engine to analyze emotional information and passes the data to a generative AI to instruct it on how to generate a recipe.

[2021] Recipe provided

[2022] 4. Recipe Generation

[2023] The generative AI generates recipes and prompts that take into account the user's emotional and conditional information.

[2024] 5. Submit your recipe

[2025] The generated recipe is sent to the user's terminal via the server.

[2026] Specific examples

[2027] For example, if the user is tired (emotional information) and has chicken and potatoes as ingredients, the server will generate the following recipe based on the information received:

[2028] Example prompt sentence:

[2029] "You look tired. How about a nutritious creamed chicken and potato dish? It's easy to make and only takes 30 minutes."

[2030] As described above, personalized recipe suggestions based on emotional information are possible, which can increase user satisfaction.

[2031] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2032] Step 1:

[2033] The user launches a dedicated food delivery app on their smartphone. Through the app's UI, the user inputs condition information (place of origin, age group, ingredients prepared on the device, food preferences, and disliked ingredients). The app also uses the smartphone's camera and microphone to acquire emotional information (e.g., facial expressions and voice). Input information includes place of origin, age group, ingredients, preferences, disliked ingredients, facial expression data, and voice data. This data is then compiled into a single data packet for output.

[2034] Step 2:

[2035] Condition information and emotion information are sent from the terminal to the server. The server receives all data packets entered by the user as input. The data packets are stored in the server as output.

[2036] Step 3:

[2037] The server analyzes the emotional information using an emotion engine. The emotional information (e.g., facial expression data, voice data) stored on the server is used as input. The emotion engine (e.g., OpenCV, TensorFlow) is used to analyze the data and identify the user's emotional state (e.g., tired, stressed, relaxed). The analyzed emotional state information is generated as output.

[2038] Step 4:

[2039] The server passes condition information and emotional information to the generative AI, instructing it to generate the optimal recipe. A dataset containing analyzed emotional state information and condition information (place of origin, age, ingredients, preferences, and disliked ingredients) is used as input. The generative AI identifies the cooking style based on this information and generates a prompt. The optimal recipe and prompt are generated as output.

[2040] Step 5:

[2041] The recipe and prompt text generated by the generative AI are sent from the server to the user's device. The input includes the generated recipe and prompt text. The output is the recipe and prompt text in a format that can be displayed on the user's device.

[2042] Step 6:

[2043] The user terminal displays the received recipe and prompt text. The input includes data (recipe, prompt text) from the server. The output is displayed on the screen in a format that is easy for the user to understand, allowing the user to confirm the suggested dishes and start ordering or cooking as necessary.

[2044] Specific examples

[2045] For example, if the user is tired and has chicken and potatoes, in step 4 the generative AI will generate the following prompt and recipe:

[2046] Example prompt sentence:

[2047] "You look tired. How about a nutritious creamed chicken and potato dish? It's easy to make and only takes 30 minutes."

[2048] 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.

[2049] 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.

[2050] 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.

[2051] 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.

[2052] 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.

[2053] 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.

[2054] 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).

[2055] 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.

[2056] 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."

[2057] 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.

[2058] 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).

[2059] 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.

[2060] 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.

[2061] 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.

[2062] 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.

[2063] 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.

[2064] 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.

[2065] 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.

[2066] 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.

[2067] 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.

[2068] 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.

[2069] The following is further disclosed regarding the above embodiment.

[2070] ---

[2071] (Claim 1)

[2072] means for receiving condition information input by a user;

[2073] a generation means for generating a recipe based on the condition information;

[2074] a means for providing the generated recipe to a user;

[2075] A system including:

[2076] (Claim 2)

[2077] 2. The system according to claim 1, wherein the condition information includes the user's hometown, age group, ingredients in the refrigerator, food preferences, and food dislikes.

[2078] (Claim 3)

[2079] 2. The system of claim 1, wherein the generating means includes means for identifying a cooking style based on the user's birthplace and age.

[2080] (Claim 4)

[2081] 2. The system according to claim 1, wherein the generating means includes means for generating a recipe taking into account ingredients present in a refrigerator.

[2082] (Claim 5)

[2083] 2. The system of claim 1, wherein the generating means includes means for filtering recipes based on the user's favorite and least favorite ingredients.

[2084] (Claim 6)

[2085] 2. The system according to claim 1, wherein the providing means includes means for transmitting the generated recipe to a user terminal.

[2086] ---

[2087] This is the draft of the patent claims, which will allow you to formulate patent claims that cover each major process in the system.

[2088] "Example 1"

[2089] (Claim 1)

[2090] means for receiving condition information input by a user;

[2091] means for generating a prompt sentence based on the condition information;

[2092] means for generating a recipe using a generative AI model based on the prompt sentence;

[2093] a means for providing the generated recipe to a user;

[2094] A system including:

[2095] (Claim 2)

[2096] 2. The system according to claim 1, wherein the condition information includes the user's hometown, age group, available ingredients, food preferences, and disliked ingredients.

[2097] (Claim 3)

[2098] 2. The system of claim 1, wherein the generating means includes means for identifying a cooking style based on the user's birthplace and age.

[2099] "Application Example 1"

[2100] (Claim 1)

[2101] means for receiving condition information input by a user;

[2102] a generation means for generating a recipe based on the condition information;

[2103] A means for proposing a delivery menu based on the generated recipe;

[2104] means for providing a suggested delivery menu to a user;

[2105] A system including:

[2106] (Claim 2)

[2107] 2. The system according to claim 1, wherein the condition information includes the user's hometown, age group, ingredients in the refrigerator, food preferences, and food dislikes.

[2108] (Claim 3)

[2109] The system according to claim 1, characterized in that the generating means includes means for identifying a cooking style based on the user's place of origin and age, and for suggesting a delivery menu based on the identified cooking style.

[2110] "Example 2: Combining Emotion Engines"

[2111] (Claim 1)

[2112] means for receiving condition information and emotion information input by a user;

[2113] a generation means for generating a recipe based on the condition information and emotion information;

[2114] a means for providing the generated recipe to a user;

[2115] A system including:

[2116] (Claim 2)

[2117] 2. The system according to claim 1, wherein the condition information includes the user's hometown, age group, ingredients in stock, food preferences, and ingredients that the user dislikes.

[2118] (Claim 3)

[2119] 2. The system according to claim 1, wherein the generating means includes means for identifying a cooking style based on the user's place of origin and age, and means for analyzing emotional information.

[2120] "Application example 2 when combining emotion engines"

[2121] (Claim 1)

[2122] means for receiving condition information and emotion information input by a user;

[2123] a generation means for generating a recipe based on the condition information and emotion information;

[2124] a means for providing the generated recipe to a user;

[2125] A system including:

[2126] (Claim 2)

[2127] 2. The system according to claim 1, wherein the condition information includes the user's hometown, age group, ingredients prepared in the device, food preferences, and food dislikes.

[2128] (Claim 3)

[2129] 2. The system of claim 1, wherein the generating means includes means for identifying a cooking style based on the user's birthplace and age, and means for generating a prompt sentence. [Explanation of symbols]

[2130] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving condition information input by a user; a generation means for generating a recipe based on the condition information; a means for providing the generated recipe to a user; A system including:

2. 2. The system according to claim 1, wherein the condition information includes the user's hometown, age group, ingredients in the refrigerator, food preferences, and food dislikes.

3. 2. The system of claim 1, wherein the generating means includes means for identifying a cooking style based on the user's birthplace and age.

4. 2. The system according to claim 1, wherein the generating means includes means for generating a recipe taking into account ingredients present in a refrigerator.

5. 2. The system of claim 1, wherein the generating means includes means for filtering recipes based on the user's favorite and least favorite ingredients.

6. 2. The system according to claim 1, wherein the providing means includes means for transmitting the generated recipe to a user terminal.

Images