System

Abstract

A system is provided.SOLUTION: The system includes a means for inputting conditions of ingredients, the number of persons, seasoning, and cooking time selected by a user, a means for generating original recipe data on the basis of the conditions, a means for displaying a cooking procedure in detail on the basis of the generated original recipe, and a means for collecting feedback from the user and reflecting it on the next and subsequent recipe generation.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional recipe provision systems have had the problem of making it difficult to find an appropriate recipe that meets conditions such as ingredients, number of people, seasonings, cooking time, etc., and users have had to go to the trouble of adjusting quantities and steps themselves. Additionally, there was a lack of a mechanism for reflecting feedback after cooking in the next recipe suggestion, making it impossible to provide recipes optimized to the user's preferences. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system that includes a means for the user to input conditions such as ingredients selected by the user, number of people, seasonings, and cooking time, a means for generating original recipe data based on these conditions, a means for displaying detailed cooking procedures based on the generated original recipe, and a means for collecting feedback from the user and reflecting it in subsequent recipe generation.

[0006] This system allows users to automatically generate and obtain the optimal recipe based on their conditions, and by reflecting feedback from cooking in suggestions for future meals, it is possible to continue providing recipes that suit the user's preferences.

[0007] "User" refers to a person who uses the system to provide input and feedback.

[0008] "Ingredients" are the ingredients needed to make a dish, and are one of the elements entered by the user.

[0009] "Number of people" is an input item that indicates how many people the user wants to cook for.

[0010] "Seasoning" is an input item for specifying the flavor and seasoning of a dish, and includes salt sauce, soy sauce, miso, etc.

[0011] "Cooking time" is an input item that indicates the time required to complete the dish.

[0012] "Conditions" refer to elements required for recipe generation, such as ingredients, number of people, seasonings, and cooking time, entered by the user.

[0013] "Original recipe data" refers to new recipe information for dishes that is generated based on conditions entered by the user.

[0014] "Generation means" refers to a function within the system for constructing original recipe data based on input conditions.

[0015] "Cooking instructions" refers to a detailed explanation of the series of steps and operations required to complete a dish.

[0016] "Feedback" refers to opinions such as impressions and suggestions for improvement that users enter after completing a dish.

[0017] "Means of collection" refers to the functionality within the system for inputting, receiving, and storing feedback.

[0018] "Means for reflecting feedback in future recipe generation" refers to a function within the system that makes improvements to future recipes based on collected feedback. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] MODE FOR CARRYING OUT THE INVENTION

[0041] System Overview

[0042] This system automatically generates original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and provides detailed cooking instructions. It also collects user feedback and reflects it in future recipe generation to always provide recipes optimized to the user's preferences.

[0043] System configuration

[0044] The system is broadly composed of the following modules:

[0045] 1. User Interface (UI) Module

[0046] 2. Recipe Generation Module

[0047] 3. Procedure Assistant Module

[0048] 4. Feedback Module

[0049] Program processing

[0050] 1. User Interface (UI) Module

[0051] Users launch the application from their smartphone or PC and input the ingredients they want to use, the number of people they want to cook for, the desired seasoning, cooking time, etc. For example, if they want to cook two servings using chicken and green onions and have them seasoned with salt, they can enter that information.

[0052] 2. Recipe Generation Module

[0053] The device sends the conditions entered by the user to the server. Based on the received data, the server searches and retrieves past similar recipes and seasoning distribution data from a database, and generates an original recipe that best suits the conditions. For example, the server determines specific amounts such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)."

[0054] 3. Procedure Assistant Module

[0055] The server sends the generated recipe data to the device, which receives it and displays it to the user. When the user starts cooking based on the recipe, instructions are displayed, for example, as follows:

[0056] 1. Cut the chicken into bite-sized pieces.

[0057] 2. Cut the green onions into 1cm wide pieces.

[0058] 3. Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes.

[0059] 4. Once the chicken is cooked through, add the green onions and stir fry for a further 3 minutes.

[0060] 5. Add salt, sake, mirin, and water, and simmer for 1 minute while stirring.

[0061] 4. Feedback Module

[0062] After the user has finished cooking, they can enter their feedback about the dish (for example, "There was too much salt, so next time I'll use 0.5 teaspoons") into the app. The device sends that feedback to the server, which stores it in a database. If the same user requests a recipe with the same ingredients and conditions from now on, an improved recipe will be generated based on the feedback information.

[0063] Specific examples

[0064] As a concrete example, consider a scenario in which a user prepares a dish for two people using chicken and green onions with a salt sauce. First, the user selects "chicken" and "green onions" as ingredients in the app, and sets the conditions of two servings, salt sauce, and within 30 minutes. The device sends this information to the server, which then generates a recipe that meets the conditions. The generated recipe specifically includes "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water," which the device receives and displays to the user. The user cooks according to the instructions, and after cooking, enters feedback into the app. This feedback is used to generate future recipes.

[0065] This allows users to always receive recipes optimized to their preferences. The system eliminates the traditional hassle of searching for recipes and adjusting portions, and provides more specific and detailed cooking instructions.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] The user opens the application screen and enters the ingredients they want to use, the number of people they want to cook for, the desired seasoning, and the cooking time.

[0069] Specifically, you would make two servings using chicken and green onions, request a salty flavor, and enter "within 30 minutes."

[0070] Step 2:

[0071] The terminal receives the input data and sends it to the server.

[0072] Specifically, the data is sent to the server as an HTTP request (e.g., POST / generate-recipe).

[0073] Step 3:

[0074] The server receives the request and parses the received data.

[0075] Specifically, the conditions entered by the user are extracted and each field is identified.

[0076] Step 4:

[0077] The server searches the database to retrieve similar recipes and past cooking data.

[0078] Specifically, past recipe data that matches the conditions is obtained using an SQL query.

[0079] Step 5:

[0080] An original recipe is generated based on the data acquired by the server.

[0081] Specifically, it calculates the amount of ingredients and the distribution of seasonings, and creates an appropriate cooking procedure.

[0082] For example, it generates specific recipe data such as "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water."

[0083] Step 6:

[0084] The server transmits the generated recipe data to the terminal.

[0085] Specifically, the generated recipe information is returned as an HTTP response (e.g., 200 OK).

[0086] Step 7:

[0087] The device analyzes the received recipe data and displays it visually to the user.

[0088] Specifically, the recipe's ingredients, quantities, and cooking steps are displayed in detail on the screen.

[0089] Step 8:

[0090] The user cooks the food based on the displayed recipe.

[0091] Specifically, the user follows the steps presented to them and performs actions such as cutting ingredients, frying, and mixing seasonings.

[0092] Step 9:

[0093] The user completes the cooking and then enters feedback into the app about the cooking results and taste.

[0094] Specifically, write your impressions such as, "There was too much salt, so next time I'll use 0.5 teaspoon."

[0095] Step 10:

[0096] The terminal transmits the feedback data to the server.

[0097] Specifically, feedback is sent to the server via an HTTP request (e.g., POST / submit-feedback).

[0098] Step 11:

[0099] The server receives the feedback and stores it in a database.

[0100] Specifically, the feedback information is recorded in the database using an SQL INSERT statement.

[0101] Step 12:

[0102] The next time the user tries to generate a recipe under the same conditions, the server will optimize the generated recipe taking into account past feedback data.

[0103] Specifically, the distribution of seasonings and cooking methods will be improved based on the collected feedback.

[0104] Example 1

[0105] 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."

[0106] Conventional recipe search systems require users to adjust the exact amounts of ingredients and seasonings, and it is difficult to reflect user preferences and feedback in the next recipe. This means that users have to either repeat the same operations every time or spend time adjusting the recipe themselves. This reduces convenience and reduces user satisfaction.

[0107] 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.

[0108] In this invention, the server includes a means for a user to input conditions such as ingredients, number of people, seasonings, and cooking time, a means for using a generative AI model to generate original recipe data based on the conditions, a means for displaying detailed cooking steps based on the generated original recipe, and a means for collecting feedback from the user in the form of prompt sentences and reflecting this in subsequent recipe generation. This allows a user to simply input conditions to automatically generate an original recipe optimized to their preferences and receive detailed cooking steps, and further enables subsequent recipes to be improved based on the feedback.

[0109] "User" refers to an individual who intends to use the system to generate a recipe.

[0110] "Ingredients" refers to the ingredients that a user selects to use in a recipe.

[0111] "Number of people" refers to the number of people used to determine the amount of food the user will cook.

[0112] "Seasoning" refers to the flavor and type of seasoning the user desires for the dish.

[0113] "Cooking time" refers to the maximum cooking time desired by the user.

[0114] "Conditions" refers to the ingredients, number of people, seasonings, and cooking time input by the user.

[0115] "Original recipe data" refers to recipe information that is automatically generated based on conditions entered by the user.

[0116] "Generative AI Model" refers to an artificial intelligence model used to generate original recipe data based on conditions.

[0117] "Detailed cooking instructions" refers to specific, step-by-step cooking methods based on the original recipe data.

[0118] "Feedback" refers to the evaluation and suggestions for improvement that users provide to the system after cooking.

[0119] A "prompt sentence" refers to a sentence entered by a user that describes the requests and conditions for recipe generation.

[0120] "Database" refers to a data storage system for accumulating past similar recipes, seasoning distribution data, and user feedback data.

[0121] MODE FOR CARRYING OUT THE INVENTION

[0122] System Overview

[0123] The system of the present invention automatically generates original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and provides detailed cooking instructions. Furthermore, by collecting feedback from the user and reflecting it in future recipe generation, the system always provides recipes optimized to the user's preferences.

[0124] System configuration

[0125] This system is broadly composed of the following modules:

[0126] 1. User Interface (UI) Module

[0127] 2. Data sending and receiving module

[0128] 3. Recipe Generation Module

[0129] 4. Cooking procedure assistant module

[0130] 5. Feedback Module

[0131] User Interface (UI) Module

[0132] Users launch the application from their smartphone or PC and input the ingredients they want to use, the number of people they want to cook for, the desired seasoning, cooking time, etc. For example, if they want to cook two servings using chicken and green onions and have them seasoned with salt, they can enter that information.

[0133] Data sending and receiving modules

[0134] The device sends the conditions entered by the user to the server. The communication protocol is HTTP, and the input data is structured in JSON format. A POST request is sent to the server, and the transmitted content includes information on ingredients, number of people, seasoning, and cooking time.

[0135] Recipe Generation Module

[0136] The server analyzes the received data and searches and retrieves similar past recipes and seasoning distribution data from a database. Using a generative AI model, an original recipe that best suits the input conditions is generated. At this time, the amounts of ingredients and the distribution of seasonings are also calculated. For example, the required amounts may be determined as "200g of chicken," "1 scallion," "1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, and 50ml of water."

[0137] Cooking procedure assistant module

[0138] The server sends the generated recipe data to the device, which receives it and displays it to the user, along with detailed instructions, when the user starts cooking based on the recipe.

[0139] Feedback Module

[0140] After the user has finished cooking, they can enter their feedback on the dish into the app. For example, they can write a comment such as, "There was too much salt, so next time I'll use 0.5 teaspoons." The device sends this feedback to the server, which stores it in a database. If the same user requests a recipe with the same ingredients and conditions from now on, an improved recipe will be generated based on the feedback information.

[0141] Specific examples

[0142] As a concrete example, consider a scenario in which a user prepares a dish for two people using chicken and green onions with a salt sauce. First, the user selects "chicken" and "green onions" as ingredients in the app, and sets the conditions of two servings, salt sauce, and within 30 minutes. The device sends this information to the server, which then generates a recipe that meets the conditions. The generated recipe specifically includes "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water," which the device receives and displays to the user. The user cooks according to the instructions, and after cooking, enters feedback into the app. This feedback is used to generate future recipes.

[0143] (Example prompt)

[0144] "Generate a recipe for two servings of chicken and green onion with a salt sauce in 30 minutes or less."

[0145] Hardware and software used

[0146] The hardware used includes the devices used by users (smartphones and PCs) and the servers for processing and storing data.The software used includes front-end frameworks (e.g., React, Vue.js) for building user interfaces, back-end frameworks (e.g., Node.js, Django) for sending and receiving data, and machine learning libraries (e.g., TensorFlow, PyTorch) for running generative AI models.

[0147] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0148] Step 1: The user inputs the ingredients, number of people, seasonings, and cooking time.

[0149] The user launches the application from their smartphone or PC and inputs the ingredients they want to use (e.g., chicken, green onions), the number of people they want to cook for (e.g., two servings), the desired seasoning (e.g., salt sauce), and the cooking time (e.g., within 30 minutes). This information is structured in JSON format.

[0150] Input: Ingredients, number of people, seasoning, cooking time

[0151] Output: Input data in JSON format

[0152] Specific working example:

[0153] The user enters conditions into each input field and clicks the submit button.

[0154] Step 2: The device sends the input data to the server

[0155] The device sends the JSON format data entered by the user to the server using the HTTP POST request as the communication protocol.

[0156] Input: Input data in JSON format

[0157] Output: Data sent as an HTTP POST request

[0158] Specific working example:

[0159] The data received by the terminal is sent as the payload of the POST request.

[0160] Step 3: The server receives and parses the data

[0161] The server receives the HTTP POST request, retrieves the data sent from the payload, and analyzes it to extract the ingredients, number of people, seasoning, and cooking time.

[0162] Input: JSON format data included in the POST request

[0163] Output: Parsed condition data

[0164] Specific working example:

[0165] The server extracts JSON data from the request body and breaks it down according to conditions.

[0166] Step 4: The server searches the database and retrieves the required recipe information.

[0167] Based on the analyzed condition data, the server searches and retrieves similar past recipes and seasoning distribution data from the database.

[0168] Input: Parsed condition data

[0169] Output: Past similar recipes and seasoning distribution data

[0170] Specific working example:

[0171] The server queries the database based on ingredients, number of people, seasonings, and cooking time.

[0172] Step 5: The server generates an original recipe using the generative AI model

[0173] The server inputs the acquired data into a generative AI model to generate an original recipe that best suits the conditions. The model also calculates the amount of ingredients and the distribution of seasonings.

[0174] Input: Previously acquired similar recipes and seasoning distribution data

[0175] Output: Original recipe data

[0176] Specific working example:

[0177] The server passes the input data to the generative AI model to generate the optimal recipe.

[0178] Step 6: The server sends the original recipe data to the terminal.

[0179] The server converts the generated original recipe data into JSON format and sends it to the terminal.

[0180] Input: Original recipe data

[0181] Output: Original recipe data in JSON format

[0182] Specific working example:

[0183] The server encodes the generated recipe data and sends it to the terminal.

[0184] Step 7: The device displays the original recipe data to the user

[0185] The device analyzes the original recipe data received and displays it on the user interface. The recipe also includes detailed cooking instructions.

[0186] Input: Original recipe data in JSON format

[0187] Output: Recipe information displayed in the user interface

[0188] Specific working example:

[0189] The device analyzes the recipe data and displays it visually.

[0190] Step 8: User completes cooking and provides feedback

[0191] After the user has finished cooking, they can enter feedback into the application, for example, "There was too much salt" or "Next time I'll use 0.5 teaspoon."

[0192] Input: User feedback information

[0193] Output: Feedback data in JSON format

[0194] Specific working example:

[0195] A user enters a comment in the feedback section within the app and clicks the submit button.

[0196] Step 9: The device sends the feedback data to the server

[0197] The device sends the feedback data entered by the user to the server, which is also sent in JSON format.

[0198] Input: Feedback data in JSON format

[0199] Output: Feedback data as an HTTP POST request

[0200] Specific working example:

[0201] The feedback received by the device is sent as the payload of the POST request.

[0202] Step 10: The server receives the feedback data and stores it in a database.

[0203] The server analyzes the received feedback data and stores it in a database, which is then reflected in future recipe generation.

[0204] Input: Feedback data in JSON format included in a POST request

[0205] Output: Feedback data stored in a database

[0206] Specific working example:

[0207] The server stores the feedback in a database and uses it to generate future recipes.

[0208] (Application example 1)

[0209] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0210] Conventional recipe generation systems simply generate original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and then provide cooking instructions, which can be time-consuming when actually cooking. While there was a function to improve the recipe for future meals based on feedback, there was a lack of means to automate the cooking process, making it difficult to efficiently serve delicious food. Furthermore, in large facilities such as cafeterias and factories, the time and effort required to manually prepare meals for large numbers of people was a particular problem.

[0211] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0212] In this invention, the server includes means for inputting user-selected conditions (ingredients, number of people, seasonings, and cooking time), means for generating original recipe data based on the conditions, means for displaying detailed cooking steps based on the generated original recipe, means for collecting user feedback and reflecting it in subsequent recipe generation, and means for transmitting the original recipe data and cooking steps to an automatic cooking device, which then executes the cooking. This makes it possible to automatically cook dishes based on the generated recipe, making it possible to efficiently provide delicious dishes even in large-scale facilities.

[0213] "User" means an individual or entity that uses the system to generate recipes and prepare food.

[0214] "Ingredients" refer to the ingredients and seasonings used to make a dish.

[0215] "Number of people" refers to the number of people to whom food is being served.

[0216] "Seasoning" refers to the seasonings and cooking methods used to adjust the flavor and taste of a dish.

[0217] "Cooking time" refers to the time required to complete a dish.

[0218] "Conditions" refers collectively to the ingredients, number of people, seasonings, and cooking time selected by the user.

[0219] "Original recipe data" refers to recipe data generated based on conditions entered by the user.

[0220] "Cooking procedure" refers to the cooking steps that are specifically instructed based on the original recipe data.

[0221] "Feedback" refers to the opinions and ratings provided by users after cooking.

[0222] An "automatic cooking device" is a device that automatically cooks food based on input cooking instructions.

[0223] A "server" is a computer system that receives user input, generates recipes, displays cooking instructions, and sends instructions to the automated cooking device.

[0224] A "database" is an information storage system for accumulating past recipe data and user feedback data.

[0225] System Overview

[0226] This invention is a system that works in conjunction with an automatic cooking device to generate original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and then automatically cooks based on those recipes. It also aims to collect feedback from users and reflect it in future recipe generation, thereby always providing dishes that are optimized to the user's preferences.

[0227] System configuration

[0228] The system is broadly composed of the following modules:

[0229] 1. User Interface (UI) Module

[0230] 2. Recipe Generation Module

[0231] 3. Cooking instruction sending module

[0232] 4. Feedback Module

[0233] Program processing explanation

[0234] 1. User Interface (UI) Module

[0235] Users launch the application on their smartphone or tablet and input the ingredients they want to use, the number of people they want to cook for, the desired seasoning, cooking time, etc. For example, if they want to cook two servings of chicken and green onions and have them seasoned with salt, they can input that information in this interface.

[0236] 2. Recipe Generation Module

[0237] The device sends the conditions entered by the user to the server. Based on the received data, the server searches and retrieves past similar recipes and seasoning distribution data from a database, and generates an original recipe that best suits the conditions. For example, the server determines specific amounts such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)."

[0238] 3. Cooking instruction sending module

[0239] The server sends the generated recipe data and cooking instructions to the automatic cooking device, which then starts cooking based on the instructions. For example, the following cooking instructions may be sent:

[0240] 1. Cut the chicken into bite-sized pieces.

[0241] 2. Cut the green onions into 1cm wide pieces.

[0242] 3. Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes.

[0243] 4. Once the chicken is cooked through, add the green onions and stir fry for a further 3 minutes.

[0244] 5. Add salt, sake, mirin, and water, and simmer for 1 minute while stirring.

[0245] 4. Feedback Module

[0246] After the user has finished cooking, they can enter their feedback about the dish (for example, "There was too much salt, so next time I'll use 0.5 teaspoons") into the app. The device sends that feedback to the server, which stores it in a database. If the same user requests a recipe with the same ingredients and conditions from now on, an improved recipe will be generated based on the feedback information.

[0247] Hardware and Software

[0248] Hardware: Automated cooking equipment in factories (e.g., general-purpose cooking robots)

[0249] Software: Recipe generation API (e.g., built with Flask or Django), robot control API (API endpoints supporting HTTP requests)

[0250] Specific examples

[0251] The factory cafeteria manager uses his smartphone to enter the following:

[0252] Ingredients: Chicken, green onion

[0253] Number of people: 2 servings

[0254] Seasoning: Salt sauce

[0255] Cooking time: 30 minutes

[0256] Based on this, a request is sent to the recipe generation API, and the generated recipe is sent to the automatic cooking device. The automatic cooking device starts cooking according to the instructions, and once finished, the "stir-fried chicken and green onions with salt sauce" is served.

[0257] Prompt Sentence Examples

[0258] Ingredients: Chicken, Green onion, Serves: 2, Seasoning: Salt, Cooking time: 30 minutes. Generate the best recipe based on your criteria.

[0259] This will enable efficient and high-quality food provision even in large locations such as factories.

[0260] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0261] Step 1:

[0262] Users launch the application on their smartphone or tablet and enter information such as the ingredients they want to use, the number of people they want to cook for, the desired seasoning, and cooking time.

[0263] The conditions entered were ingredients "chicken, green onion", serving size "2 servings", seasoning "salt sauce", and cooking time "30 minutes".

[0264] The terminal converts this input data into JSON format and sends it to the server.

[0265] Step 2:

[0266] The server analyzes the received input data and, based on that, searches and retrieves past similar recipes and seasoning distribution data from a database.

[0267] The server uses popular Python libraries (e.g., Pandas, SQLAlchemy) to perform data retrieval.

[0268] The server generates original recipe data based on the search results.

[0269] For example, you would decide on specific amounts of ingredients such as "200g chicken, 1 green onion" and seasonings such as "1 teaspoon salt, 1 tablespoon sake, 1 tablespoon mirin, 50ml water."

[0270] Step 3:

[0271] The server converts the generated original recipe data and specific cooking instructions into JSON format and returns it to the terminal.

[0272] The returned data includes specific cooking instructions:

[0273] 1. Cut the chicken into bite-sized pieces.

[0274] 2. Cut the green onions into 1cm wide pieces.

[0275] 3. Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes.

[0276] 4. Once the chicken is cooked through, add the green onions and stir fry for a further 3 minutes.

[0277] 5. Add salt, sake, mirin, and water, and simmer for 1 minute while stirring.

[0278] Step 4:

[0279] The terminal transmits the received original recipe data and cooking instructions to the automatic cooking device.

[0280] This is done using an HTTP request (e.g., an HTTP POST request).

[0281] The automatic cooking device automatically starts cooking based on the transmitted cooking instructions.

[0282] Step 5:

[0283] After the user has finished cooking, they can enter their feedback on the dish into the app.

[0284] For example, you can enter a specific opinion such as, "There was too much salt, so next time I'd like to use 0.5 teaspoons."

[0285] The terminal transmits this feedback data to the server.

[0286] Step 6:

[0287] The server stores the received feedback data in a database.

[0288] From next time onwards, if the same user requests a recipe with the same ingredients and conditions, the recipe will be improved based on this feedback data.

[0289] This makes it possible to provide recipes optimized to the user's preferences.

[0290] 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.

[0291] MODE FOR CARRYING OUT THE INVENTION

[0292] System Overview

[0293] This system automatically generates original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and provides detailed cooking instructions.It also collects and analyzes user feedback and emotional data using an emotion engine, and reflects this in future recipe generation to always provide recipes optimized to the user's preferences.

[0294] System configuration

[0295] The system consists of the following modules:

[0296] 1. User Interface (UI) Module

[0297] 2. Recipe Generation Module

[0298] 3. Procedure Assistant Module

[0299] 4. Feedback Module

[0300] 5. Emotion Engine Module

[0301] Program processing

[0302] 1. User Interface (UI) Module

[0303] Users launch the application from their smartphone or PC and input the ingredients they want to use, the number of people they want to cook for, the desired seasoning, cooking time, etc. For example, if they want to cook two servings using chicken and green onions and have them seasoned with salt, they can enter that information.

[0304] 2. Recipe Generation Module

[0305] The device sends the conditions entered by the user to the server. Based on the received data, the server searches and retrieves past similar recipes and seasoning distribution data from a database, and generates an original recipe that best suits the conditions. For example, the server determines specific amounts such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)."

[0306] 3. Procedure Assistant Module

[0307] The server sends the generated recipe data to the device, which receives it and displays it to the user. When the user starts cooking based on the recipe, the following instructions are displayed:

[0308] 1. Cut the chicken into bite-sized pieces.

[0309] 2. Cut the green onions into 1cm wide pieces.

[0310] 3. Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes.

[0311] 4. Once the chicken is cooked through, add the green onions and stir fry for a further 3 minutes.

[0312] 5. Add salt, sake, mirin, and water, and simmer for 1 minute while stirring.

[0313] 4. Feedback Module

[0314] After the user has finished cooking, they can enter their feedback about the dish (for example, "There was too much salt, so next time I'll use 0.5 teaspoons") into the app. The device sends that feedback to the server, which stores it in a database. If the same user requests a recipe with the same ingredients and conditions from now on, an improved recipe will be generated based on the feedback information.

[0315] 5. Emotion Engine Module

[0316] When a user enters feedback, the emotion engine recognizes the user's emotions by analyzing the text entered by the user and facial and voice data captured using the camera and microphone. For example, it can determine whether the user is satisfied with the food or stressed.

[0317] The device sends the user's emotional data to the server, which analyzes and stores it. This data is taken into account when generating recipes from the next time onwards, and a more optimal recipe based on the user's emotions is provided. For example, if a user felt that the previous dish was spicy, a less spicy recipe will be suggested.

[0318] Specific examples

[0319] As a concrete example, consider a scenario in which a user creates a "chicken and green onion dish with salt sauce, serving two." First, the user selects "chicken" and "green onion" as ingredients in the app, and sets the conditions of two servings, salt sauce, and within 30 minutes. The device sends this information to the server, which then generates a recipe that meets the conditions. The generated recipe specifically calls for "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water," which the device receives and displays to the user.

[0320] The user cooks the food based on the displayed recipe and then enters feedback into the app after cooking. The emotion engine analyzes the user's emotions and evaluates their satisfaction with the food, along with comments such as "The amount of salt was too much, so next time I'll use 0.5 teaspoons." This feedback and emotion data are sent from the device to the server and are used to generate future recipes.

[0321] This allows users to always receive recipes optimized to their preferences and emotions, improving the quality and satisfaction of their cooking.The system eliminates the traditional hassle of searching for recipes and adjusting portion sizes, and can provide more specific and detailed cooking instructions and emotion-based recipe suggestions.

[0322] The processing flow will be explained below.

[0323] Step 1:

[0324] The user opens the application screen and enters the ingredients they want to use, the number of people they want to cook for, the desired seasoning, and the cooking time.

[0325] Specifically, you would make two servings using chicken and green onions, request a salty flavor, and enter "within 30 minutes."

[0326] Step 2:

[0327] The terminal receives the input data and sends it to the server.

[0328] Specifically, the entered data is sent to the server as an HTTP request (e.g., POST / generate-recipe).

[0329] Step 3:

[0330] The server receives the request and parses the received data.

[0331] Specifically, the conditions entered by the user are extracted and each field is identified.

[0332] Step 4:

[0333] The server searches the database to retrieve similar recipes and past cooking data.

[0334] Specifically, past recipe data that matches the conditions is obtained using an SQL query.

[0335] Step 5:

[0336] An original recipe is generated based on the data acquired by the server.

[0337] Specifically, it calculates the amount of ingredients and the distribution of seasonings, and creates an appropriate cooking procedure.

[0338] For example, it generates specific recipe data such as "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water."

[0339] Step 6:

[0340] The server transmits the generated recipe data to the terminal.

[0341] Specifically, the generated recipe information is returned as an HTTP response (e.g., 200 OK).

[0342] Step 7:

[0343] The device analyzes the received recipe data and displays it visually to the user.

[0344] Specifically, the recipe's ingredients, quantities, and cooking steps are displayed in detail on the screen.

[0345] Step 8:

[0346] The user cooks the food based on the displayed recipe.

[0347] Specifically, the user follows the steps presented to them to perform actions such as cutting ingredients, frying, and mixing seasonings.

[0348] Step 9:

[0349] The user completes the cooking and then enters feedback into the app about the cooking results and taste.

[0350] Specifically, write your impressions such as, "There was too much salt, so next time I'll use 0.5 teaspoon."

[0351] Step 10:

[0352] The emotion engine analyzes the feedback, facial expressions, and voice input from the user to obtain emotional data.

[0353] Specifically, the system uses a camera and microphone to capture changes in the user's tone of voice and facial expressions, and assigns emotional labels such as "satisfied" or "dissatisfied."

[0354] Step 11:

[0355] The terminal transmits the feedback data and the emotion data to the server.

[0356] Specifically, feedback and emotional data are sent to the server via an HTTP request (e.g., POST / submit-feedback).

[0357] Step 12:

[0358] The server receives the feedback data and emotion data and stores them in a database.

[0359] Specifically, feedback information and emotion data are recorded in a database using SQL INSERT statements.

[0360] Step 13:

[0361] The next time the user tries to generate a recipe under the same conditions, the server will optimize the generated recipe by taking into account past feedback data and emotion data.

[0362] Specifically, the system improves the distribution of seasonings and cooking methods based on the collected feedback and emotional data. For example, it analyzes the factors that led to low satisfaction in the previous meal and makes adjustments based on that.

[0363] Example 2

[0364] 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."

[0365] Modern consumers are faced with a wide variety of ingredients and cooking options, making it difficult to find recipes that best suit their tastes. Furthermore, existing systems do not fully utilize feedback and sentiment data from individual users, making it difficult to increase user satisfaction. The present invention aims to solve these problems by providing a system that suggests optimal recipes based on a user's individual preferences and feedback.

[0366] 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.

[0367] In this invention, the server includes means for inputting conditions such as ingredients, number of people, seasonings, and cooking time selected by the user, means for generating original recipe data based on the conditions, means for displaying detailed cooking procedures based on the generated original recipe, means for collecting feedback from the user and reflecting it in generating subsequent original recipes, and means for recognizing user emotional data and reflecting that data in generating original recipes. This makes it possible to provide recipes optimized for the preferences and emotional state of each individual user.

[0368] "User" refers to an individual who uses this system to create recipes and receive cooking instructions.

[0369] "Ingredients" refers to the ingredients selected by the user for cooking.

[0370] "Number of people" refers to data that indicates the amount of food the user is making and specifies how many people the food is for.

[0371] "Seasoning" refers to data indicating the flavor and type of seasoning the user desires for the dish.

[0372] "Cooking time" refers to data indicating the time it takes to complete the dish desired by the user.

[0373] "Original recipe" refers to unique recipe data generated based on input conditions.

[0374] "Means" refers to the technical configuration for realizing a specific function in this system.

[0375] "Feedback" refers to the ratings and opinions provided by users about the results of their cooking.

[0376] "Emotional data" refers to data obtained by analyzing a user's emotional state.

[0377] "Server" refers to the computer system that processes and stores data in this system.

[0378] "Terminal" refers to the device (e.g., smartphone or PC) used by a user to access the system.

[0379] "Database" refers to a storage device for storing and managing collected data.

[0380] "Generative AI model" refers to the artificial intelligence algorithm used to generate original recipes.

[0381] A "prompt" refers to a sentence or instruction input to a generative AI model.

[0382] This system automatically generates original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and provides detailed cooking instructions. Furthermore, the system collects and analyzes feedback and emotional data from users, and reflects this in future recipe generation, thereby providing recipes that are always optimized to the user's preferences.

[0383] System configuration

[0384] The system consists of the following modules:

[0385] 1. User Interface (UI) Module

[0386] 2. Recipe Generation Module

[0387] 3. Procedure Assistant Module

[0388] 4. Feedback Module

[0389] 5. Emotion Engine Module

[0390] Hardware and Software

[0391] The hardware used includes user devices such as smartphones and PCs, as well as servers, while the software used includes applications that provide a user interface, database software, and machine learning libraries for running generative AI models.

[0392] Program processing

[0393] The program processing in this system is as follows:

[0394] 1. User Interface (UI) Module

[0395] Users launch the application from their smartphone or PC and input the ingredients they want to use, the number of people they want to cook for, the desired seasoning, cooking time, etc. For example, they can use "chicken" and "green onions" to cook "two servings," request "salt sauce," and set the cooking time to "within 30 minutes."

[0396] 2. Recipe Generation Module

[0397] The device sends the conditions entered by the user to the server. Based on the received data, the server searches and retrieves similar past recipes and seasoning distribution data from a database, and uses a generative AI model to generate an original recipe that best suits the conditions. For example, the server determines specific amounts such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)."

[0398] 3. Procedure Assistant Module

[0399] The server sends the generated recipe data to the device, which receives it and displays it to the user. When the user starts cooking based on the recipe, the following instructions are displayed:

[0400] 1. Cut the chicken into bite-sized pieces.

[0401] 2. Cut the green onions into 1cm wide pieces.

[0402] 3. Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes.

[0403] 4. Once the chicken is cooked through, add the green onions and stir fry for a further 3 minutes.

[0404] 5. Add salt, sake, mirin, and water, and simmer for 1 minute while stirring.

[0405] 4. Feedback Module

[0406] After the user has finished cooking, they can enter feedback about the dish into the app. For example, they can enter feedback such as, "There was too much salt, so next time I'll use 0.5 teaspoons."

[0407] 5. Emotion Engine Module

[0408] When a user enters feedback, the emotion engine recognizes the user's emotions by analyzing the text entered by the user and facial and voice data captured using the camera and microphone. For example, it can determine whether the user is satisfied with the food or stressed.

[0409] Specific examples

[0410] As a concrete example, consider a scenario in which a user makes a dish for two people using chicken and green onions with a salt sauce. The user selects "chicken" and "green onions" as ingredients in the app and sets the conditions of two servings, salt sauce, and within 30 minutes. The device sends this information to the server, which then generates a recipe that meets the conditions. The generated recipe consists of "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water," which the device receives and displays to the user. The user cooks the food based on the displayed recipe and enters feedback into the app after cooking. At this time, the emotion engine analyzes the user's emotions and evaluates the user's level of satisfaction, along with comments such as "The amount of salt was too much, so next time I'll use 0.5 teaspoons." This feedback and emotion data are sent from the device to the server and used to generate future recipes.

[0411] Prompt Sentence Examples

[0412] An example of a prompt to input to a generative AI model is as follows:

[0413] You are in charge of programming a cooking recipe generation system. Your task is to automatically generate the optimal recipe for a user to make "Chicken and green onion dish with salt sauce, for two people." You must provide specific ingredients and steps, and take into account the user's past feedback and sentiment data.

[0414] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0415] Step 1:

[0416] The user interface (UI) module allows users to launch the application from their smartphone or PC. Users input conditions such as the ingredients they want to use, the number of people they want to cook for, the desired seasoning, and cooking time. For example, a user might select "chicken" and "green onions" as ingredients, cook "two servings," request "salt sauce," and set the cooking time to "within 30 minutes."

[0417] Input: The user enters the condition.

[0418] Output: The format in which the input data is formatted and sent to the server (e.g. JSON data).

[0419] Step 2:

[0420] The device sends the conditions entered by the user to the server. The sent data is accurately passed to the server in JSON format, etc.

[0421] Input: Data entered by the user.

[0422] Output: The formatted data that is sent to the server.

[0423] Specific operation: Press the "Send" button on the terminal. When the "Send" button is pressed, the input data is validated. Data that passes validation is sent to the server.

[0424] Step 3:

[0425] Based on the data received by the server, the database is searched for and retrieved from the server similar recipes and seasoning distribution data from the past. This data is then used by a generative AI model to generate an original recipe that best suits the conditions.

[0426] Input: Formatted condition data.

[0427] Output: The generated original recipe data.

[0428] Specific operations: The server analyzes the received data, searches for related data from the database to retrieve similar recipes, and uses a generative AI model to create the optimal recipe.

[0429] Step 4:

[0430] The server transmits the generated recipe data to the terminal, which receives it and displays it to the user.

[0431] Input: Generated original recipe data.

[0432] Output: Recipe information displayed to the user.

[0433] Specific operation: The server sends the generated recipe data in JSON format. The device receives the recipe data and displays it on the interface. The recipe includes specific ingredient amounts and cooking instructions.

[0434] Step 5:

[0435] The user starts cooking based on the displayed recipe, and the step-by-step instructions are provided by the step-by-step assistant module.

[0436] Input: User confirms cooking instructions.

[0437] Output: Specific instructions for the user to proceed with the cooking.

[0438] How it works: Each cooking step is displayed on the recipe screen. The user proceeds with the cooking process while checking each step. The screen is updated as the cooking process progresses.

[0439] Step 6:

[0440] After the user has finished cooking, they can enter their feedback on the dish into the app, such as "I added too much salt, so next time I'll use 0.5 teaspoons."

[0441] Input: Post-cooking feedback.

[0442] Output: Formatted feedback data.

[0443] Specific operation: After cooking is complete, the user enters comments on the feedback screen that appears, and inputs emotional data (such as satisfaction and stress levels).

[0444] Step 7:

[0445] The device sends feedback to the server, which stores the feedback data in a database and uses it to generate future recipes.

[0446] Input: Formatted feedback data.

[0447] Output: Feedback data stored in a database.

[0448] Specific operation: Press the feedback sending button. Feedback and emotion data will be sent together.

[0449] Step 8:

[0450] The server uses an emotion engine to analyze and store the user's emotion data. The analysis results are taken into account when generating recipes from the next time onwards.

[0451] Input: Feedback data and emotion data.

[0452] Output: Parsed emotion data.

[0453] Specific operation: The server analyzes the received emotion data. The emotion engine evaluates the satisfaction and stress levels. The evaluation results are stored in a database.

[0454] (Application example 2)

[0455] 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."

[0456] Conventional recipe generation systems simply generate recipes based on ingredients and seasoning conditions, and are unable to fully reflect users' specific emotions and feedback. This has led to a demand for systems that can provide recipes that fully satisfy users. Furthermore, the lack of an efficient recipe generation and cooking instruction system that can be used in brick-and-mortar establishments such as restaurants has made it difficult to develop new dishes and streamline kitchen operations.

[0457] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0458] In this invention, the server includes a means for inputting user-selected conditions such as ingredients, number of people, seasonings, and cooking time, a means for generating original recipe data based on the conditions, a means for displaying detailed cooking steps based on the generated original recipe, a means for collecting user feedback and reflecting the feedback in subsequent recipe generation, and a means for analyzing user emotion data and optimizing the recipe based on the user's emotion. This makes it possible to provide optimized recipes that reflect the user's emotion and feedback. This can also contribute to the development of new dishes in restaurants and the efficiency of kitchen operations.

[0459] "Ingredients, number of people, seasoning, and cooking time" are items that the user selects when creating a recipe, and the combination of these is an important factor in determining the specific recipe.

[0460] "Original recipe data" refers to recipe data that the system automatically generates based on conditions specified by the user, and may also be generated based on past recipe data or seasoning distribution data.

[0461] The "means for displaying detailed cooking steps" is a function for displaying specific and detailed steps for the user to actually prepare a dish based on the generated original recipe.

[0462] "Means of collecting feedback and reflecting it in future recipe generation" refers to a function that allows users to input their impressions and suggestions for improvement after actually cooking into the system, which then stores them in a database for use when generating the next recipe.

[0463] "Means for analyzing emotional data and optimizing recipes based on the user's emotions" refers to a function that allows the emotion engine to recognize and analyze the user's emotions when they enter feedback, and then use that data to optimize future recipe suggestions.

[0464] A "restaurant" is a place where users can eat, and is a general concept that encompasses store formats such as restaurants and cafes.

[0465] This invention is a system that automatically generates original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and provides detailed cooking instructions. This system consists of five main modules: a user interface (UI) module, a recipe generation module, a step assistant module, a feedback module, and an emotion engine module.

[0466] 1. User Interface (UI) Module

[0467] It is a means for users to launch an application on their smartphone or tablet device and input conditions such as ingredients, number of people, seasoning, cooking time, etc. For example, when a restaurant chef creates a new dish, if he or she wants to use "chicken" and "green onion" to make "two servings" and "salt sauce" and wants it to be "salted," the function is provided to input this information.

[0468] 2. Recipe Generation Module

[0469] The terminal sends the conditions entered by the user to the server. Based on the received data, the server searches and retrieves similar past recipes and seasoning distribution data from a database, and generates an original recipe that best suits the conditions. For example, the server determines specific amounts such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)." Backend processing using Python and Flask is performed during this process.

[0470] 3. Procedure Assistant Module

[0471] The server sends the generated recipe data to the device, which receives it and displays it to the user. When the user starts cooking based on the recipe, detailed cooking instructions are displayed in real time. Specifically, instructions such as "Cut the chicken into bite-sized pieces," "Cut the green onions into 1cm pieces," "Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes," "Once the chicken is cooked through, add the green onions and fry for another 3 minutes," and "Add salt, sake, mirin, and water, and simmer for 1 minute while mixing everything together" are displayed.

[0472] 4. Feedback Module

[0473] After the user has finished cooking, they can enter their feedback on the dish from their device and send it to the server. For example, they can provide feedback such as, "I added too much salt, so next time I'll use 0.5 teaspoons." The server stores this feedback in a database and uses it to generate future recipes.

[0474] 5. Emotion Engine Module

[0475] When a user enters feedback, the emotion engine recognizes and analyzes the user's emotions. This emotion recognition is performed by analyzing the text entered by the user and facial expressions and voice data acquired using a camera or microphone. The server analyzes and saves the user's emotion data, and takes this into consideration when generating recipes from the next time onwards, allowing it to provide more optimal recipes based on the user's emotions.

[0476] Specific examples

[0477] A restaurant chef opens an application to create a new dish and enters the following criteria:

[0478] Ingredients: chicken, green onion

[0479] Number of people: 2 servings

[0480] Seasoning: Salt sauce

[0481] Cooking time: 30 minutes

[0482] The system generates a recipe based on this information and displays cooking instructions. After the chef has finished cooking, they can enter their feedback, which is then analyzed by the emotion engine. This data is then used to generate future recipes.

[0483] Prompt Sentence Examples

[0484] A chef is looking for a recipe for a new dish. Generate a recipe based on the following criteria and provide detailed cooking instructions:

[0485] Ingredients: chicken, green onion

[0486] Number of people: 2 servings

[0487] Seasoning: Salt sauce

[0488] Cooking time: 30 minutes

[0489] In addition, feedback and emotional data after cooking is completed will be taken into consideration and reflected in future recipe suggestions.

[0490] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0491] Step 1:

[0492] Users launch the application on their smartphone or tablet and input the ingredients, number of people, seasoning, cooking time, etc. Specifically, a restaurant chef would input the following conditions: "chicken," "green onion," "serves two," "salt sauce," and "30 minutes."

[0493] Input: ingredients, number of people, seasoning, cooking time

[0494] Output: Condition data

[0495] Step 2:

[0496] The device sends the entered condition data to the server. Based on the received data, the server searches and retrieves past similar recipes and seasoning distribution data from a database, and generates an original recipe that best suits the conditions. Specifically, the server determines the specific amounts of ingredients, such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)."

[0497] Input: Condition data

[0498] Data processing: database search, retrieval of similar recipes, generation of original recipes

[0499] Output: Generated recipe data

[0500] Step 3:

[0501] The server sends the generated recipe data to the device, which receives it and displays it to the user. The user then begins cooking based on the displayed recipe data. Specific instructions are displayed, such as "Cut the chicken into bite-sized pieces," "Cut the green onions into 1cm pieces," and "Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes."

[0502] Input: Generated recipe data

[0503] Data processing: None

[0504] Output: Display of cooking instructions

[0505] Step 4:

[0506] After the user has finished cooking, they can input their feedback about the dish and send it to the server from their device. For example, they might say, "I added too much salt, so next time I'll use 0.5 teaspoons." The server stores this feedback in a database and uses it to generate future recipes.

[0507] Input: User feedback

[0508] Data processing: Accumulation in the database, reflection in next recipe generation

[0509] Output: Accumulated feedback data

[0510] Step 5:

[0511] When a user enters feedback, the emotion engine recognizes and analyzes the user's emotions. It analyzes facial expressions and voice data captured using a camera and microphone to determine whether the user is satisfied with the cooking or stressed. The server analyzes and saves the emotion data and takes it into consideration when generating recipes in the future.

[0512] Input: Feedback text, facial expression data, voice data

[0513] Data processing: text analysis, facial expression and voice analysis, emotion data generation

[0514] Output: Parsed emotion data

[0515] Step 6:

[0516] The server uses the accumulated feedback data and analyzed emotion data and takes this information into account when generating new recipes, so that future recipes will be further optimized based on the user's emotions and feedback.

[0517] Input: Accumulated feedback data, analyzed emotion data

[0518] Data processing: Integrating feedback and sentiment data and reflecting it in recipe generation

[0519] Output: New optimized recipe data

[0520] 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.

[0521] 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.

[0522] 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.

[0523] [Second embodiment]

[0524] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0525] 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.

[0526] 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).

[0527] 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.

[0528] 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.

[0529] 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).

[0530] 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.

[0531] 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.

[0532] 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.

[0533] 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.

[0534] 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.

[0535] 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."

[0536] MODE FOR CARRYING OUT THE INVENTION

[0537] System Overview

[0538] This system automatically generates original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and provides detailed cooking instructions. It also collects user feedback and reflects it in future recipe generation to always provide recipes optimized to the user's preferences.

[0539] System configuration

[0540] The system is broadly composed of the following modules:

[0541] 1. User Interface (UI) Module

[0542] 2. Recipe Generation Module

[0543] 3. Procedure Assistant Module

[0544] 4. Feedback Module

[0545] Program processing

[0546] 1. User Interface (UI) Module

[0547] Users launch the application from their smartphone or PC and input the ingredients they want to use, the number of people they want to cook for, the desired seasoning, cooking time, etc. For example, if they want to cook two servings using chicken and green onions and have them seasoned with salt, they can enter that information.

[0548] 2. Recipe Generation Module

[0549] The device sends the conditions entered by the user to the server. Based on the received data, the server searches and retrieves past similar recipes and seasoning distribution data from a database, and generates an original recipe that best suits the conditions. For example, the server determines specific amounts such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)."

[0550] 3. Procedure Assistant Module

[0551] The server sends the generated recipe data to the device, which receives it and displays it to the user. When the user starts cooking based on the recipe, instructions are displayed, for example, as follows:

[0552] 1. Cut the chicken into bite-sized pieces.

[0553] 2. Cut the green onions into 1cm wide pieces.

[0554] 3. Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes.

[0555] 4. Once the chicken is cooked through, add the green onions and stir fry for a further 3 minutes.

[0556] 5. Add salt, sake, mirin, and water, and simmer for 1 minute while stirring.

[0557] 4. Feedback Module

[0558] After the user has finished cooking, they can enter their feedback about the dish (for example, "There was too much salt, so next time I'll use 0.5 teaspoons") into the app. The device sends that feedback to the server, which stores it in a database. If the same user requests a recipe with the same ingredients and conditions from now on, an improved recipe will be generated based on the feedback information.

[0559] Specific examples

[0560] As a concrete example, consider a scenario in which a user prepares a dish for two people using chicken and green onions with a salt sauce. First, the user selects "chicken" and "green onions" as ingredients in the app, and sets the conditions of two servings, salt sauce, and within 30 minutes. The device sends this information to the server, which then generates a recipe that meets the conditions. The generated recipe specifically includes "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water," which the device receives and displays to the user. The user cooks according to the instructions, and after cooking, enters feedback into the app. This feedback is used to generate future recipes.

[0561] This allows users to always receive recipes optimized to their preferences. The system eliminates the traditional hassle of searching for recipes and adjusting portions, and provides more specific and detailed cooking instructions.

[0562] The processing flow will be explained below.

[0563] Step 1:

[0564] The user opens the application screen and enters the ingredients they want to use, the number of people they want to cook for, the desired seasoning, and the cooking time.

[0565] Specifically, you would make two servings using chicken and green onions, request a salty flavor, and enter "within 30 minutes."

[0566] Step 2:

[0567] The terminal receives the input data and sends it to the server.

[0568] Specifically, the data is sent to the server as an HTTP request (e.g., POST / generate-recipe).

[0569] Step 3:

[0570] The server receives the request and parses the received data.

[0571] Specifically, the conditions entered by the user are extracted and each field is identified.

[0572] Step 4:

[0573] The server searches the database to retrieve similar recipes and past cooking data.

[0574] Specifically, past recipe data that matches the conditions is obtained using an SQL query.

[0575] Step 5:

[0576] An original recipe is generated based on the data acquired by the server.

[0577] Specifically, it calculates the amount of ingredients and the distribution of seasonings, and creates an appropriate cooking procedure.

[0578] For example, it generates specific recipe data such as "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water."

[0579] Step 6:

[0580] The server transmits the generated recipe data to the terminal.

[0581] Specifically, the generated recipe information is returned as an HTTP response (e.g., 200 OK).

[0582] Step 7:

[0583] The device analyzes the received recipe data and displays it visually to the user.

[0584] Specifically, the recipe's ingredients, quantities, and cooking steps are displayed in detail on the screen.

[0585] Step 8:

[0586] The user cooks the food based on the displayed recipe.

[0587] Specifically, the user follows the steps presented to them and performs actions such as cutting ingredients, frying, and mixing seasonings.

[0588] Step 9:

[0589] The user completes the cooking and then enters feedback into the app about the cooking results and taste.

[0590] Specifically, write your impressions such as, "There was too much salt, so next time I'll use 0.5 teaspoon."

[0591] Step 10:

[0592] The terminal transmits the feedback data to the server.

[0593] Specifically, feedback is sent to the server via an HTTP request (e.g., POST / submit-feedback).

[0594] Step 11:

[0595] The server receives the feedback and stores it in a database.

[0596] Specifically, the feedback information is recorded in the database using an SQL INSERT statement.

[0597] Step 12:

[0598] The next time the user tries to generate a recipe under the same conditions, the server will optimize the generated recipe taking into account past feedback data.

[0599] Specifically, the distribution of seasonings and cooking methods will be improved based on the collected feedback.

[0600] Example 1

[0601] 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."

[0602] Conventional recipe search systems require users to adjust the exact amounts of ingredients and seasonings, and it is difficult to reflect user preferences and feedback in the next recipe. This means that users have to either repeat the same operations every time or spend time adjusting the recipe themselves. This reduces convenience and reduces user satisfaction.

[0603] 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.

[0604] In this invention, the server includes a means for a user to input conditions such as ingredients, number of people, seasonings, and cooking time, a means for using a generative AI model to generate original recipe data based on the conditions, a means for displaying detailed cooking steps based on the generated original recipe, and a means for collecting feedback from the user in the form of prompt sentences and reflecting this in subsequent recipe generation. This allows a user to simply input conditions to automatically generate an original recipe optimized to their preferences and receive detailed cooking steps, and further enables subsequent recipes to be improved based on the feedback.

[0605] "User" refers to an individual who intends to use the system to generate a recipe.

[0606] "Ingredients" refers to the ingredients that a user selects to use in a recipe.

[0607] "Number of people" refers to the number of people used to determine the amount of food the user will cook.

[0608] "Seasoning" refers to the flavor and type of seasoning the user desires for the dish.

[0609] "Cooking time" refers to the maximum cooking time desired by the user.

[0610] "Conditions" refers to the ingredients, number of people, seasonings, and cooking time input by the user.

[0611] "Original recipe data" refers to recipe information that is automatically generated based on conditions entered by the user.

[0612] "Generative AI Model" refers to an artificial intelligence model used to generate original recipe data based on conditions.

[0613] "Detailed cooking instructions" refers to specific, step-by-step cooking methods based on the original recipe data.

[0614] "Feedback" refers to the evaluation and suggestions for improvement that users provide to the system after cooking.

[0615] A "prompt sentence" refers to a sentence entered by a user that describes the requests and conditions for recipe generation.

[0616] "Database" refers to a data storage system for accumulating past similar recipes, seasoning distribution data, and user feedback data.

[0617] MODE FOR CARRYING OUT THE INVENTION

[0618] System Overview

[0619] The system of the present invention automatically generates original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and provides detailed cooking instructions. Furthermore, by collecting feedback from the user and reflecting it in future recipe generation, the system always provides recipes optimized to the user's preferences.

[0620] System configuration

[0621] This system is broadly composed of the following modules:

[0622] 1. User Interface (UI) Module

[0623] 2. Data sending and receiving module

[0624] 3. Recipe Generation Module

[0625] 4. Cooking procedure assistant module

[0626] 5. Feedback Module

[0627] User Interface (UI) Module

[0628] Users launch the application from their smartphone or PC and input the ingredients they want to use, the number of people they want to cook for, the desired seasoning, cooking time, etc. For example, if they want to cook two servings using chicken and green onions and have them seasoned with salt, they can enter that information.

[0629] Data sending and receiving modules

[0630] The device sends the conditions entered by the user to the server. The communication protocol is HTTP, and the input data is structured in JSON format. A POST request is sent to the server, and the transmitted content includes information on ingredients, number of people, seasoning, and cooking time.

[0631] Recipe Generation Module

[0632] The server analyzes the received data and searches and retrieves similar past recipes and seasoning distribution data from a database. Using a generative AI model, an original recipe that best suits the input conditions is generated. At this time, the amounts of ingredients and the distribution of seasonings are also calculated. For example, the required amounts may be determined as "200g of chicken," "1 scallion," "1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, and 50ml of water."

[0633] Cooking procedure assistant module

[0634] The server sends the generated recipe data to the device, which receives it and displays it to the user, along with detailed instructions, when the user starts cooking based on the recipe.

[0635] Feedback Module

[0636] After the user has finished cooking, they can enter their feedback on the dish into the app. For example, they can write a comment such as, "There was too much salt, so next time I'll use 0.5 teaspoons." The device sends this feedback to the server, which stores it in a database. If the same user requests a recipe with the same ingredients and conditions from now on, an improved recipe will be generated based on the feedback information.

[0637] Specific examples

[0638] As a concrete example, consider a scenario in which a user prepares a dish for two people using chicken and green onions with a salt sauce. First, the user selects "chicken" and "green onions" as ingredients in the app, and sets the conditions of two servings, salt sauce, and within 30 minutes. The device sends this information to the server, which then generates a recipe that meets the conditions. The generated recipe specifically includes "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water," which the device receives and displays to the user. The user cooks according to the instructions, and after cooking, enters feedback into the app. This feedback is used to generate future recipes.

[0639] (Example prompt)

[0640] "Generate a recipe for two servings of chicken and green onion with a salt sauce in 30 minutes or less."

[0641] Hardware and software used

[0642] The hardware used includes the devices used by users (smartphones and PCs) and the servers for processing and storing data.The software used includes front-end frameworks (e.g., React, Vue.js) for building user interfaces, back-end frameworks (e.g., Node.js, Django) for sending and receiving data, and machine learning libraries (e.g., TensorFlow, PyTorch) for running generative AI models.

[0643] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0644] Step 1: The user inputs the ingredients, number of people, seasonings, and cooking time.

[0645] The user launches the application from their smartphone or PC and inputs the ingredients they want to use (e.g., chicken, green onions), the number of people they want to cook for (e.g., two servings), the desired seasoning (e.g., salt sauce), and the cooking time (e.g., within 30 minutes). This information is structured in JSON format.

[0646] Input: Ingredients, number of people, seasoning, cooking time

[0647] Output: Input data in JSON format

[0648] Specific working example:

[0649] The user enters conditions into each input field and clicks the submit button.

[0650] Step 2: The device sends the input data to the server

[0651] The device sends the JSON format data entered by the user to the server using the HTTP POST request as the communication protocol.

[0652] Input: Input data in JSON format

[0653] Output: Data sent as an HTTP POST request

[0654] Specific working example:

[0655] The data received by the terminal is sent as the payload of the POST request.

[0656] Step 3: The server receives and parses the data

[0657] The server receives the HTTP POST request, retrieves the data sent from the payload, and analyzes it to extract the ingredients, number of people, seasoning, and cooking time.

[0658] Input: JSON format data included in the POST request

[0659] Output: Parsed condition data

[0660] Specific working example:

[0661] The server extracts JSON data from the request body and breaks it down according to conditions.

[0662] Step 4: The server searches the database and retrieves the required recipe information.

[0663] Based on the analyzed condition data, the server searches and retrieves similar past recipes and seasoning distribution data from the database.

[0664] Input: Parsed condition data

[0665] Output: Past similar recipes and seasoning distribution data

[0666] Specific working example:

[0667] The server queries the database based on ingredients, number of people, seasonings, and cooking time.

[0668] Step 5: The server generates an original recipe using the generative AI model

[0669] The server inputs the acquired data into a generative AI model to generate an original recipe that best suits the conditions. The model also calculates the amount of ingredients and the distribution of seasonings.

[0670] Input: Previously acquired similar recipes and seasoning distribution data

[0671] Output: Original recipe data

[0672] Specific working example:

[0673] The server passes the input data to the generative AI model to generate the optimal recipe.

[0674] Step 6: The server sends the original recipe data to the terminal.

[0675] The server converts the generated original recipe data into JSON format and sends it to the terminal.

[0676] Input: Original recipe data

[0677] Output: Original recipe data in JSON format

[0678] Specific working example:

[0679] The server encodes the generated recipe data and sends it to the terminal.

[0680] Step 7: The device displays the original recipe data to the user

[0681] The device analyzes the original recipe data received and displays it on the user interface. The recipe also includes detailed cooking instructions.

[0682] Input: Original recipe data in JSON format

[0683] Output: Recipe information displayed in the user interface

[0684] Specific working example:

[0685] The device analyzes the recipe data and displays it visually.

[0686] Step 8: User completes cooking and provides feedback

[0687] After the user has finished cooking, they can enter feedback into the application, for example, "There was too much salt" or "Next time I'll use 0.5 teaspoon."

[0688] Input: User feedback information

[0689] Output: Feedback data in JSON format

[0690] Specific working example:

[0691] A user enters a comment in the feedback section within the app and clicks the submit button.

[0692] Step 9: The device sends the feedback data to the server

[0693] The device sends the feedback data entered by the user to the server, which is also sent in JSON format.

[0694] Input: Feedback data in JSON format

[0695] Output: Feedback data as an HTTP POST request

[0696] Specific working example:

[0697] The feedback received by the device is sent as the payload of the POST request.

[0698] Step 10: The server receives the feedback data and stores it in a database.

[0699] The server analyzes the received feedback data and stores it in a database, which is then reflected in future recipe generation.

[0700] Input: Feedback data in JSON format included in a POST request

[0701] Output: Feedback data stored in a database

[0702] Specific working example:

[0703] The server stores the feedback in a database and uses it to generate future recipes.

[0704] (Application example 1)

[0705] 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."

[0706] Conventional recipe generation systems simply generate original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and then provide cooking instructions, which can be time-consuming when actually cooking. While there was a function to improve the recipe for future meals based on feedback, there was a lack of means to automate the cooking process, making it difficult to efficiently serve delicious food. Furthermore, in large facilities such as cafeterias and factories, the time and effort required to manually prepare meals for large numbers of people was a particular problem.

[0707] 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.

[0708] In this invention, the server includes means for inputting user-selected conditions (ingredients, number of people, seasonings, and cooking time), means for generating original recipe data based on the conditions, means for displaying detailed cooking steps based on the generated original recipe, means for collecting user feedback and reflecting it in subsequent recipe generation, and means for transmitting the original recipe data and cooking steps to an automatic cooking device, which then executes the cooking. This makes it possible to automatically cook dishes based on the generated recipe, making it possible to efficiently provide delicious dishes even in large-scale facilities.

[0709] "User" means an individual or entity that uses the system to generate recipes and prepare food.

[0710] "Ingredients" refer to the ingredients and seasonings used to make a dish.

[0711] "Number of people" refers to the number of people to whom food is being served.

[0712] "Seasoning" refers to the seasonings and cooking methods used to adjust the flavor and taste of a dish.

[0713] "Cooking time" refers to the time required to complete a dish.

[0714] "Conditions" refers collectively to the ingredients, number of people, seasonings, and cooking time selected by the user.

[0715] "Original recipe data" refers to recipe data generated based on conditions entered by the user.

[0716] "Cooking procedure" refers to the cooking steps that are specifically instructed based on the original recipe data.

[0717] "Feedback" refers to the opinions and ratings provided by users after cooking.

[0718] An "automatic cooking device" is a device that automatically cooks food based on input cooking instructions.

[0719] A "server" is a computer system that receives user input, generates recipes, displays cooking instructions, and sends instructions to the automated cooking device.

[0720] A "database" is an information storage system for accumulating past recipe data and user feedback data.

[0721] System Overview

[0722] This invention is a system that works in conjunction with an automatic cooking device to generate original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and then automatically cooks based on those recipes. It also aims to collect feedback from users and reflect it in future recipe generation, thereby always providing dishes that are optimized to the user's preferences.

[0723] System configuration

[0724] The system is broadly composed of the following modules:

[0725] 1. User Interface (UI) Module

[0726] 2. Recipe Generation Module

[0727] 3. Cooking instruction sending module

[0728] 4. Feedback Module

[0729] Program processing explanation

[0730] 1. User Interface (UI) Module

[0731] Users launch the application on their smartphone or tablet and input the ingredients they want to use, the number of people they want to cook for, the desired seasoning, cooking time, etc. For example, if they want to cook two servings of chicken and green onions and have them seasoned with salt, they can input that information in this interface.

[0732] 2. Recipe Generation Module

[0733] The device sends the conditions entered by the user to the server. Based on the received data, the server searches and retrieves past similar recipes and seasoning distribution data from a database, and generates an original recipe that best suits the conditions. For example, the server determines specific amounts such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)."

[0734] 3. Cooking instruction sending module

[0735] The server sends the generated recipe data and cooking instructions to the automatic cooking device, which then starts cooking based on the instructions. For example, the following cooking instructions may be sent:

[0736] 1. Cut the chicken into bite-sized pieces.

[0737] 2. Cut the green onions into 1cm wide pieces.

[0738] 3. Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes.

[0739] 4. Once the chicken is cooked through, add the green onions and stir fry for a further 3 minutes.

[0740] 5. Add salt, sake, mirin, and water, and simmer for 1 minute while stirring.

[0741] 4. Feedback Module

[0742] After the user has finished cooking, they can enter their feedback about the dish (for example, "There was too much salt, so next time I'll use 0.5 teaspoons") into the app. The device sends that feedback to the server, which stores it in a database. If the same user requests a recipe with the same ingredients and conditions from now on, an improved recipe will be generated based on the feedback information.

[0743] Hardware and Software

[0744] Hardware: Automated cooking equipment in factories (e.g., general-purpose cooking robots)

[0745] Software: Recipe generation API (e.g., built with Flask or Django), robot control API (API endpoints supporting HTTP requests)

[0746] Specific examples

[0747] The factory cafeteria manager uses his smartphone to enter the following:

[0748] Ingredients: Chicken, green onion

[0749] Number of people: 2 servings

[0750] Seasoning: Salt sauce

[0751] Cooking time: 30 minutes

[0752] Based on this, a request is sent to the recipe generation API, and the generated recipe is sent to the automatic cooking device. The automatic cooking device starts cooking according to the instructions, and once finished, the "stir-fried chicken and green onions with salt sauce" is served.

[0753] Prompt Sentence Examples

[0754] Ingredients: Chicken, Green onion, Serves: 2, Seasoning: Salt, Cooking time: 30 minutes. Generate the best recipe based on your criteria.

[0755] This will enable efficient and high-quality food provision even in large locations such as factories.

[0756] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0757] Step 1:

[0758] Users launch the application on their smartphone or tablet and enter information such as the ingredients they want to use, the number of people they want to cook for, the desired seasoning, and cooking time.

[0759] The conditions entered were ingredients "chicken, green onion", serving size "2 servings", seasoning "salt sauce", and cooking time "30 minutes".

[0760] The terminal converts this input data into JSON format and sends it to the server.

[0761] Step 2:

[0762] The server analyzes the received input data and, based on that, searches and retrieves past similar recipes and seasoning distribution data from a database.

[0763] The server uses popular Python libraries (e.g., Pandas, SQLAlchemy) to perform data retrieval.

[0764] The server generates original recipe data based on the search results.

[0765] For example, you would decide on specific amounts of ingredients such as "200g chicken, 1 green onion" and seasonings such as "1 teaspoon salt, 1 tablespoon sake, 1 tablespoon mirin, 50ml water."

[0766] Step 3:

[0767] The server converts the generated original recipe data and specific cooking instructions into JSON format and returns it to the terminal.

[0768] The returned data includes specific cooking instructions:

[0769] 1. Cut the chicken into bite-sized pieces.

[0770] 2. Cut the green onions into 1cm wide pieces.

[0771] 3. Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes.

[0772] 4. Once the chicken is cooked through, add the green onions and stir fry for a further 3 minutes.

[0773] 5. Add salt, sake, mirin, and water, and simmer for 1 minute while stirring.

[0774] Step 4:

[0775] The terminal transmits the received original recipe data and cooking instructions to the automatic cooking device.

[0776] This is done using an HTTP request (e.g., an HTTP POST request).

[0777] The automatic cooking device automatically starts cooking based on the transmitted cooking instructions.

[0778] Step 5:

[0779] After the user has finished cooking, they can enter their feedback on the dish into the app.

[0780] For example, you can enter a specific opinion such as, "There was too much salt, so next time I'd like to use 0.5 teaspoons."

[0781] The terminal transmits this feedback data to the server.

[0782] Step 6:

[0783] The server stores the received feedback data in a database.

[0784] From next time onwards, if the same user requests a recipe with the same ingredients and conditions, the recipe will be improved based on this feedback data.

[0785] This makes it possible to provide recipes optimized to the user's preferences.

[0786] 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.

[0787] MODE FOR CARRYING OUT THE INVENTION

[0788] System Overview

[0789] This system automatically generates original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and provides detailed cooking instructions.It also collects and analyzes user feedback and emotional data using an emotion engine, and reflects this in future recipe generation to always provide recipes optimized to the user's preferences.

[0790] System configuration

[0791] The system consists of the following modules:

[0792] 1. User Interface (UI) Module

[0793] 2. Recipe Generation Module

[0794] 3. Procedure Assistant Module

[0795] 4. Feedback Module

[0796] 5. Emotion Engine Module

[0797] Program processing

[0798] 1. User Interface (UI) Module

[0799] Users launch the application from their smartphone or PC and input the ingredients they want to use, the number of people they want to cook for, the desired seasoning, cooking time, etc. For example, if they want to cook two servings using chicken and green onions and have them seasoned with salt, they can enter that information.

[0800] 2. Recipe Generation Module

[0801] The device sends the conditions entered by the user to the server. Based on the received data, the server searches and retrieves past similar recipes and seasoning distribution data from a database, and generates an original recipe that best suits the conditions. For example, the server determines specific amounts such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)."

[0802] 3. Procedure Assistant Module

[0803] The server sends the generated recipe data to the device, which receives it and displays it to the user. When the user starts cooking based on the recipe, the following instructions are displayed:

[0804] 1. Cut the chicken into bite-sized pieces.

[0805] 2. Cut the green onions into 1cm wide pieces.

[0806] 3. Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes.

[0807] 4. Once the chicken is cooked through, add the green onions and stir fry for a further 3 minutes.

[0808] 5. Add salt, sake, mirin, and water, and simmer for 1 minute while stirring.

[0809] 4. Feedback Module

[0810] After the user has finished cooking, they can enter their feedback about the dish (for example, "There was too much salt, so next time I'll use 0.5 teaspoons") into the app. The device sends that feedback to the server, which stores it in a database. If the same user requests a recipe with the same ingredients and conditions from now on, an improved recipe will be generated based on the feedback information.

[0811] 5. Emotion Engine Module

[0812] When a user enters feedback, the emotion engine recognizes the user's emotions by analyzing the text entered by the user and facial and voice data captured using the camera and microphone. For example, it can determine whether the user is satisfied with the food or stressed.

[0813] The device sends the user's emotional data to the server, which analyzes and stores it. This data is taken into account when generating recipes from the next time onwards, and a more optimal recipe based on the user's emotions is provided. For example, if a user felt that the previous dish was spicy, a less spicy recipe will be suggested.

[0814] Specific examples

[0815] As a concrete example, consider a scenario in which a user creates a "chicken and green onion dish with salt sauce, serving two." First, the user selects "chicken" and "green onion" as ingredients in the app, and sets the conditions of two servings, salt sauce, and within 30 minutes. The device sends this information to the server, which then generates a recipe that meets the conditions. The generated recipe specifically calls for "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water," which the device receives and displays to the user.

[0816] The user cooks the food based on the displayed recipe and then enters feedback into the app after cooking. The emotion engine analyzes the user's emotions and evaluates their satisfaction with the food, along with comments such as "The amount of salt was too much, so next time I'll use 0.5 teaspoons." This feedback and emotion data are sent from the device to the server and are used to generate future recipes.

[0817] This allows users to always receive recipes optimized to their preferences and emotions, improving the quality and satisfaction of their cooking.The system eliminates the traditional hassle of searching for recipes and adjusting portion sizes, and can provide more specific and detailed cooking instructions and emotion-based recipe suggestions.

[0818] The processing flow will be explained below.

[0819] Step 1:

[0820] The user opens the application screen and enters the ingredients they want to use, the number of people they want to cook for, the desired seasoning, and the cooking time.

[0821] Specifically, you would make two servings using chicken and green onions, request a salty flavor, and enter "within 30 minutes."

[0822] Step 2:

[0823] The terminal receives the input data and sends it to the server.

[0824] Specifically, the entered data is sent to the server as an HTTP request (e.g., POST / generate-recipe).

[0825] Step 3:

[0826] The server receives the request and parses the received data.

[0827] Specifically, the conditions entered by the user are extracted and each field is identified.

[0828] Step 4:

[0829] The server searches the database to retrieve similar recipes and past cooking data.

[0830] Specifically, past recipe data that matches the conditions is obtained using an SQL query.

[0831] Step 5:

[0832] An original recipe is generated based on the data acquired by the server.

[0833] Specifically, it calculates the amount of ingredients and the distribution of seasonings, and creates an appropriate cooking procedure.

[0834] For example, it generates specific recipe data such as "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water."

[0835] Step 6:

[0836] The server transmits the generated recipe data to the terminal.

[0837] Specifically, the generated recipe information is returned as an HTTP response (e.g., 200 OK).

[0838] Step 7:

[0839] The device analyzes the received recipe data and displays it visually to the user.

[0840] Specifically, the recipe's ingredients, quantities, and cooking steps are displayed in detail on the screen.

[0841] Step 8:

[0842] The user cooks the food based on the displayed recipe.

[0843] Specifically, the user follows the steps presented to them to perform actions such as cutting ingredients, frying, and mixing seasonings.

[0844] Step 9:

[0845] The user completes the cooking and then enters feedback into the app about the cooking results and taste.

[0846] Specifically, write your impressions such as, "There was too much salt, so next time I'll use 0.5 teaspoon."

[0847] Step 10:

[0848] The emotion engine analyzes the feedback, facial expressions, and voice input from the user to obtain emotional data.

[0849] Specifically, the system uses a camera and microphone to capture changes in the user's tone of voice and facial expressions, and assigns emotional labels such as "satisfied" or "dissatisfied."

[0850] Step 11:

[0851] The terminal transmits the feedback data and the emotion data to the server.

[0852] Specifically, feedback and emotional data are sent to the server via an HTTP request (e.g., POST / submit-feedback).

[0853] Step 12:

[0854] The server receives the feedback data and emotion data and stores them in a database.

[0855] Specifically, feedback information and emotion data are recorded in a database using SQL INSERT statements.

[0856] Step 13:

[0857] The next time the user tries to generate a recipe under the same conditions, the server will optimize the generated recipe by taking into account past feedback data and emotion data.

[0858] Specifically, the system improves the distribution of seasonings and cooking methods based on the collected feedback and emotional data. For example, it analyzes the factors that led to low satisfaction in the previous meal and makes adjustments based on that.

[0859] Example 2

[0860] 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."

[0861] Modern consumers are faced with a wide variety of ingredients and cooking options, making it difficult to find recipes that best suit their tastes. Furthermore, existing systems do not fully utilize feedback and sentiment data from individual users, making it difficult to increase user satisfaction. The present invention aims to solve these problems by providing a system that suggests optimal recipes based on a user's individual preferences and feedback.

[0862] 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.

[0863] In this invention, the server includes means for inputting conditions such as ingredients, number of people, seasonings, and cooking time selected by the user, means for generating original recipe data based on the conditions, means for displaying detailed cooking procedures based on the generated original recipe, means for collecting feedback from the user and reflecting it in generating subsequent original recipes, and means for recognizing user emotional data and reflecting that data in generating original recipes. This makes it possible to provide recipes optimized for the preferences and emotional state of each individual user.

[0864] "User" refers to an individual who uses this system to create recipes and receive cooking instructions.

[0865] "Ingredients" refers to the ingredients selected by the user for cooking.

[0866] "Number of people" refers to data that indicates the amount of food the user is making and specifies how many people the food is for.

[0867] "Seasoning" refers to data indicating the flavor and type of seasoning the user desires for the dish.

[0868] "Cooking time" refers to data indicating the time it takes to complete the dish desired by the user.

[0869] "Original recipe" refers to unique recipe data generated based on input conditions.

[0870] "Means" refers to the technical configuration for realizing a specific function in this system.

[0871] "Feedback" refers to the ratings and opinions provided by users about the results of their cooking.

[0872] "Emotional data" refers to data obtained by analyzing a user's emotional state.

[0873] "Server" refers to the computer system that processes and stores data in this system.

[0874] "Terminal" refers to the device (e.g., smartphone or PC) used by a user to access the system.

[0875] "Database" refers to a storage device for storing and managing collected data.

[0876] "Generative AI model" refers to the artificial intelligence algorithm used to generate original recipes.

[0877] A "prompt" refers to a sentence or instruction input to a generative AI model.

[0878] This system automatically generates original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and provides detailed cooking instructions. Furthermore, the system collects and analyzes feedback and emotional data from users, and reflects this in future recipe generation, thereby providing recipes that are always optimized to the user's preferences.

[0879] System configuration

[0880] The system consists of the following modules:

[0881] 1. User Interface (UI) Module

[0882] 2. Recipe Generation Module

[0883] 3. Procedure Assistant Module

[0884] 4. Feedback Module

[0885] 5. Emotion Engine Module

[0886] Hardware and Software

[0887] The hardware used includes user devices such as smartphones and PCs, as well as servers, while the software used includes applications that provide a user interface, database software, and machine learning libraries for running generative AI models.

[0888] Program processing

[0889] The program processing in this system is as follows:

[0890] 1. User Interface (UI) Module

[0891] Users launch the application from their smartphone or PC and input the ingredients they want to use, the number of people they want to cook for, the desired seasoning, cooking time, etc. For example, they can use "chicken" and "green onions" to cook "two servings," request "salt sauce," and set the cooking time to "within 30 minutes."

[0892] 2. Recipe Generation Module

[0893] The device sends the conditions entered by the user to the server. Based on the received data, the server searches and retrieves similar past recipes and seasoning distribution data from a database, and uses a generative AI model to generate an original recipe that best suits the conditions. For example, the server determines specific amounts such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)."

[0894] 3. Procedure Assistant Module

[0895] The server sends the generated recipe data to the device, which receives it and displays it to the user. When the user starts cooking based on the recipe, the following instructions are displayed:

[0896] 1. Cut the chicken into bite-sized pieces.

[0897] 2. Cut the green onions into 1cm wide pieces.

[0898] 3. Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes.

[0899] 4. Once the chicken is cooked through, add the green onions and stir fry for a further 3 minutes.

[0900] 5. Add salt, sake, mirin, and water, and simmer for 1 minute while stirring.

[0901] 4. Feedback Module

[0902] After the user has finished cooking, they can enter feedback about the dish into the app. For example, they can enter feedback such as, "There was too much salt, so next time I'll use 0.5 teaspoons."

[0903] 5. Emotion Engine Module

[0904] When a user enters feedback, the emotion engine recognizes the user's emotions by analyzing the text entered by the user and facial and voice data captured using the camera and microphone. For example, it can determine whether the user is satisfied with the food or stressed.

[0905] Specific examples

[0906] As a concrete example, consider a scenario in which a user makes a dish for two people using chicken and green onions with a salt sauce. The user selects "chicken" and "green onions" as ingredients in the app and sets the conditions of two servings, salt sauce, and within 30 minutes. The device sends this information to the server, which then generates a recipe that meets the conditions. The generated recipe consists of "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water," which the device receives and displays to the user. The user cooks the food based on the displayed recipe and enters feedback into the app after cooking. At this time, the emotion engine analyzes the user's emotions and evaluates the user's level of satisfaction, along with comments such as "The amount of salt was too much, so next time I'll use 0.5 teaspoons." This feedback and emotion data are sent from the device to the server and used to generate future recipes.

[0907] Prompt Sentence Examples

[0908] An example of a prompt to input to a generative AI model is as follows:

[0909] You are in charge of programming a cooking recipe generation system. Your task is to automatically generate the optimal recipe for a user to make "Chicken and green onion dish with salt sauce, for two people." You must provide specific ingredients and steps, and take into account the user's past feedback and sentiment data.

[0910] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0911] Step 1:

[0912] The user interface (UI) module allows users to launch the application from their smartphone or PC. Users input conditions such as the ingredients they want to use, the number of people they want to cook for, the desired seasoning, and cooking time. For example, a user might select "chicken" and "green onions" as ingredients, cook "two servings," request "salt sauce," and set the cooking time to "within 30 minutes."

[0913] Input: The user enters the condition.

[0914] Output: The format in which the input data is formatted and sent to the server (e.g. JSON data).

[0915] Step 2:

[0916] The device sends the conditions entered by the user to the server. The sent data is accurately passed to the server in JSON format, etc.

[0917] Input: Data entered by the user.

[0918] Output: The formatted data that is sent to the server.

[0919] Specific operation: Press the "Send" button on the terminal. When the "Send" button is pressed, the input data is validated. Data that passes validation is sent to the server.

[0920] Step 3:

[0921] Based on the data received by the server, the database is searched for and retrieved from the server similar recipes and seasoning distribution data from the past. This data is then used by a generative AI model to generate an original recipe that best suits the conditions.

[0922] Input: Formatted condition data.

[0923] Output: The generated original recipe data.

[0924] Specific operations: The server analyzes the received data, searches for related data from the database to retrieve similar recipes, and uses a generative AI model to create the optimal recipe.

[0925] Step 4:

[0926] The server transmits the generated recipe data to the terminal, which receives it and displays it to the user.

[0927] Input: Generated original recipe data.

[0928] Output: Recipe information displayed to the user.

[0929] Specific operation: The server sends the generated recipe data in JSON format. The device receives the recipe data and displays it on the interface. The recipe includes specific ingredient amounts and cooking instructions.

[0930] Step 5:

[0931] The user starts cooking based on the displayed recipe, and the step-by-step instructions are provided by the step-by-step assistant module.

[0932] Input: User confirms cooking instructions.

[0933] Output: Specific instructions for the user to proceed with the cooking.

[0934] How it works: Each cooking step is displayed on the recipe screen. The user proceeds with the cooking process while checking each step. The screen is updated as the cooking process progresses.

[0935] Step 6:

[0936] After the user has finished cooking, they can enter their feedback on the dish into the app, such as "I added too much salt, so next time I'll use 0.5 teaspoons."

[0937] Input: Post-cooking feedback.

[0938] Output: Formatted feedback data.

[0939] Specific operation: After cooking is complete, the user enters comments on the feedback screen that appears, and inputs emotional data (such as satisfaction and stress levels).

[0940] Step 7:

[0941] The device sends feedback to the server, which stores the feedback data in a database and uses it to generate future recipes.

[0942] Input: Formatted feedback data.

[0943] Output: Feedback data stored in a database.

[0944] Specific operation: Press the feedback sending button. Feedback and emotion data will be sent together.

[0945] Step 8:

[0946] The server uses an emotion engine to analyze and store the user's emotion data. The analysis results are taken into account when generating recipes from the next time onwards.

[0947] Input: Feedback data and emotion data.

[0948] Output: Parsed emotion data.

[0949] Specific operation: The server analyzes the received emotion data. The emotion engine evaluates the satisfaction and stress levels. The evaluation results are stored in a database.

[0950] (Application example 2)

[0951] 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."

[0952] Conventional recipe generation systems simply generate recipes based on ingredients and seasoning conditions, and are unable to fully reflect users' specific emotions and feedback. This has led to a demand for systems that can provide recipes that fully satisfy users. Furthermore, the lack of an efficient recipe generation and cooking instruction system that can be used in brick-and-mortar establishments such as restaurants has made it difficult to develop new dishes and streamline kitchen operations.

[0953] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0954] In this invention, the server includes a means for inputting user-selected conditions such as ingredients, number of people, seasonings, and cooking time, a means for generating original recipe data based on the conditions, a means for displaying detailed cooking steps based on the generated original recipe, a means for collecting user feedback and reflecting the feedback in subsequent recipe generation, and a means for analyzing user emotion data and optimizing the recipe based on the user's emotion. This makes it possible to provide optimized recipes that reflect the user's emotion and feedback. This can also contribute to the development of new dishes in restaurants and the efficiency of kitchen operations.

[0955] "Ingredients, number of people, seasoning, and cooking time" are items that the user selects when creating a recipe, and the combination of these is an important factor in determining the specific recipe.

[0956] "Original recipe data" refers to recipe data that the system automatically generates based on conditions specified by the user, and may also be generated based on past recipe data or seasoning distribution data.

[0957] The "means for displaying detailed cooking steps" is a function for displaying specific and detailed steps for the user to actually prepare a dish based on the generated original recipe.

[0958] "Means of collecting feedback and reflecting it in future recipe generation" refers to a function that allows users to input their impressions and suggestions for improvement after actually cooking into the system, which then stores them in a database for use when generating the next recipe.

[0959] "Means for analyzing emotional data and optimizing recipes based on the user's emotions" refers to a function that allows the emotion engine to recognize and analyze the user's emotions when they enter feedback, and then use that data to optimize future recipe suggestions.

[0960] A "restaurant" is a place where users can eat, and is a general concept that encompasses store formats such as restaurants and cafes.

[0961] This invention is a system that automatically generates original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and provides detailed cooking instructions. This system consists of five main modules: a user interface (UI) module, a recipe generation module, a step assistant module, a feedback module, and an emotion engine module.

[0962] 1. User Interface (UI) Module

[0963] It is a means for users to launch an application on their smartphone or tablet device and input conditions such as ingredients, number of people, seasoning, cooking time, etc. For example, when a restaurant chef creates a new dish, if he or she wants to use "chicken" and "green onion" to make "two servings" and "salt sauce" and wants it to be "salted," the function is provided to input this information.

[0964] 2. Recipe Generation Module

[0965] The terminal sends the conditions entered by the user to the server. Based on the received data, the server searches and retrieves similar past recipes and seasoning distribution data from a database, and generates an original recipe that best suits the conditions. For example, the server determines specific amounts such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)." Backend processing using Python and Flask is performed during this process.

[0966] 3. Procedure Assistant Module

[0967] The server sends the generated recipe data to the device, which receives it and displays it to the user. When the user starts cooking based on the recipe, detailed cooking instructions are displayed in real time. Specifically, instructions such as "Cut the chicken into bite-sized pieces," "Cut the green onions into 1cm pieces," "Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes," "Once the chicken is cooked through, add the green onions and fry for another 3 minutes," and "Add salt, sake, mirin, and water, and simmer for 1 minute while mixing everything together" are displayed.

[0968] 4. Feedback Module

[0969] After the user has finished cooking, they can enter their feedback on the dish from their device and send it to the server. For example, they can provide feedback such as, "I added too much salt, so next time I'll use 0.5 teaspoons." The server stores this feedback in a database and uses it to generate future recipes.

[0970] 5. Emotion Engine Module

[0971] When a user enters feedback, the emotion engine recognizes and analyzes the user's emotions. This emotion recognition is performed by analyzing the text entered by the user and facial expressions and voice data acquired using a camera or microphone. The server analyzes and saves the user's emotion data, and takes this into consideration when generating recipes from the next time onwards, allowing it to provide more optimal recipes based on the user's emotions.

[0972] Specific examples

[0973] A restaurant chef opens an application to create a new dish and enters the following criteria:

[0974] Ingredients: chicken, green onion

[0975] Number of people: 2 servings

[0976] Seasoning: Salt sauce

[0977] Cooking time: 30 minutes

[0978] The system generates a recipe based on this information and displays cooking instructions. After the chef has finished cooking, they can enter their feedback, which is then analyzed by the emotion engine. This data is then used to generate future recipes.

[0979] Prompt Sentence Examples

[0980] A chef is looking for a recipe for a new dish. Generate a recipe based on the following criteria and provide detailed cooking instructions:

[0981] Ingredients: chicken, green onion

[0982] Number of people: 2 servings

[0983] Seasoning: Salt sauce

[0984] Cooking time: 30 minutes

[0985] In addition, feedback and emotional data after cooking is completed will be taken into consideration and reflected in future recipe suggestions.

[0986] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0987] Step 1:

[0988] Users launch the application on their smartphone or tablet and input the ingredients, number of people, seasoning, cooking time, etc. Specifically, a restaurant chef would input the following conditions: "chicken," "green onion," "serves two," "salt sauce," and "30 minutes."

[0989] Input: ingredients, number of people, seasoning, cooking time

[0990] Output: Condition data

[0991] Step 2:

[0992] The device sends the entered condition data to the server. Based on the received data, the server searches and retrieves past similar recipes and seasoning distribution data from a database, and generates an original recipe that best suits the conditions. Specifically, the server determines the specific amounts of ingredients, such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)."

[0993] Input: Condition data

[0994] Data processing: database search, retrieval of similar recipes, generation of original recipes

[0995] Output: Generated recipe data

[0996] Step 3:

[0997] The server sends the generated recipe data to the device, which receives it and displays it to the user. The user then begins cooking based on the displayed recipe data. Specific instructions are displayed, such as "Cut the chicken into bite-sized pieces," "Cut the green onions into 1cm pieces," and "Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes."

[0998] Input: Generated recipe data

[0999] Data processing: None

[1000] Output: Display of cooking instructions

[1001] Step 4:

[1002] After the user has finished cooking, they can input their feedback about the dish and send it to the server from their device. For example, they might say, "I added too much salt, so next time I'll use 0.5 teaspoons." The server stores this feedback in a database and uses it to generate future recipes.

[1003] Input: User feedback

[1004] Data processing: Accumulation in the database, reflection in next recipe generation

[1005] Output: Accumulated feedback data

[1006] Step 5:

[1007] When a user enters feedback, the emotion engine recognizes and analyzes the user's emotions. It analyzes facial expressions and voice data captured using a camera and microphone to determine whether the user is satisfied with the cooking or stressed. The server analyzes and saves the emotion data and takes it into consideration when generating recipes in the future.

[1008] Input: Feedback text, facial expression data, voice data

[1009] Data processing: text analysis, facial expression and voice analysis, emotion data generation

[1010] Output: Parsed emotion data

[1011] Step 6:

[1012] The server uses the accumulated feedback data and analyzed emotion data and takes this information into account when generating new recipes, so that future recipes will be further optimized based on the user's emotions and feedback.

[1013] Input: Accumulated feedback data, analyzed emotion data

[1014] Data processing: Integrating feedback and sentiment data and reflecting it in recipe generation

[1015] Output: New optimized recipe data

[1016] 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.

[1017] 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.

[1018] 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.

[1019] [Third embodiment]

[1020] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1021] 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.

[1022] 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).

[1023] 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.

[1024] 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.

[1025] 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).

[1026] 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.

[1027] 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.

[1028] 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.

[1029] 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.

[1030] 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.

[1031] 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."

[1032] MODE FOR CARRYING OUT THE INVENTION

[1033] System Overview

[1034] This system automatically generates original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and provides detailed cooking instructions. It also collects user feedback and reflects it in future recipe generation to always provide recipes optimized to the user's preferences.

[1035] System configuration

[1036] The system is broadly composed of the following modules:

[1037] 1. User Interface (UI) Module

[1038] 2. Recipe Generation Module

[1039] 3. Procedure Assistant Module

[1040] 4. Feedback Module

[1041] Program processing

[1042] 1. User Interface (UI) Module

[1043] Users launch the application from their smartphone or PC and input the ingredients they want to use, the number of people they want to cook for, the desired seasoning, cooking time, etc. For example, if they want to cook two servings using chicken and green onions and have them seasoned with salt, they can enter that information.

[1044] 2. Recipe Generation Module

[1045] The device sends the conditions entered by the user to the server. Based on the received data, the server searches and retrieves past similar recipes and seasoning distribution data from a database, and generates an original recipe that best suits the conditions. For example, the server determines specific amounts such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)."

[1046] 3. Procedure Assistant Module

[1047] The server sends the generated recipe data to the device, which receives it and displays it to the user. When the user starts cooking based on the recipe, instructions are displayed, for example, as follows:

[1048] 1. Cut the chicken into bite-sized pieces.

[1049] 2. Cut the green onions into 1cm wide pieces.

[1050] 3. Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes.

[1051] 4. Once the chicken is cooked through, add the green onions and stir fry for a further 3 minutes.

[1052] 5. Add salt, sake, mirin, and water, and simmer for 1 minute while stirring.

[1053] 4. Feedback Module

[1054] After the user has finished cooking, they can enter their feedback about the dish (for example, "There was too much salt, so next time I'll use 0.5 teaspoons") into the app. The device sends that feedback to the server, which stores it in a database. If the same user requests a recipe with the same ingredients and conditions from now on, an improved recipe will be generated based on the feedback information.

[1055] Specific examples

[1056] As a concrete example, consider a scenario in which a user prepares a dish for two people using chicken and green onions with a salt sauce. First, the user selects "chicken" and "green onions" as ingredients in the app, and sets the conditions of two servings, salt sauce, and within 30 minutes. The device sends this information to the server, which then generates a recipe that meets the conditions. The generated recipe specifically includes "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water," which the device receives and displays to the user. The user cooks according to the instructions, and after cooking, enters feedback into the app. This feedback is used to generate future recipes.

[1057] This allows users to always receive recipes optimized to their preferences. The system eliminates the traditional hassle of searching for recipes and adjusting portions, and provides more specific and detailed cooking instructions.

[1058] The processing flow will be explained below.

[1059] Step 1:

[1060] The user opens the application screen and enters the ingredients they want to use, the number of people they want to cook for, the desired seasoning, and the cooking time.

[1061] Specifically, you would make two servings using chicken and green onions, request a salty flavor, and enter "within 30 minutes."

[1062] Step 2:

[1063] The terminal receives the input data and sends it to the server.

[1064] Specifically, the data is sent to the server as an HTTP request (e.g., POST / generate-recipe).

[1065] Step 3:

[1066] The server receives the request and parses the received data.

[1067] Specifically, the conditions entered by the user are extracted and each field is identified.

[1068] Step 4:

[1069] The server searches the database to retrieve similar recipes and past cooking data.

[1070] Specifically, past recipe data that matches the conditions is obtained using an SQL query.

[1071] Step 5:

[1072] An original recipe is generated based on the data acquired by the server.

[1073] Specifically, it calculates the amount of ingredients and the distribution of seasonings, and creates an appropriate cooking procedure.

[1074] For example, it generates specific recipe data such as "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water."

[1075] Step 6:

[1076] The server transmits the generated recipe data to the terminal.

[1077] Specifically, the generated recipe information is returned as an HTTP response (e.g., 200 OK).

[1078] Step 7:

[1079] The device analyzes the received recipe data and displays it visually to the user.

[1080] Specifically, the recipe's ingredients, quantities, and cooking steps are displayed in detail on the screen.

[1081] Step 8:

[1082] The user cooks the food based on the displayed recipe.

[1083] Specifically, the user follows the steps presented to them and performs actions such as cutting ingredients, frying, and mixing seasonings.

[1084] Step 9:

[1085] The user completes the cooking and then enters feedback into the app about the cooking results and taste.

[1086] Specifically, write your impressions such as, "There was too much salt, so next time I'll use 0.5 teaspoon."

[1087] Step 10:

[1088] The terminal transmits the feedback data to the server.

[1089] Specifically, feedback is sent to the server via an HTTP request (e.g., POST / submit-feedback).

[1090] Step 11:

[1091] The server receives the feedback and stores it in a database.

[1092] Specifically, the feedback information is recorded in the database using an SQL INSERT statement.

[1093] Step 12:

[1094] The next time the user tries to generate a recipe under the same conditions, the server will optimize the generated recipe taking into account past feedback data.

[1095] Specifically, the distribution of seasonings and cooking methods will be improved based on the collected feedback.

[1096] Example 1

[1097] 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."

[1098] Conventional recipe search systems require users to adjust the exact amounts of ingredients and seasonings, and it is difficult to reflect user preferences and feedback in the next recipe. This means that users have to either repeat the same operations every time or spend time adjusting the recipe themselves. This reduces convenience and reduces user satisfaction.

[1099] 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.

[1100] In this invention, the server includes a means for a user to input conditions such as ingredients, number of people, seasonings, and cooking time, a means for using a generative AI model to generate original recipe data based on the conditions, a means for displaying detailed cooking steps based on the generated original recipe, and a means for collecting feedback from the user in the form of prompt sentences and reflecting this in subsequent recipe generation. This allows a user to simply input conditions to automatically generate an original recipe optimized to their preferences and receive detailed cooking steps, and further enables subsequent recipes to be improved based on the feedback.

[1101] "User" refers to an individual who intends to use the system to generate a recipe.

[1102] "Ingredients" refers to the ingredients that a user selects to use in a recipe.

[1103] "Number of people" refers to the number of people used to determine the amount of food the user will cook.

[1104] "Seasoning" refers to the flavor and type of seasoning the user desires for the dish.

[1105] "Cooking time" refers to the maximum cooking time desired by the user.

[1106] "Conditions" refers to the ingredients, number of people, seasonings, and cooking time input by the user.

[1107] "Original recipe data" refers to recipe information that is automatically generated based on conditions entered by the user.

[1108] "Generative AI Model" refers to an artificial intelligence model used to generate original recipe data based on conditions.

[1109] "Detailed cooking instructions" refers to specific, step-by-step cooking methods based on the original recipe data.

[1110] "Feedback" refers to the evaluation and suggestions for improvement that users provide to the system after cooking.

[1111] A "prompt sentence" refers to a sentence entered by a user that describes the requests and conditions for recipe generation.

[1112] "Database" refers to a data storage system for accumulating past similar recipes, seasoning distribution data, and user feedback data.

[1113] MODE FOR CARRYING OUT THE INVENTION

[1114] System Overview

[1115] The system of the present invention automatically generates original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and provides detailed cooking instructions. Furthermore, by collecting feedback from the user and reflecting it in future recipe generation, the system always provides recipes optimized to the user's preferences.

[1116] System configuration

[1117] This system is broadly composed of the following modules:

[1118] 1. User Interface (UI) Module

[1119] 2. Data sending and receiving module

[1120] 3. Recipe Generation Module

[1121] 4. Cooking procedure assistant module

[1122] 5. Feedback Module

[1123] User Interface (UI) Module

[1124] Users launch the application from their smartphone or PC and input the ingredients they want to use, the number of people they want to cook for, the desired seasoning, cooking time, etc. For example, if they want to cook two servings using chicken and green onions and have them seasoned with salt, they can enter that information.

[1125] Data sending and receiving modules

[1126] The device sends the conditions entered by the user to the server. The communication protocol is HTTP, and the input data is structured in JSON format. A POST request is sent to the server, and the transmitted content includes information on ingredients, number of people, seasoning, and cooking time.

[1127] Recipe Generation Module

[1128] The server analyzes the received data and searches and retrieves similar past recipes and seasoning distribution data from a database. Using a generative AI model, an original recipe that best suits the input conditions is generated. At this time, the amounts of ingredients and the distribution of seasonings are also calculated. For example, the required amounts may be determined as "200g of chicken," "1 scallion," "1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, and 50ml of water."

[1129] Cooking procedure assistant module

[1130] The server sends the generated recipe data to the device, which receives it and displays it to the user, along with detailed instructions, when the user starts cooking based on the recipe.

[1131] Feedback Module

[1132] After the user has finished cooking, they can enter their feedback on the dish into the app. For example, they can write a comment such as, "There was too much salt, so next time I'll use 0.5 teaspoons." The device sends this feedback to the server, which stores it in a database. If the same user requests a recipe with the same ingredients and conditions from now on, an improved recipe will be generated based on the feedback information.

[1133] Specific examples

[1134] As a concrete example, consider a scenario in which a user prepares a dish for two people using chicken and green onions with a salt sauce. First, the user selects "chicken" and "green onions" as ingredients in the app, and sets the conditions of two servings, salt sauce, and within 30 minutes. The device sends this information to the server, which then generates a recipe that meets the conditions. The generated recipe specifically includes "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water," which the device receives and displays to the user. The user cooks according to the instructions, and after cooking, enters feedback into the app. This feedback is used to generate future recipes.

[1135] (Example prompt)

[1136] "Generate a recipe for two servings of chicken and green onion with a salt sauce in 30 minutes or less."

[1137] Hardware and software used

[1138] The hardware used includes the devices used by users (smartphones and PCs) and the servers for processing and storing data.The software used includes front-end frameworks (e.g., React, Vue.js) for building user interfaces, back-end frameworks (e.g., Node.js, Django) for sending and receiving data, and machine learning libraries (e.g., TensorFlow, PyTorch) for running generative AI models.

[1139] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1140] Step 1: The user inputs the ingredients, number of people, seasonings, and cooking time.

[1141] The user launches the application from their smartphone or PC and inputs the ingredients they want to use (e.g., chicken, green onions), the number of people they want to cook for (e.g., two servings), the desired seasoning (e.g., salt sauce), and the cooking time (e.g., within 30 minutes). This information is structured in JSON format.

[1142] Input: Ingredients, number of people, seasoning, cooking time

[1143] Output: Input data in JSON format

[1144] Specific working example:

[1145] The user enters conditions into each input field and clicks the submit button.

[1146] Step 2: The device sends the input data to the server

[1147] The device sends the JSON format data entered by the user to the server using the HTTP POST request as the communication protocol.

[1148] Input: Input data in JSON format

[1149] Output: Data sent as an HTTP POST request

[1150] Specific working example:

[1151] The data received by the terminal is sent as the payload of the POST request.

[1152] Step 3: The server receives and parses the data

[1153] The server receives the HTTP POST request, retrieves the data sent from the payload, and analyzes it to extract the ingredients, number of people, seasoning, and cooking time.

[1154] Input: JSON format data included in the POST request

[1155] Output: Parsed condition data

[1156] Specific working example:

[1157] The server extracts JSON data from the request body and breaks it down according to conditions.

[1158] Step 4: The server searches the database and retrieves the required recipe information.

[1159] Based on the analyzed condition data, the server searches and retrieves similar past recipes and seasoning distribution data from the database.

[1160] Input: Parsed condition data

[1161] Output: Past similar recipes and seasoning distribution data

[1162] Specific working example:

[1163] The server queries the database based on ingredients, number of people, seasonings, and cooking time.

[1164] Step 5: The server generates an original recipe using the generative AI model

[1165] The server inputs the acquired data into a generative AI model to generate an original recipe that best suits the conditions. The model also calculates the amount of ingredients and the distribution of seasonings.

[1166] Input: Previously acquired similar recipes and seasoning distribution data

[1167] Output: Original recipe data

[1168] Specific working example:

[1169] The server passes the input data to the generative AI model to generate the optimal recipe.

[1170] Step 6: The server sends the original recipe data to the terminal.

[1171] The server converts the generated original recipe data into JSON format and sends it to the terminal.

[1172] Input: Original recipe data

[1173] Output: Original recipe data in JSON format

[1174] Specific working example:

[1175] The server encodes the generated recipe data and sends it to the terminal.

[1176] Step 7: The device displays the original recipe data to the user

[1177] The device analyzes the original recipe data received and displays it on the user interface. The recipe also includes detailed cooking instructions.

[1178] Input: Original recipe data in JSON format

[1179] Output: Recipe information displayed in the user interface

[1180] Specific working example:

[1181] The device analyzes the recipe data and displays it visually.

[1182] Step 8: User completes cooking and provides feedback

[1183] After the user has finished cooking, they can enter feedback into the application, for example, "There was too much salt" or "Next time I'll use 0.5 teaspoon."

[1184] Input: User feedback information

[1185] Output: Feedback data in JSON format

[1186] Specific working example:

[1187] A user enters a comment in the feedback section within the app and clicks the submit button.

[1188] Step 9: The device sends the feedback data to the server

[1189] The device sends the feedback data entered by the user to the server, which is also sent in JSON format.

[1190] Input: Feedback data in JSON format

[1191] Output: Feedback data as an HTTP POST request

[1192] Specific working example:

[1193] The feedback received by the device is sent as the payload of the POST request.

[1194] Step 10: The server receives the feedback data and stores it in a database.

[1195] The server analyzes the received feedback data and stores it in a database, which is then reflected in future recipe generation.

[1196] Input: Feedback data in JSON format included in a POST request

[1197] Output: Feedback data stored in a database

[1198] Specific working example:

[1199] The server stores the feedback in a database and uses it to generate future recipes.

[1200] (Application example 1)

[1201] 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."

[1202] Conventional recipe generation systems simply generate original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and then provide cooking instructions, which can be time-consuming when actually cooking. While there was a function to improve the recipe for future meals based on feedback, there was a lack of means to automate the cooking process, making it difficult to efficiently serve delicious food. Furthermore, in large facilities such as cafeterias and factories, the time and effort required to manually prepare meals for large numbers of people was a particular problem.

[1203] 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.

[1204] In this invention, the server includes means for inputting user-selected conditions (ingredients, number of people, seasonings, and cooking time), means for generating original recipe data based on the conditions, means for displaying detailed cooking steps based on the generated original recipe, means for collecting user feedback and reflecting it in subsequent recipe generation, and means for transmitting the original recipe data and cooking steps to an automatic cooking device, which then executes the cooking. This makes it possible to automatically cook dishes based on the generated recipe, making it possible to efficiently provide delicious dishes even in large-scale facilities.

[1205] "User" means an individual or entity that uses the system to generate recipes and prepare food.

[1206] "Ingredients" refer to the ingredients and seasonings used to make a dish.

[1207] "Number of people" refers to the number of people to whom food is being served.

[1208] "Seasoning" refers to the seasonings and cooking methods used to adjust the flavor and taste of a dish.

[1209] "Cooking time" refers to the time required to complete a dish.

[1210] "Conditions" refers collectively to the ingredients, number of people, seasonings, and cooking time selected by the user.

[1211] "Original recipe data" refers to recipe data generated based on conditions entered by the user.

[1212] "Cooking procedure" refers to the cooking steps that are specifically instructed based on the original recipe data.

[1213] "Feedback" refers to the opinions and ratings provided by users after cooking.

[1214] An "automatic cooking device" is a device that automatically cooks food based on input cooking instructions.

[1215] A "server" is a computer system that receives user input, generates recipes, displays cooking instructions, and sends instructions to the automated cooking device.

[1216] A "database" is an information storage system for accumulating past recipe data and user feedback data.

[1217] System Overview

[1218] This invention is a system that works in conjunction with an automatic cooking device to generate original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and then automatically cooks based on those recipes. It also aims to collect feedback from users and reflect it in future recipe generation, thereby always providing dishes that are optimized to the user's preferences.

[1219] System configuration

[1220] The system is broadly composed of the following modules:

[1221] 1. User Interface (UI) Module

[1222] 2. Recipe Generation Module

[1223] 3. Cooking instruction sending module

[1224] 4. Feedback Module

[1225] Program processing explanation

[1226] 1. User Interface (UI) Module

[1227] Users launch the application on their smartphone or tablet and input the ingredients they want to use, the number of people they want to cook for, the desired seasoning, cooking time, etc. For example, if they want to cook two servings of chicken and green onions and have them seasoned with salt, they can input that information in this interface.

[1228] 2. Recipe Generation Module

[1229] The device sends the conditions entered by the user to the server. Based on the received data, the server searches and retrieves past similar recipes and seasoning distribution data from a database, and generates an original recipe that best suits the conditions. For example, the server determines specific amounts such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)."

[1230] 3. Cooking instruction sending module

[1231] The server sends the generated recipe data and cooking instructions to the automatic cooking device, which then starts cooking based on the instructions. For example, the following cooking instructions may be sent:

[1232] 1. Cut the chicken into bite-sized pieces.

[1233] 2. Cut the green onions into 1cm wide pieces.

[1234] 3. Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes.

[1235] 4. Once the chicken is cooked through, add the green onions and stir fry for a further 3 minutes.

[1236] 5. Add salt, sake, mirin, and water, and simmer for 1 minute while stirring.

[1237] 4. Feedback Module

[1238] After the user has finished cooking, they can enter their feedback about the dish (for example, "There was too much salt, so next time I'll use 0.5 teaspoons") into the app. The device sends that feedback to the server, which stores it in a database. If the same user requests a recipe with the same ingredients and conditions from now on, an improved recipe will be generated based on the feedback information.

[1239] Hardware and Software

[1240] Hardware: Automated cooking equipment in factories (e.g., general-purpose cooking robots)

[1241] Software: Recipe generation API (e.g., built with Flask or Django), robot control API (API endpoints supporting HTTP requests)

[1242] Specific examples

[1243] The factory cafeteria manager uses his smartphone to enter the following:

[1244] Ingredients: Chicken, green onion

[1245] Number of people: 2 servings

[1246] Seasoning: Salt sauce

[1247] Cooking time: 30 minutes

[1248] Based on this, a request is sent to the recipe generation API, and the generated recipe is sent to the automatic cooking device. The automatic cooking device starts cooking according to the instructions, and once finished, the "stir-fried chicken and green onions with salt sauce" is served.

[1249] Prompt Sentence Examples

[1250] Ingredients: Chicken, Green onion, Serves: 2, Seasoning: Salt, Cooking time: 30 minutes. Generate the best recipe based on your criteria.

[1251] This will enable efficient and high-quality food provision even in large locations such as factories.

[1252] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1253] Step 1:

[1254] Users launch the application on their smartphone or tablet and enter information such as the ingredients they want to use, the number of people they want to cook for, the desired seasoning, and cooking time.

[1255] The conditions entered were ingredients "chicken, green onion", serving size "2 servings", seasoning "salt sauce", and cooking time "30 minutes".

[1256] The terminal converts this input data into JSON format and sends it to the server.

[1257] Step 2:

[1258] The server analyzes the received input data and, based on that, searches and retrieves past similar recipes and seasoning distribution data from a database.

[1259] The server uses popular Python libraries (e.g., Pandas, SQLAlchemy) to perform data retrieval.

[1260] The server generates original recipe data based on the search results.

[1261] For example, you would decide on specific amounts of ingredients such as "200g chicken, 1 green onion" and seasonings such as "1 teaspoon salt, 1 tablespoon sake, 1 tablespoon mirin, 50ml water."

[1262] Step 3:

[1263] The server converts the generated original recipe data and specific cooking instructions into JSON format and returns it to the terminal.

[1264] The returned data includes specific cooking instructions:

[1265] 1. Cut the chicken into bite-sized pieces.

[1266] 2. Cut the green onions into 1cm wide pieces.

[1267] 3. Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes.

[1268] 4. Once the chicken is cooked through, add the green onions and stir fry for a further 3 minutes.

[1269] 5. Add salt, sake, mirin, and water, and simmer for 1 minute while stirring.

[1270] Step 4:

[1271] The terminal transmits the received original recipe data and cooking instructions to the automatic cooking device.

[1272] This is done using an HTTP request (e.g., an HTTP POST request).

[1273] The automatic cooking device automatically starts cooking based on the transmitted cooking instructions.

[1274] Step 5:

[1275] After the user has finished cooking, they can enter their feedback on the dish into the app.

[1276] For example, you can enter a specific opinion such as, "There was too much salt, so next time I'd like to use 0.5 teaspoons."

[1277] The terminal transmits this feedback data to the server.

[1278] Step 6:

[1279] The server stores the received feedback data in a database.

[1280] From next time onwards, if the same user requests a recipe with the same ingredients and conditions, the recipe will be improved based on this feedback data.

[1281] This makes it possible to provide recipes optimized to the user's preferences.

[1282] 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.

[1283] MODE FOR CARRYING OUT THE INVENTION

[1284] System Overview

[1285] This system automatically generates original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and provides detailed cooking instructions.It also collects and analyzes user feedback and emotional data using an emotion engine, and reflects this in future recipe generation to always provide recipes optimized to the user's preferences.

[1286] System configuration

[1287] The system consists of the following modules:

[1288] 1. User Interface (UI) Module

[1289] 2. Recipe Generation Module

[1290] 3. Procedure Assistant Module

[1291] 4. Feedback Module

[1292] 5. Emotion Engine Module

[1293] Program processing

[1294] 1. User Interface (UI) Module

[1295] Users launch the application from their smartphone or PC and input the ingredients they want to use, the number of people they want to cook for, the desired seasoning, cooking time, etc. For example, if they want to cook two servings using chicken and green onions and have them seasoned with salt, they can enter that information.

[1296] 2. Recipe Generation Module

[1297] The device sends the conditions entered by the user to the server. Based on the received data, the server searches and retrieves past similar recipes and seasoning distribution data from a database, and generates an original recipe that best suits the conditions. For example, the server determines specific amounts such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)."

[1298] 3. Procedure Assistant Module

[1299] The server sends the generated recipe data to the device, which receives it and displays it to the user. When the user starts cooking based on the recipe, the following instructions are displayed:

[1300] 1. Cut the chicken into bite-sized pieces.

[1301] 2. Cut the green onions into 1cm wide pieces.

[1302] 3. Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes.

[1303] 4. Once the chicken is cooked through, add the green onions and stir fry for a further 3 minutes.

[1304] 5. Add salt, sake, mirin, and water, and simmer for 1 minute while stirring.

[1305] 4. Feedback Module

[1306] After the user has finished cooking, they can enter their feedback about the dish (for example, "There was too much salt, so next time I'll use 0.5 teaspoons") into the app. The device sends that feedback to the server, which stores it in a database. If the same user requests a recipe with the same ingredients and conditions from now on, an improved recipe will be generated based on the feedback information.

[1307] 5. Emotion Engine Module

[1308] When a user enters feedback, the emotion engine recognizes the user's emotions by analyzing the text entered by the user and facial and voice data captured using the camera and microphone. For example, it can determine whether the user is satisfied with the food or stressed.

[1309] The device sends the user's emotional data to the server, which analyzes and stores it. This data is taken into account when generating recipes from the next time onwards, and a more optimal recipe based on the user's emotions is provided. For example, if a user felt that the previous dish was spicy, a less spicy recipe will be suggested.

[1310] Specific examples

[1311] As a concrete example, consider a scenario in which a user creates a "chicken and green onion dish with salt sauce, serving two." First, the user selects "chicken" and "green onion" as ingredients in the app, and sets the conditions of two servings, salt sauce, and within 30 minutes. The device sends this information to the server, which then generates a recipe that meets the conditions. The generated recipe specifically calls for "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water," which the device receives and displays to the user.

[1312] The user cooks the food based on the displayed recipe and then enters feedback into the app after cooking. The emotion engine analyzes the user's emotions and evaluates their satisfaction with the food, along with comments such as "The amount of salt was too much, so next time I'll use 0.5 teaspoons." This feedback and emotion data are sent from the device to the server and are used to generate future recipes.

[1313] This allows users to always receive recipes optimized to their preferences and emotions, improving the quality and satisfaction of their cooking.The system eliminates the traditional hassle of searching for recipes and adjusting portion sizes, and can provide more specific and detailed cooking instructions and emotion-based recipe suggestions.

[1314] The processing flow will be explained below.

[1315] Step 1:

[1316] The user opens the application screen and enters the ingredients they want to use, the number of people they want to cook for, the desired seasoning, and the cooking time.

[1317] Specifically, you would make two servings using chicken and green onions, request a salty flavor, and enter "within 30 minutes."

[1318] Step 2:

[1319] The terminal receives the input data and sends it to the server.

[1320] Specifically, the entered data is sent to the server as an HTTP request (e.g., POST / generate-recipe).

[1321] Step 3:

[1322] The server receives the request and parses the received data.

[1323] Specifically, the conditions entered by the user are extracted and each field is identified.

[1324] Step 4:

[1325] The server searches the database to retrieve similar recipes and past cooking data.

[1326] Specifically, past recipe data that matches the conditions is obtained using an SQL query.

[1327] Step 5:

[1328] An original recipe is generated based on the data acquired by the server.

[1329] Specifically, it calculates the amount of ingredients and the distribution of seasonings, and creates an appropriate cooking procedure.

[1330] For example, it generates specific recipe data such as "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water."

[1331] Step 6:

[1332] The server transmits the generated recipe data to the terminal.

[1333] Specifically, the generated recipe information is returned as an HTTP response (e.g., 200 OK).

[1334] Step 7:

[1335] The device analyzes the received recipe data and displays it visually to the user.

[1336] Specifically, the recipe's ingredients, quantities, and cooking steps are displayed in detail on the screen.

[1337] Step 8:

[1338] The user cooks the food based on the displayed recipe.

[1339] Specifically, the user follows the steps presented to them to perform actions such as cutting ingredients, frying, and mixing seasonings.

[1340] Step 9:

[1341] The user completes the cooking and then enters feedback into the app about the cooking results and taste.

[1342] Specifically, write your impressions such as, "There was too much salt, so next time I'll use 0.5 teaspoon."

[1343] Step 10:

[1344] The emotion engine analyzes the feedback, facial expressions, and voice input from the user to obtain emotional data.

[1345] Specifically, the system uses a camera and microphone to capture changes in the user's tone of voice and facial expressions, and assigns emotional labels such as "satisfied" or "dissatisfied."

[1346] Step 11:

[1347] The terminal transmits the feedback data and the emotion data to the server.

[1348] Specifically, feedback and emotional data are sent to the server via an HTTP request (e.g., POST / submit-feedback).

[1349] Step 12:

[1350] The server receives the feedback data and emotion data and stores them in a database.

[1351] Specifically, feedback information and emotion data are recorded in a database using SQL INSERT statements.

[1352] Step 13:

[1353] The next time the user tries to generate a recipe under the same conditions, the server will optimize the generated recipe by taking into account past feedback data and emotion data.

[1354] Specifically, the system improves the distribution of seasonings and cooking methods based on the collected feedback and emotional data. For example, it analyzes the factors that led to low satisfaction in the previous meal and makes adjustments based on that.

[1355] Example 2

[1356] 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."

[1357] Modern consumers are faced with a wide variety of ingredients and cooking options, making it difficult to find recipes that best suit their tastes. Furthermore, existing systems do not fully utilize feedback and sentiment data from individual users, making it difficult to increase user satisfaction. The present invention aims to solve these problems by providing a system that suggests optimal recipes based on a user's individual preferences and feedback.

[1358] 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.

[1359] In this invention, the server includes means for inputting conditions such as ingredients, number of people, seasonings, and cooking time selected by the user, means for generating original recipe data based on the conditions, means for displaying detailed cooking procedures based on the generated original recipe, means for collecting feedback from the user and reflecting it in generating subsequent original recipes, and means for recognizing user emotional data and reflecting that data in generating original recipes. This makes it possible to provide recipes optimized for the preferences and emotional state of each individual user.

[1360] "User" refers to an individual who uses this system to create recipes and receive cooking instructions.

[1361] "Ingredients" refers to the ingredients selected by the user for cooking.

[1362] "Number of people" refers to data that indicates the amount of food the user is making and specifies how many people the food is for.

[1363] "Seasoning" refers to data indicating the flavor and type of seasoning the user desires for the dish.

[1364] "Cooking time" refers to data indicating the time it takes to complete the dish desired by the user.

[1365] "Original recipe" refers to unique recipe data generated based on input conditions.

[1366] "Means" refers to the technical configuration for realizing a specific function in this system.

[1367] "Feedback" refers to the ratings and opinions provided by users about the results of their cooking.

[1368] "Emotional data" refers to data obtained by analyzing a user's emotional state.

[1369] "Server" refers to the computer system that processes and stores data in this system.

[1370] "Terminal" refers to the device (e.g., smartphone or PC) used by a user to access the system.

[1371] "Database" refers to a storage device for storing and managing collected data.

[1372] "Generative AI model" refers to the artificial intelligence algorithm used to generate original recipes.

[1373] A "prompt" refers to a sentence or instruction input to a generative AI model.

[1374] This system automatically generates original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and provides detailed cooking instructions. Furthermore, the system collects and analyzes feedback and emotional data from users, and reflects this in future recipe generation, thereby providing recipes that are always optimized to the user's preferences.

[1375] System configuration

[1376] The system consists of the following modules:

[1377] 1. User Interface (UI) Module

[1378] 2. Recipe Generation Module

[1379] 3. Procedure Assistant Module

[1380] 4. Feedback Module

[1381] 5. Emotion Engine Module

[1382] Hardware and Software

[1383] The hardware used includes user devices such as smartphones and PCs, as well as servers, while the software used includes applications that provide a user interface, database software, and machine learning libraries for running generative AI models.

[1384] Program processing

[1385] The program processing in this system is as follows:

[1386] 1. User Interface (UI) Module

[1387] Users launch the application from their smartphone or PC and input the ingredients they want to use, the number of people they want to cook for, the desired seasoning, cooking time, etc. For example, they can use "chicken" and "green onions" to cook "two servings," request "salt sauce," and set the cooking time to "within 30 minutes."

[1388] 2. Recipe Generation Module

[1389] The device sends the conditions entered by the user to the server. Based on the received data, the server searches and retrieves similar past recipes and seasoning distribution data from a database, and uses a generative AI model to generate an original recipe that best suits the conditions. For example, the server determines specific amounts such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)."

[1390] 3. Procedure Assistant Module

[1391] The server sends the generated recipe data to the device, which receives it and displays it to the user. When the user starts cooking based on the recipe, the following instructions are displayed:

[1392] 1. Cut the chicken into bite-sized pieces.

[1393] 2. Cut the green onions into 1cm wide pieces.

[1394] 3. Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes.

[1395] 4. Once the chicken is cooked through, add the green onions and stir fry for a further 3 minutes.

[1396] 5. Add salt, sake, mirin, and water, and simmer for 1 minute while stirring.

[1397] 4. Feedback Module

[1398] After the user has finished cooking, they can enter feedback about the dish into the app. For example, they can enter feedback such as, "There was too much salt, so next time I'll use 0.5 teaspoons."

[1399] 5. Emotion Engine Module

[1400] When a user enters feedback, the emotion engine recognizes the user's emotions by analyzing the text entered by the user and facial and voice data captured using the camera and microphone. For example, it can determine whether the user is satisfied with the food or stressed.

[1401] Specific examples

[1402] As a concrete example, consider a scenario in which a user makes a dish for two people using chicken and green onions with a salt sauce. The user selects "chicken" and "green onions" as ingredients in the app and sets the conditions of two servings, salt sauce, and within 30 minutes. The device sends this information to the server, which then generates a recipe that meets the conditions. The generated recipe consists of "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water," which the device receives and displays to the user. The user cooks the food based on the displayed recipe and enters feedback into the app after cooking. At this time, the emotion engine analyzes the user's emotions and evaluates the user's level of satisfaction, along with comments such as "The amount of salt was too much, so next time I'll use 0.5 teaspoons." This feedback and emotion data are sent from the device to the server and used to generate future recipes.

[1403] Prompt Sentence Examples

[1404] An example of a prompt to input to a generative AI model is as follows:

[1405] You are in charge of programming a cooking recipe generation system. Your task is to automatically generate the optimal recipe for a user to make "Chicken and green onion dish with salt sauce, for two people." You must provide specific ingredients and steps, and take into account the user's past feedback and sentiment data.

[1406] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1407] Step 1:

[1408] The user interface (UI) module allows users to launch the application from their smartphone or PC. Users input conditions such as the ingredients they want to use, the number of people they want to cook for, the desired seasoning, and cooking time. For example, a user might select "chicken" and "green onions" as ingredients, cook "two servings," request "salt sauce," and set the cooking time to "within 30 minutes."

[1409] Input: The user enters the condition.

[1410] Output: The format in which the input data is formatted and sent to the server (e.g. JSON data).

[1411] Step 2:

[1412] The device sends the conditions entered by the user to the server. The sent data is accurately passed to the server in JSON format, etc.

[1413] Input: Data entered by the user.

[1414] Output: The formatted data that is sent to the server.

[1415] Specific operation: Press the "Send" button on the terminal. When the "Send" button is pressed, the input data is validated. Data that passes validation is sent to the server.

[1416] Step 3:

[1417] Based on the data received by the server, the database is searched for and retrieved from the server similar recipes and seasoning distribution data from the past. This data is then used by a generative AI model to generate an original recipe that best suits the conditions.

[1418] Input: Formatted condition data.

[1419] Output: The generated original recipe data.

[1420] Specific operations: The server analyzes the received data, searches for related data from the database to retrieve similar recipes, and uses a generative AI model to create the optimal recipe.

[1421] Step 4:

[1422] The server transmits the generated recipe data to the terminal, which receives it and displays it to the user.

[1423] Input: Generated original recipe data.

[1424] Output: Recipe information displayed to the user.

[1425] Specific operation: The server sends the generated recipe data in JSON format. The device receives the recipe data and displays it on the interface. The recipe includes specific ingredient amounts and cooking instructions.

[1426] Step 5:

[1427] The user starts cooking based on the displayed recipe, and the step-by-step instructions are provided by the step-by-step assistant module.

[1428] Input: User confirms cooking instructions.

[1429] Output: Specific instructions for the user to proceed with the cooking.

[1430] How it works: Each cooking step is displayed on the recipe screen. The user proceeds with the cooking process while checking each step. The screen is updated as the cooking process progresses.

[1431] Step 6:

[1432] After the user has finished cooking, they can enter their feedback on the dish into the app, such as "I added too much salt, so next time I'll use 0.5 teaspoons."

[1433] Input: Post-cooking feedback.

[1434] Output: Formatted feedback data.

[1435] Specific operation: After cooking is complete, the user enters comments on the feedback screen that appears, and inputs emotional data (such as satisfaction and stress levels).

[1436] Step 7:

[1437] The device sends feedback to the server, which stores the feedback data in a database and uses it to generate future recipes.

[1438] Input: Formatted feedback data.

[1439] Output: Feedback data stored in a database.

[1440] Specific operation: Press the feedback sending button. Feedback and emotion data will be sent together.

[1441] Step 8:

[1442] The server uses an emotion engine to analyze and store the user's emotion data. The analysis results are taken into account when generating recipes from the next time onwards.

[1443] Input: Feedback data and emotion data.

[1444] Output: Parsed emotion data.

[1445] Specific operation: The server analyzes the received emotion data. The emotion engine evaluates the satisfaction and stress levels. The evaluation results are stored in a database.

[1446] (Application example 2)

[1447] 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."

[1448] Conventional recipe generation systems simply generate recipes based on ingredients and seasoning conditions, and are unable to fully reflect users' specific emotions and feedback. This has led to a demand for systems that can provide recipes that fully satisfy users. Furthermore, the lack of an efficient recipe generation and cooking instruction system that can be used in brick-and-mortar establishments such as restaurants has made it difficult to develop new dishes and streamline kitchen operations.

[1449] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1450] In this invention, the server includes a means for inputting user-selected conditions such as ingredients, number of people, seasonings, and cooking time, a means for generating original recipe data based on the conditions, a means for displaying detailed cooking steps based on the generated original recipe, a means for collecting user feedback and reflecting the feedback in subsequent recipe generation, and a means for analyzing user emotion data and optimizing the recipe based on the user's emotion. This makes it possible to provide optimized recipes that reflect the user's emotion and feedback. This can also contribute to the development of new dishes in restaurants and the efficiency of kitchen operations.

[1451] "Ingredients, number of people, seasoning, and cooking time" are items that the user selects when creating a recipe, and the combination of these is an important factor in determining the specific recipe.

[1452] "Original recipe data" refers to recipe data that the system automatically generates based on conditions specified by the user, and may also be generated based on past recipe data or seasoning distribution data.

[1453] The "means for displaying detailed cooking steps" is a function for displaying specific and detailed steps for the user to actually prepare a dish based on the generated original recipe.

[1454] "Means of collecting feedback and reflecting it in future recipe generation" refers to a function that allows users to input their impressions and suggestions for improvement after actually cooking into the system, which then stores them in a database for use when generating the next recipe.

[1455] "Means for analyzing emotional data and optimizing recipes based on the user's emotions" refers to a function that allows the emotion engine to recognize and analyze the user's emotions when they enter feedback, and then use that data to optimize future recipe suggestions.

[1456] A "restaurant" is a place where users can eat, and is a general concept that encompasses store formats such as restaurants and cafes.

[1457] This invention is a system that automatically generates original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and provides detailed cooking instructions. This system consists of five main modules: a user interface (UI) module, a recipe generation module, a step assistant module, a feedback module, and an emotion engine module.

[1458] 1. User Interface (UI) Module

[1459] It is a means for users to launch an application on their smartphone or tablet device and input conditions such as ingredients, number of people, seasoning, cooking time, etc. For example, when a restaurant chef creates a new dish, if he or she wants to use "chicken" and "green onion" to make "two servings" and "salt sauce" and wants it to be "salted," the function is provided to input this information.

[1460] 2. Recipe Generation Module

[1461] The terminal sends the conditions entered by the user to the server. Based on the received data, the server searches and retrieves similar past recipes and seasoning distribution data from a database, and generates an original recipe that best suits the conditions. For example, the server determines specific amounts such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)." Backend processing using Python and Flask is performed during this process.

[1462] 3. Procedure Assistant Module

[1463] The server sends the generated recipe data to the device, which receives it and displays it to the user. When the user starts cooking based on the recipe, detailed cooking instructions are displayed in real time. Specifically, instructions such as "Cut the chicken into bite-sized pieces," "Cut the green onions into 1cm pieces," "Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes," "Once the chicken is cooked through, add the green onions and fry for another 3 minutes," and "Add salt, sake, mirin, and water, and simmer for 1 minute while mixing everything together" are displayed.

[1464] 4. Feedback Module

[1465] After the user has finished cooking, they can enter their feedback on the dish from their device and send it to the server. For example, they can provide feedback such as, "I added too much salt, so next time I'll use 0.5 teaspoons." The server stores this feedback in a database and uses it to generate future recipes.

[1466] 5. Emotion Engine Module

[1467] When a user enters feedback, the emotion engine recognizes and analyzes the user's emotions. This emotion recognition is performed by analyzing the text entered by the user and facial expressions and voice data acquired using a camera or microphone. The server analyzes and saves the user's emotion data, and takes this into consideration when generating recipes from the next time onwards, allowing it to provide more optimal recipes based on the user's emotions.

[1468] Specific examples

[1469] A restaurant chef opens an application to create a new dish and enters the following criteria:

[1470] Ingredients: chicken, green onion

[1471] Number of people: 2 servings

[1472] Seasoning: Salt sauce

[1473] Cooking time: 30 minutes

[1474] The system generates a recipe based on this information and displays cooking instructions. After the chef has finished cooking, they can enter their feedback, which is then analyzed by the emotion engine. This data is then used to generate future recipes.

[1475] Prompt Sentence Examples

[1476] A chef is looking for a recipe for a new dish. Generate a recipe based on the following criteria and provide detailed cooking instructions:

[1477] Ingredients: chicken, green onion

[1478] Number of people: 2 servings

[1479] Seasoning: Salt sauce

[1480] Cooking time: 30 minutes

[1481] In addition, feedback and emotional data after cooking is completed will be taken into consideration and reflected in future recipe suggestions.

[1482] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1483] Step 1:

[1484] Users launch the application on their smartphone or tablet and input the ingredients, number of people, seasoning, cooking time, etc. Specifically, a restaurant chef would input the following conditions: "chicken," "green onion," "serves two," "salt sauce," and "30 minutes."

[1485] Input: ingredients, number of people, seasoning, cooking time

[1486] Output: Condition data

[1487] Step 2:

[1488] The device sends the entered condition data to the server. Based on the received data, the server searches and retrieves past similar recipes and seasoning distribution data from a database, and generates an original recipe that best suits the conditions. Specifically, the server determines the specific amounts of ingredients, such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)."

[1489] Input: Condition data

[1490] Data processing: database search, retrieval of similar recipes, generation of original recipes

[1491] Output: Generated recipe data

[1492] Step 3:

[1493] The server sends the generated recipe data to the device, which receives it and displays it to the user. The user then begins cooking based on the displayed recipe data. Specific instructions are displayed, such as "Cut the chicken into bite-sized pieces," "Cut the green onions into 1cm pieces," and "Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes."

[1494] Input: Generated recipe data

[1495] Data processing: None

[1496] Output: Display of cooking instructions

[1497] Step 4:

[1498] After the user has finished cooking, they can input their feedback about the dish and send it to the server from their device. For example, they might say, "I added too much salt, so next time I'll use 0.5 teaspoons." The server stores this feedback in a database and uses it to generate future recipes.

[1499] Input: User feedback

[1500] Data processing: Accumulation in the database, reflection in next recipe generation

[1501] Output: Accumulated feedback data

[1502] Step 5:

[1503] When a user enters feedback, the emotion engine recognizes and analyzes the user's emotions. It analyzes facial expressions and voice data captured using a camera and microphone to determine whether the user is satisfied with the cooking or stressed. The server analyzes and saves the emotion data and takes it into consideration when generating recipes in the future.

[1504] Input: Feedback text, facial expression data, voice data

[1505] Data processing: text analysis, facial expression and voice analysis, emotion data generation

[1506] Output: Parsed emotion data

[1507] Step 6:

[1508] The server uses the accumulated feedback data and analyzed emotion data and takes this information into account when generating new recipes, so that future recipes will be further optimized based on the user's emotions and feedback.

[1509] Input: Accumulated feedback data, analyzed emotion data

[1510] Data processing: Integrating feedback and sentiment data and reflecting it in recipe generation

[1511] Output: New optimized recipe data

[1512] 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.

[1513] 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.

[1514] 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.

[1515] [Fourth embodiment]

[1516] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1517] 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.

[1518] 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).

[1519] 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.

[1520] 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.

[1521] 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).

[1522] 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.

[1523] 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.

[1524] 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.

[1525] 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.

[1526] 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.

[1527] 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.

[1528] 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."

[1529] MODE FOR CARRYING OUT THE INVENTION

[1530] System Overview

[1531] This system automatically generates original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and provides detailed cooking instructions. It also collects user feedback and reflects it in future recipe generation to always provide recipes optimized to the user's preferences.

[1532] System configuration

[1533] The system is broadly composed of the following modules:

[1534] 1. User Interface (UI) Module

[1535] 2. Recipe Generation Module

[1536] 3. Procedure Assistant Module

[1537] 4. Feedback Module

[1538] Program processing

[1539] 1. User Interface (UI) Module

[1540] Users launch the application from their smartphone or PC and input the ingredients they want to use, the number of people they want to cook for, the desired seasoning, cooking time, etc. For example, if they want to cook two servings using chicken and green onions and have them seasoned with salt, they can enter that information.

[1541] 2. Recipe Generation Module

[1542] The device sends the conditions entered by the user to the server. Based on the received data, the server searches and retrieves past similar recipes and seasoning distribution data from a database, and generates an original recipe that best suits the conditions. For example, the server determines specific amounts such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)."

[1543] 3. Procedure Assistant Module

[1544] The server sends the generated recipe data to the device, which receives it and displays it to the user. When the user starts cooking based on the recipe, instructions are displayed, for example, as follows:

[1545] 1. Cut the chicken into bite-sized pieces.

[1546] 2. Cut the green onions into 1cm wide pieces.

[1547] 3. Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes.

[1548] 4. Once the chicken is cooked through, add the green onions and stir fry for a further 3 minutes.

[1549] 5. Add salt, sake, mirin, and water, and simmer for 1 minute while stirring.

[1550] 4. Feedback Module

[1551] After the user has finished cooking, they can enter their feedback about the dish (for example, "There was too much salt, so next time I'll use 0.5 teaspoons") into the app. The device sends that feedback to the server, which stores it in a database. If the same user requests a recipe with the same ingredients and conditions from now on, an improved recipe will be generated based on the feedback information.

[1552] Specific examples

[1553] As a concrete example, consider a scenario in which a user prepares a dish for two people using chicken and green onions with a salt sauce. First, the user selects "chicken" and "green onions" as ingredients in the app, and sets the conditions of two servings, salt sauce, and within 30 minutes. The device sends this information to the server, which then generates a recipe that meets the conditions. The generated recipe specifically includes "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water," which the device receives and displays to the user. The user cooks according to the instructions, and after cooking, enters feedback into the app. This feedback is used to generate future recipes.

[1554] This allows users to always receive recipes optimized to their preferences. The system eliminates the traditional hassle of searching for recipes and adjusting portions, and provides more specific and detailed cooking instructions.

[1555] The processing flow will be explained below.

[1556] Step 1:

[1557] The user opens the application screen and enters the ingredients they want to use, the number of people they want to cook for, the desired seasoning, and the cooking time.

[1558] Specifically, you would make two servings using chicken and green onions, request a salty flavor, and enter "within 30 minutes."

[1559] Step 2:

[1560] The terminal receives the input data and sends it to the server.

[1561] Specifically, the data is sent to the server as an HTTP request (e.g., POST / generate-recipe).

[1562] Step 3:

[1563] The server receives the request and parses the received data.

[1564] Specifically, the conditions entered by the user are extracted and each field is identified.

[1565] Step 4:

[1566] The server searches the database to retrieve similar recipes and past cooking data.

[1567] Specifically, past recipe data that matches the conditions is obtained using an SQL query.

[1568] Step 5:

[1569] An original recipe is generated based on the data acquired by the server.

[1570] Specifically, it calculates the amount of ingredients and the distribution of seasonings, and creates an appropriate cooking procedure.

[1571] For example, it generates specific recipe data such as "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water."

[1572] Step 6:

[1573] The server transmits the generated recipe data to the terminal.

[1574] Specifically, the generated recipe information is returned as an HTTP response (e.g., 200 OK).

[1575] Step 7:

[1576] The device analyzes the received recipe data and displays it visually to the user.

[1577] Specifically, the recipe's ingredients, quantities, and cooking steps are displayed in detail on the screen.

[1578] Step 8:

[1579] The user cooks the food based on the displayed recipe.

[1580] Specifically, the user follows the steps presented to them and performs actions such as cutting ingredients, frying, and mixing seasonings.

[1581] Step 9:

[1582] The user completes the cooking and then enters feedback into the app about the cooking results and taste.

[1583] Specifically, write your impressions such as, "There was too much salt, so next time I'll use 0.5 teaspoon."

[1584] Step 10:

[1585] The terminal transmits the feedback data to the server.

[1586] Specifically, feedback is sent to the server via an HTTP request (e.g., POST / submit-feedback).

[1587] Step 11:

[1588] The server receives the feedback and stores it in a database.

[1589] Specifically, the feedback information is recorded in the database using an SQL INSERT statement.

[1590] Step 12:

[1591] The next time the user tries to generate a recipe under the same conditions, the server will optimize the generated recipe taking into account past feedback data.

[1592] Specifically, the distribution of seasonings and cooking methods will be improved based on the collected feedback.

[1593] Example 1

[1594] 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."

[1595] Conventional recipe search systems require users to adjust the exact amounts of ingredients and seasonings, and it is difficult to reflect user preferences and feedback in the next recipe. This means that users have to either repeat the same operations every time or spend time adjusting the recipe themselves. This reduces convenience and reduces user satisfaction.

[1596] 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.

[1597] In this invention, the server includes a means for a user to input conditions such as ingredients, number of people, seasonings, and cooking time, a means for using a generative AI model to generate original recipe data based on the conditions, a means for displaying detailed cooking steps based on the generated original recipe, and a means for collecting feedback from the user in the form of prompt sentences and reflecting this in subsequent recipe generation. This allows a user to simply input conditions to automatically generate an original recipe optimized to their preferences and receive detailed cooking steps, and further enables subsequent recipes to be improved based on the feedback.

[1598] "User" refers to an individual who intends to use the system to generate a recipe.

[1599] "Ingredients" refers to the ingredients that a user selects to use in a recipe.

[1600] "Number of people" refers to the number of people used to determine the amount of food the user will cook.

[1601] "Seasoning" refers to the flavor and type of seasoning the user desires for the dish.

[1602] "Cooking time" refers to the maximum cooking time desired by the user.

[1603] "Conditions" refers to the ingredients, number of people, seasonings, and cooking time input by the user.

[1604] "Original recipe data" refers to recipe information that is automatically generated based on conditions entered by the user.

[1605] "Generative AI Model" refers to an artificial intelligence model used to generate original recipe data based on conditions.

[1606] "Detailed cooking instructions" refers to specific, step-by-step cooking methods based on the original recipe data.

[1607] "Feedback" refers to the evaluation and suggestions for improvement that users provide to the system after cooking.

[1608] A "prompt sentence" refers to a sentence entered by a user that describes the requests and conditions for recipe generation.

[1609] "Database" refers to a data storage system for accumulating past similar recipes, seasoning distribution data, and user feedback data.

[1610] MODE FOR CARRYING OUT THE INVENTION

[1611] System Overview

[1612] The system of the present invention automatically generates original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and provides detailed cooking instructions. Furthermore, by collecting feedback from the user and reflecting it in future recipe generation, the system always provides recipes optimized to the user's preferences.

[1613] System configuration

[1614] This system is broadly composed of the following modules:

[1615] 1. User Interface (UI) Module

[1616] 2. Data sending and receiving module

[1617] 3. Recipe Generation Module

[1618] 4. Cooking procedure assistant module

[1619] 5. Feedback Module

[1620] User Interface (UI) Module

[1621] Users launch the application from their smartphone or PC and input the ingredients they want to use, the number of people they want to cook for, the desired seasoning, cooking time, etc. For example, if they want to cook two servings using chicken and green onions and have them seasoned with salt, they can enter that information.

[1622] Data sending and receiving modules

[1623] The device sends the conditions entered by the user to the server. The communication protocol is HTTP, and the input data is structured in JSON format. A POST request is sent to the server, and the transmitted content includes information on ingredients, number of people, seasoning, and cooking time.

[1624] Recipe Generation Module

[1625] The server analyzes the received data and searches and retrieves similar past recipes and seasoning distribution data from a database. Using a generative AI model, an original recipe that best suits the input conditions is generated. At this time, the amounts of ingredients and the distribution of seasonings are also calculated. For example, the required amounts may be determined as "200g of chicken," "1 scallion," "1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, and 50ml of water."

[1626] Cooking procedure assistant module

[1627] The server sends the generated recipe data to the device, which receives it and displays it to the user, along with detailed instructions, when the user starts cooking based on the recipe.

[1628] Feedback Module

[1629] After the user has finished cooking, they can enter their feedback on the dish into the app. For example, they can write a comment such as, "There was too much salt, so next time I'll use 0.5 teaspoons." The device sends this feedback to the server, which stores it in a database. If the same user requests a recipe with the same ingredients and conditions from now on, an improved recipe will be generated based on the feedback information.

[1630] Specific examples

[1631] As a concrete example, consider a scenario in which a user prepares a dish for two people using chicken and green onions with a salt sauce. First, the user selects "chicken" and "green onions" as ingredients in the app, and sets the conditions of two servings, salt sauce, and within 30 minutes. The device sends this information to the server, which then generates a recipe that meets the conditions. The generated recipe specifically includes "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water," which the device receives and displays to the user. The user cooks according to the instructions, and after cooking, enters feedback into the app. This feedback is used to generate future recipes.

[1632] (Example prompt)

[1633] "Generate a recipe for two servings of chicken and green onion with a salt sauce in 30 minutes or less."

[1634] Hardware and software used

[1635] The hardware used includes the devices used by users (smartphones and PCs) and the servers for processing and storing data.The software used includes front-end frameworks (e.g., React, Vue.js) for building user interfaces, back-end frameworks (e.g., Node.js, Django) for sending and receiving data, and machine learning libraries (e.g., TensorFlow, PyTorch) for running generative AI models.

[1636] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1637] Step 1: The user inputs the ingredients, number of people, seasonings, and cooking time.

[1638] The user launches the application from their smartphone or PC and inputs the ingredients they want to use (e.g., chicken, green onions), the number of people they want to cook for (e.g., two servings), the desired seasoning (e.g., salt sauce), and the cooking time (e.g., within 30 minutes). This information is structured in JSON format.

[1639] Input: Ingredients, number of people, seasoning, cooking time

[1640] Output: Input data in JSON format

[1641] Specific working example:

[1642] The user enters conditions into each input field and clicks the submit button.

[1643] Step 2: The device sends the input data to the server

[1644] The device sends the JSON format data entered by the user to the server using the HTTP POST request as the communication protocol.

[1645] Input: Input data in JSON format

[1646] Output: Data sent as an HTTP POST request

[1647] Specific working example:

[1648] The data received by the terminal is sent as the payload of the POST request.

[1649] Step 3: The server receives and parses the data

[1650] The server receives the HTTP POST request, retrieves the data sent from the payload, and analyzes it to extract the ingredients, number of people, seasoning, and cooking time.

[1651] Input: JSON format data included in the POST request

[1652] Output: Parsed condition data

[1653] Specific working example:

[1654] The server extracts JSON data from the request body and breaks it down according to conditions.

[1655] Step 4: The server searches the database and retrieves the required recipe information.

[1656] Based on the analyzed condition data, the server searches and retrieves similar past recipes and seasoning distribution data from the database.

[1657] Input: Parsed condition data

[1658] Output: Past similar recipes and seasoning distribution data

[1659] Specific working example:

[1660] The server queries the database based on ingredients, number of people, seasonings, and cooking time.

[1661] Step 5: The server generates an original recipe using the generative AI model

[1662] The server inputs the acquired data into a generative AI model to generate an original recipe that best suits the conditions. The model also calculates the amount of ingredients and the distribution of seasonings.

[1663] Input: Previously acquired similar recipes and seasoning distribution data

[1664] Output: Original recipe data

[1665] Specific working example:

[1666] The server passes the input data to the generative AI model to generate the optimal recipe.

[1667] Step 6: The server sends the original recipe data to the terminal.

[1668] The server converts the generated original recipe data into JSON format and sends it to the terminal.

[1669] Input: Original recipe data

[1670] Output: Original recipe data in JSON format

[1671] Specific working example:

[1672] The server encodes the generated recipe data and sends it to the terminal.

[1673] Step 7: The device displays the original recipe data to the user

[1674] The device analyzes the original recipe data received and displays it on the user interface. The recipe also includes detailed cooking instructions.

[1675] Input: Original recipe data in JSON format

[1676] Output: Recipe information displayed in the user interface

[1677] Specific working example:

[1678] The device analyzes the recipe data and displays it visually.

[1679] Step 8: User completes cooking and provides feedback

[1680] After the user has finished cooking, they can enter feedback into the application, for example, "There was too much salt" or "Next time I'll use 0.5 teaspoon."

[1681] Input: User feedback information

[1682] Output: Feedback data in JSON format

[1683] Specific working example:

[1684] A user enters a comment in the feedback section within the app and clicks the submit button.

[1685] Step 9: The device sends the feedback data to the server

[1686] The device sends the feedback data entered by the user to the server, which is also sent in JSON format.

[1687] Input: Feedback data in JSON format

[1688] Output: Feedback data as an HTTP POST request

[1689] Specific working example:

[1690] The feedback received by the device is sent as the payload of the POST request.

[1691] Step 10: The server receives the feedback data and stores it in a database.

[1692] The server analyzes the received feedback data and stores it in a database, which is then reflected in future recipe generation.

[1693] Input: Feedback data in JSON format included in a POST request

[1694] Output: Feedback data stored in a database

[1695] Specific working example:

[1696] The server stores the feedback in a database and uses it to generate future recipes.

[1697] (Application example 1)

[1698] 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."

[1699] Conventional recipe generation systems simply generate original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and then provide cooking instructions, which can be time-consuming when actually cooking. While there was a function to improve the recipe for future meals based on feedback, there was a lack of means to automate the cooking process, making it difficult to efficiently serve delicious food. Furthermore, in large facilities such as cafeterias and factories, the time and effort required to manually prepare meals for large numbers of people was a particular problem.

[1700] 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.

[1701] In this invention, the server includes means for inputting user-selected conditions (ingredients, number of people, seasonings, and cooking time), means for generating original recipe data based on the conditions, means for displaying detailed cooking steps based on the generated original recipe, means for collecting user feedback and reflecting it in subsequent recipe generation, and means for transmitting the original recipe data and cooking steps to an automatic cooking device, which then executes the cooking. This makes it possible to automatically cook dishes based on the generated recipe, making it possible to efficiently provide delicious dishes even in large-scale facilities.

[1702] "User" means an individual or entity that uses the system to generate recipes and prepare food.

[1703] "Ingredients" refer to the ingredients and seasonings used to make a dish.

[1704] "Number of people" refers to the number of people to whom food is being served.

[1705] "Seasoning" refers to the seasonings and cooking methods used to adjust the flavor and taste of a dish.

[1706] "Cooking time" refers to the time required to complete a dish.

[1707] "Conditions" refers collectively to the ingredients, number of people, seasonings, and cooking time selected by the user.

[1708] "Original recipe data" refers to recipe data generated based on conditions entered by the user.

[1709] "Cooking procedure" refers to the cooking steps that are specifically instructed based on the original recipe data.

[1710] "Feedback" refers to the opinions and ratings provided by users after cooking.

[1711] An "automatic cooking device" is a device that automatically cooks food based on input cooking instructions.

[1712] A "server" is a computer system that receives user input, generates recipes, displays cooking instructions, and sends instructions to the automated cooking device.

[1713] A "database" is an information storage system for accumulating past recipe data and user feedback data.

[1714] System Overview

[1715] This invention is a system that works in conjunction with an automatic cooking device to generate original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and then automatically cooks based on those recipes. It also aims to collect feedback from users and reflect it in future recipe generation, thereby always providing dishes that are optimized to the user's preferences.

[1716] System configuration

[1717] The system is broadly composed of the following modules:

[1718] 1. User Interface (UI) Module

[1719] 2. Recipe Generation Module

[1720] 3. Cooking instruction sending module

[1721] 4. Feedback Module

[1722] Program processing explanation

[1723] 1. User Interface (UI) Module

[1724] Users launch the application on their smartphone or tablet and input the ingredients they want to use, the number of people they want to cook for, the desired seasoning, cooking time, etc. For example, if they want to cook two servings of chicken and green onions and have them seasoned with salt, they can input that information in this interface.

[1725] 2. Recipe Generation Module

[1726] The device sends the conditions entered by the user to the server. Based on the received data, the server searches and retrieves past similar recipes and seasoning distribution data from a database, and generates an original recipe that best suits the conditions. For example, the server determines specific amounts such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)."

[1727] 3. Cooking instruction sending module

[1728] The server sends the generated recipe data and cooking instructions to the automatic cooking device, which then starts cooking based on the instructions. For example, the following cooking instructions may be sent:

[1729] 1. Cut the chicken into bite-sized pieces.

[1730] 2. Cut the green onions into 1cm wide pieces.

[1731] 3. Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes.

[1732] 4. Once the chicken is cooked through, add the green onions and stir fry for a further 3 minutes.

[1733] 5. Add salt, sake, mirin, and water, and simmer for 1 minute while stirring.

[1734] 4. Feedback Module

[1735] After the user has finished cooking, they can enter their feedback about the dish (for example, "There was too much salt, so next time I'll use 0.5 teaspoons") into the app. The device sends that feedback to the server, which stores it in a database. If the same user requests a recipe with the same ingredients and conditions from now on, an improved recipe will be generated based on the feedback information.

[1736] Hardware and Software

[1737] Hardware: Automated cooking equipment in factories (e.g., general-purpose cooking robots)

[1738] Software: Recipe generation API (e.g., built with Flask or Django), robot control API (API endpoints supporting HTTP requests)

[1739] Specific examples

[1740] The factory cafeteria manager uses his smartphone to enter the following:

[1741] Ingredients: Chicken, green onion

[1742] Number of people: 2 servings

[1743] Seasoning: Salt sauce

[1744] Cooking time: 30 minutes

[1745] Based on this, a request is sent to the recipe generation API, and the generated recipe is sent to the automatic cooking device. The automatic cooking device starts cooking according to the instructions, and once finished, the "stir-fried chicken and green onions with salt sauce" is served.

[1746] Prompt Sentence Examples

[1747] Ingredients: Chicken, Green onion, Serves: 2, Seasoning: Salt, Cooking time: 30 minutes. Generate the best recipe based on your criteria.

[1748] This will enable efficient and high-quality food provision even in large locations such as factories.

[1749] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1750] Step 1:

[1751] Users launch the application on their smartphone or tablet and enter information such as the ingredients they want to use, the number of people they want to cook for, the desired seasoning, and cooking time.

[1752] The conditions entered were ingredients "chicken, green onion", serving size "2 servings", seasoning "salt sauce", and cooking time "30 minutes".

[1753] The terminal converts this input data into JSON format and sends it to the server.

[1754] Step 2:

[1755] The server analyzes the received input data and, based on that, searches and retrieves past similar recipes and seasoning distribution data from a database.

[1756] The server uses popular Python libraries (e.g., Pandas, SQLAlchemy) to perform data retrieval.

[1757] The server generates original recipe data based on the search results.

[1758] For example, you would decide on specific amounts of ingredients such as "200g chicken, 1 green onion" and seasonings such as "1 teaspoon salt, 1 tablespoon sake, 1 tablespoon mirin, 50ml water."

[1759] Step 3:

[1760] The server converts the generated original recipe data and specific cooking instructions into JSON format and returns it to the terminal.

[1761] The returned data includes specific cooking instructions:

[1762] 1. Cut the chicken into bite-sized pieces.

[1763] 2. Cut the green onions into 1cm wide pieces.

[1764] 3. Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes.

[1765] 4. Once the chicken is cooked through, add the green onions and stir fry for a further 3 minutes.

[1766] 5. Add salt, sake, mirin, and water, and simmer for 1 minute while stirring.

[1767] Step 4:

[1768] The terminal transmits the received original recipe data and cooking instructions to the automatic cooking device.

[1769] This is done using an HTTP request (e.g., an HTTP POST request).

[1770] The automatic cooking device automatically starts cooking based on the transmitted cooking instructions.

[1771] Step 5:

[1772] After the user has finished cooking, they can enter their feedback on the dish into the app.

[1773] For example, you can enter a specific opinion such as, "There was too much salt, so next time I'd like to use 0.5 teaspoons."

[1774] The terminal transmits this feedback data to the server.

[1775] Step 6:

[1776] The server stores the received feedback data in a database.

[1777] From next time onwards, if the same user requests a recipe with the same ingredients and conditions, the recipe will be improved based on this feedback data.

[1778] This makes it possible to provide recipes optimized to the user's preferences.

[1779] 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.

[1780] MODE FOR CARRYING OUT THE INVENTION

[1781] System Overview

[1782] This system automatically generates original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and provides detailed cooking instructions.It also collects and analyzes user feedback and emotional data using an emotion engine, and reflects this in future recipe generation to always provide recipes optimized to the user's preferences.

[1783] System configuration

[1784] The system consists of the following modules:

[1785] 1. User Interface (UI) Module

[1786] 2. Recipe Generation Module

[1787] 3. Procedure Assistant Module

[1788] 4. Feedback Module

[1789] 5. Emotion Engine Module

[1790] Program processing

[1791] 1. User Interface (UI) Module

[1792] Users launch the application from their smartphone or PC and input the ingredients they want to use, the number of people they want to cook for, the desired seasoning, cooking time, etc. For example, if they want to cook two servings using chicken and green onions and have them seasoned with salt, they can enter that information.

[1793] 2. Recipe Generation Module

[1794] The device sends the conditions entered by the user to the server. Based on the received data, the server searches and retrieves past similar recipes and seasoning distribution data from a database, and generates an original recipe that best suits the conditions. For example, the server determines specific amounts such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)."

[1795] 3. Procedure Assistant Module

[1796] The server sends the generated recipe data to the device, which receives it and displays it to the user. When the user starts cooking based on the recipe, the following instructions are displayed:

[1797] 1. Cut the chicken into bite-sized pieces.

[1798] 2. Cut the green onions into 1cm wide pieces.

[1799] 3. Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes.

[1800] 4. Once the chicken is cooked through, add the green onions and stir fry for a further 3 minutes.

[1801] 5. Add salt, sake, mirin, and water, and simmer for 1 minute while stirring.

[1802] 4. Feedback Module

[1803] After the user has finished cooking, they can enter their feedback about the dish (for example, "There was too much salt, so next time I'll use 0.5 teaspoons") into the app. The device sends that feedback to the server, which stores it in a database. If the same user requests a recipe with the same ingredients and conditions from now on, an improved recipe will be generated based on the feedback information.

[1804] 5. Emotion Engine Module

[1805] When a user enters feedback, the emotion engine recognizes the user's emotions by analyzing the text entered by the user and facial and voice data captured using the camera and microphone. For example, it can determine whether the user is satisfied with the food or stressed.

[1806] The device sends the user's emotional data to the server, which analyzes and stores it. This data is taken into account when generating recipes from the next time onwards, and a more optimal recipe based on the user's emotions is provided. For example, if a user felt that the previous dish was spicy, a less spicy recipe will be suggested.

[1807] Specific examples

[1808] As a concrete example, consider a scenario in which a user creates a "chicken and green onion dish with salt sauce, serving two." First, the user selects "chicken" and "green onion" as ingredients in the app, and sets the conditions of two servings, salt sauce, and within 30 minutes. The device sends this information to the server, which then generates a recipe that meets the conditions. The generated recipe specifically calls for "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water," which the device receives and displays to the user.

[1809] The user cooks the food based on the displayed recipe and then enters feedback into the app after cooking. The emotion engine analyzes the user's emotions and evaluates their satisfaction with the food, along with comments such as "The amount of salt was too much, so next time I'll use 0.5 teaspoons." This feedback and emotion data are sent from the device to the server and are used to generate future recipes.

[1810] This allows users to always receive recipes optimized to their preferences and emotions, improving the quality and satisfaction of their cooking.The system eliminates the traditional hassle of searching for recipes and adjusting portion sizes, and can provide more specific and detailed cooking instructions and emotion-based recipe suggestions.

[1811] The processing flow will be explained below.

[1812] Step 1:

[1813] The user opens the application screen and enters the ingredients they want to use, the number of people they want to cook for, the desired seasoning, and the cooking time.

[1814] Specifically, you would make two servings using chicken and green onions, request a salty flavor, and enter "within 30 minutes."

[1815] Step 2:

[1816] The terminal receives the input data and sends it to the server.

[1817] Specifically, the entered data is sent to the server as an HTTP request (e.g., POST / generate-recipe).

[1818] Step 3:

[1819] The server receives the request and parses the received data.

[1820] Specifically, the conditions entered by the user are extracted and each field is identified.

[1821] Step 4:

[1822] The server searches the database to retrieve similar recipes and past cooking data.

[1823] Specifically, past recipe data that matches the conditions is obtained using an SQL query.

[1824] Step 5:

[1825] An original recipe is generated based on the data acquired by the server.

[1826] Specifically, it calculates the amount of ingredients and the distribution of seasonings, and creates an appropriate cooking procedure.

[1827] For example, it generates specific recipe data such as "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water."

[1828] Step 6:

[1829] The server transmits the generated recipe data to the terminal.

[1830] Specifically, the generated recipe information is returned as an HTTP response (e.g., 200 OK).

[1831] Step 7:

[1832] The device analyzes the received recipe data and displays it visually to the user.

[1833] Specifically, the recipe's ingredients, quantities, and cooking steps are displayed in detail on the screen.

[1834] Step 8:

[1835] The user cooks the food based on the displayed recipe.

[1836] Specifically, the user follows the steps presented to them to perform actions such as cutting ingredients, frying, and mixing seasonings.

[1837] Step 9:

[1838] The user completes the cooking and then enters feedback into the app about the cooking results and taste.

[1839] Specifically, write your impressions such as, "There was too much salt, so next time I'll use 0.5 teaspoon."

[1840] Step 10:

[1841] The emotion engine analyzes the feedback, facial expressions, and voice input from the user to obtain emotional data.

[1842] Specifically, the system uses a camera and microphone to capture changes in the user's tone of voice and facial expressions, and assigns emotional labels such as "satisfied" or "dissatisfied."

[1843] Step 11:

[1844] The terminal transmits the feedback data and the emotion data to the server.

[1845] Specifically, feedback and emotional data are sent to the server via an HTTP request (e.g., POST / submit-feedback).

[1846] Step 12:

[1847] The server receives the feedback data and emotion data and stores them in a database.

[1848] Specifically, feedback information and emotion data are recorded in a database using SQL INSERT statements.

[1849] Step 13:

[1850] The next time the user tries to generate a recipe under the same conditions, the server will optimize the generated recipe by taking into account past feedback data and emotion data.

[1851] Specifically, the system improves the distribution of seasonings and cooking methods based on the collected feedback and emotional data. For example, it analyzes the factors that led to low satisfaction in the previous meal and makes adjustments based on that.

[1852] Example 2

[1853] 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."

[1854] Modern consumers are faced with a wide variety of ingredients and cooking options, making it difficult to find recipes that best suit their tastes. Furthermore, existing systems do not fully utilize feedback and sentiment data from individual users, making it difficult to increase user satisfaction. The present invention aims to solve these problems by providing a system that suggests optimal recipes based on a user's individual preferences and feedback.

[1855] 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.

[1856] In this invention, the server includes means for inputting conditions such as ingredients, number of people, seasonings, and cooking time selected by the user, means for generating original recipe data based on the conditions, means for displaying detailed cooking procedures based on the generated original recipe, means for collecting feedback from the user and reflecting it in generating subsequent original recipes, and means for recognizing user emotional data and reflecting that data in generating original recipes. This makes it possible to provide recipes optimized for the preferences and emotional state of each individual user.

[1857] "User" refers to an individual who uses this system to create recipes and receive cooking instructions.

[1858] "Ingredients" refers to the ingredients selected by the user for cooking.

[1859] "Number of people" refers to data that indicates the amount of food the user is making and specifies how many people the food is for.

[1860] "Seasoning" refers to data indicating the flavor and type of seasoning the user desires for the dish.

[1861] "Cooking time" refers to data indicating the time it takes to complete the dish desired by the user.

[1862] "Original recipe" refers to unique recipe data generated based on input conditions.

[1863] "Means" refers to the technical configuration for realizing a specific function in this system.

[1864] "Feedback" refers to the ratings and opinions provided by users about the results of their cooking.

[1865] "Emotional data" refers to data obtained by analyzing a user's emotional state.

[1866] "Server" refers to the computer system that processes and stores data in this system.

[1867] "Terminal" refers to the device (e.g., smartphone or PC) used by a user to access the system.

[1868] "Database" refers to a storage device for storing and managing collected data.

[1869] "Generative AI model" refers to the artificial intelligence algorithm used to generate original recipes.

[1870] A "prompt" refers to a sentence or instruction input to a generative AI model.

[1871] This system automatically generates original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and provides detailed cooking instructions. Furthermore, the system collects and analyzes feedback and emotional data from users, and reflects this in future recipe generation, thereby providing recipes that are always optimized to the user's preferences.

[1872] System configuration

[1873] The system consists of the following modules:

[1874] 1. User Interface (UI) Module

[1875] 2. Recipe Generation Module

[1876] 3. Procedure Assistant Module

[1877] 4. Feedback Module

[1878] 5. Emotion Engine Module

[1879] Hardware and Software

[1880] The hardware used includes user devices such as smartphones and PCs, as well as servers, while the software used includes applications that provide a user interface, database software, and machine learning libraries for running generative AI models.

[1881] Program processing

[1882] The program processing in this system is as follows:

[1883] 1. User Interface (UI) Module

[1884] Users launch the application from their smartphone or PC and input the ingredients they want to use, the number of people they want to cook for, the desired seasoning, cooking time, etc. For example, they can use "chicken" and "green onions" to cook "two servings," request "salt sauce," and set the cooking time to "within 30 minutes."

[1885] 2. Recipe Generation Module

[1886] The device sends the conditions entered by the user to the server. Based on the received data, the server searches and retrieves similar past recipes and seasoning distribution data from a database, and uses a generative AI model to generate an original recipe that best suits the conditions. For example, the server determines specific amounts such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)."

[1887] 3. Procedure Assistant Module

[1888] The server sends the generated recipe data to the device, which receives it and displays it to the user. When the user starts cooking based on the recipe, the following instructions are displayed:

[1889] 1. Cut the chicken into bite-sized pieces.

[1890] 2. Cut the green onions into 1cm wide pieces.

[1891] 3. Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes.

[1892] 4. Once the chicken is cooked through, add the green onions and stir fry for a further 3 minutes.

[1893] 5. Add salt, sake, mirin, and water, and simmer for 1 minute while stirring.

[1894] 4. Feedback Module

[1895] After the user has finished cooking, they can enter feedback about the dish into the app. For example, they can enter feedback such as, "There was too much salt, so next time I'll use 0.5 teaspoons."

[1896] 5. Emotion Engine Module

[1897] When a user enters feedback, the emotion engine recognizes the user's emotions by analyzing the text entered by the user and facial and voice data captured using the camera and microphone. For example, it can determine whether the user is satisfied with the food or stressed.

[1898] Specific examples

[1899] As a concrete example, consider a scenario in which a user makes a dish for two people using chicken and green onions with a salt sauce. The user selects "chicken" and "green onions" as ingredients in the app and sets the conditions of two servings, salt sauce, and within 30 minutes. The device sends this information to the server, which then generates a recipe that meets the conditions. The generated recipe consists of "200g chicken," "1 green onion," "1 teaspoon salt," "1 tablespoon sake," "1 tablespoon mirin," and "50ml water," which the device receives and displays to the user. The user cooks the food based on the displayed recipe and enters feedback into the app after cooking. At this time, the emotion engine analyzes the user's emotions and evaluates the user's level of satisfaction, along with comments such as "The amount of salt was too much, so next time I'll use 0.5 teaspoons." This feedback and emotion data are sent from the device to the server and used to generate future recipes.

[1900] Prompt Sentence Examples

[1901] An example of a prompt to input to a generative AI model is as follows:

[1902] You are in charge of programming a cooking recipe generation system. Your task is to automatically generate the optimal recipe for a user to make "Chicken and green onion dish with salt sauce, for two people." You must provide specific ingredients and steps, and take into account the user's past feedback and sentiment data.

[1903] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1904] Step 1:

[1905] The user interface (UI) module allows users to launch the application from their smartphone or PC. Users input conditions such as the ingredients they want to use, the number of people they want to cook for, the desired seasoning, and cooking time. For example, a user might select "chicken" and "green onions" as ingredients, cook "two servings," request "salt sauce," and set the cooking time to "within 30 minutes."

[1906] Input: The user enters the condition.

[1907] Output: The format in which the input data is formatted and sent to the server (e.g. JSON data).

[1908] Step 2:

[1909] The device sends the conditions entered by the user to the server. The sent data is accurately passed to the server in JSON format, etc.

[1910] Input: Data entered by the user.

[1911] Output: The formatted data that is sent to the server.

[1912] Specific operation: Press the "Send" button on the terminal. When the "Send" button is pressed, the input data is validated. Data that passes validation is sent to the server.

[1913] Step 3:

[1914] Based on the data received by the server, the database is searched for and retrieved from the server similar recipes and seasoning distribution data from the past. This data is then used by a generative AI model to generate an original recipe that best suits the conditions.

[1915] Input: Formatted condition data.

[1916] Output: The generated original recipe data.

[1917] Specific operations: The server analyzes the received data, searches for related data from the database to retrieve similar recipes, and uses a generative AI model to create the optimal recipe.

[1918] Step 4:

[1919] The server transmits the generated recipe data to the terminal, which receives it and displays it to the user.

[1920] Input: Generated original recipe data.

[1921] Output: Recipe information displayed to the user.

[1922] Specific operation: The server sends the generated recipe data in JSON format. The device receives the recipe data and displays it on the interface. The recipe includes specific ingredient amounts and cooking instructions.

[1923] Step 5:

[1924] The user starts cooking based on the displayed recipe, and the step-by-step instructions are provided by the step-by-step assistant module.

[1925] Input: User confirms cooking instructions.

[1926] Output: Specific instructions for the user to proceed with the cooking.

[1927] How it works: Each cooking step is displayed on the recipe screen. The user proceeds with the cooking process while checking each step. The screen is updated as the cooking process progresses.

[1928] Step 6:

[1929] After the user has finished cooking, they can enter their feedback on the dish into the app, such as "I added too much salt, so next time I'll use 0.5 teaspoons."

[1930] Input: Post-cooking feedback.

[1931] Output: Formatted feedback data.

[1932] Specific operation: After cooking is complete, the user enters comments on the feedback screen that appears, and inputs emotional data (such as satisfaction and stress levels).

[1933] Step 7:

[1934] The device sends feedback to the server, which stores the feedback data in a database and uses it to generate future recipes.

[1935] Input: Formatted feedback data.

[1936] Output: Feedback data stored in a database.

[1937] Specific operation: Press the feedback sending button. Feedback and emotion data will be sent together.

[1938] Step 8:

[1939] The server uses an emotion engine to analyze and store the user's emotion data. The analysis results are taken into account when generating recipes from the next time onwards.

[1940] Input: Feedback data and emotion data.

[1941] Output: Parsed emotion data.

[1942] Specific operation: The server analyzes the received emotion data. The emotion engine evaluates the satisfaction and stress levels. The evaluation results are stored in a database.

[1943] (Application example 2)

[1944] 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."

[1945] Conventional recipe generation systems simply generate recipes based on ingredients and seasoning conditions, and are unable to fully reflect users' specific emotions and feedback. This has led to a demand for systems that can provide recipes that fully satisfy users. Furthermore, the lack of an efficient recipe generation and cooking instruction system that can be used in brick-and-mortar establishments such as restaurants has made it difficult to develop new dishes and streamline kitchen operations.

[1946] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1947] In this invention, the server includes a means for inputting user-selected conditions such as ingredients, number of people, seasonings, and cooking time, a means for generating original recipe data based on the conditions, a means for displaying detailed cooking steps based on the generated original recipe, a means for collecting user feedback and reflecting the feedback in subsequent recipe generation, and a means for analyzing user emotion data and optimizing the recipe based on the user's emotion. This makes it possible to provide optimized recipes that reflect the user's emotion and feedback. This can also contribute to the development of new dishes in restaurants and the efficiency of kitchen operations.

[1948] "Ingredients, number of people, seasoning, and cooking time" are items that the user selects when creating a recipe, and the combination of these is an important factor in determining the specific recipe.

[1949] "Original recipe data" refers to recipe data that the system automatically generates based on conditions specified by the user, and may also be generated based on past recipe data or seasoning distribution data.

[1950] The "means for displaying detailed cooking steps" is a function for displaying specific and detailed steps for the user to actually prepare a dish based on the generated original recipe.

[1951] "Means of collecting feedback and reflecting it in future recipe generation" refers to a function that allows users to input their impressions and suggestions for improvement after actually cooking into the system, which then stores them in a database for use when generating the next recipe.

[1952] "Means for analyzing emotional data and optimizing recipes based on the user's emotions" refers to a function that allows the emotion engine to recognize and analyze the user's emotions when they enter feedback, and then use that data to optimize future recipe suggestions.

[1953] A "restaurant" is a place where users can eat, and is a general concept that encompasses store formats such as restaurants and cafes.

[1954] This invention is a system that automatically generates original recipes based on the ingredients, number of people, seasonings, and cooking time selected by the user, and provides detailed cooking instructions. This system consists of five main modules: a user interface (UI) module, a recipe generation module, a step assistant module, a feedback module, and an emotion engine module.

[1955] 1. User Interface (UI) Module

[1956] It is a means for users to launch an application on their smartphone or tablet device and input conditions such as ingredients, number of people, seasoning, cooking time, etc. For example, when a restaurant chef creates a new dish, if he or she wants to use "chicken" and "green onion" to make "two servings" and "salt sauce" and wants it to be "salted," the function is provided to input this information.

[1957] 2. Recipe Generation Module

[1958] The terminal sends the conditions entered by the user to the server. Based on the received data, the server searches and retrieves similar past recipes and seasoning distribution data from a database, and generates an original recipe that best suits the conditions. For example, the server determines specific amounts such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)." Backend processing using Python and Flask is performed during this process.

[1959] 3. Procedure Assistant Module

[1960] The server sends the generated recipe data to the device, which receives it and displays it to the user. When the user starts cooking based on the recipe, detailed cooking instructions are displayed in real time. Specifically, instructions such as "Cut the chicken into bite-sized pieces," "Cut the green onions into 1cm pieces," "Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes," "Once the chicken is cooked through, add the green onions and fry for another 3 minutes," and "Add salt, sake, mirin, and water, and simmer for 1 minute while mixing everything together" are displayed.

[1961] 4. Feedback Module

[1962] After the user has finished cooking, they can enter their feedback on the dish from their device and send it to the server. For example, they can provide feedback such as, "I added too much salt, so next time I'll use 0.5 teaspoons." The server stores this feedback in a database and uses it to generate future recipes.

[1963] 5. Emotion Engine Module

[1964] When a user enters feedback, the emotion engine recognizes and analyzes the user's emotions. This emotion recognition is performed by analyzing the text entered by the user and facial expressions and voice data acquired using a camera or microphone. The server analyzes and saves the user's emotion data, and takes this into consideration when generating recipes from the next time onwards, allowing it to provide more optimal recipes based on the user's emotions.

[1965] Specific examples

[1966] A restaurant chef opens an application to create a new dish and enters the following criteria:

[1967] Ingredients: chicken, green onion

[1968] Number of people: 2 servings

[1969] Seasoning: Salt sauce

[1970] Cooking time: 30 minutes

[1971] The system generates a recipe based on this information and displays cooking instructions. After the chef has finished cooking, they can enter their feedback, which is then analyzed by the emotion engine. This data is then used to generate future recipes.

[1972] Prompt Sentence Examples

[1973] A chef is looking for a recipe for a new dish. Generate a recipe based on the following criteria and provide detailed cooking instructions:

[1974] Ingredients: chicken, green onion

[1975] Number of people: 2 servings

[1976] Seasoning: Salt sauce

[1977] Cooking time: 30 minutes

[1978] In addition, feedback and emotional data after cooking is completed will be taken into consideration and reflected in future recipe suggestions.

[1979] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1980] Step 1:

[1981] Users launch the application on their smartphone or tablet and input the ingredients, number of people, seasoning, cooking time, etc. Specifically, a restaurant chef would input the following conditions: "chicken," "green onion," "serves two," "salt sauce," and "30 minutes."

[1982] Input: ingredients, number of people, seasoning, cooking time

[1983] Output: Condition data

[1984] Step 2:

[1985] The device sends the entered condition data to the server. Based on the received data, the server searches and retrieves past similar recipes and seasoning distribution data from a database, and generates an original recipe that best suits the conditions. Specifically, the server determines the specific amounts of ingredients, such as "200g of chicken," "1 scallion," and "salt sauce seasonings (1 teaspoon of salt, 1 tablespoon of sake, 1 tablespoon of mirin, 50ml of water)."

[1986] Input: Condition data

[1987] Data processing: database search, retrieval of similar recipes, generation of original recipes

[1988] Output: Generated recipe data

[1989] Step 3:

[1990] The server sends the generated recipe data to the device, which receives it and displays it to the user. The user then begins cooking based on the displayed recipe data. Specific instructions are displayed, such as "Cut the chicken into bite-sized pieces," "Cut the green onions into 1cm pieces," and "Heat oil in a frying pan and fry the chicken over medium heat for about 5 minutes."

[1991] Input: Generated recipe data

[1992] Data processing: None

[1993] Output: Display of cooking instructions

[1994] Step 4:

[1995] After the user has finished cooking, they can input their feedback about the dish and send it to the server from their device. For example, they might say, "I added too much salt, so next time I'll use 0.5 teaspoons." The server stores this feedback in a database and uses it to generate future recipes.

[1996] Input: User feedback

[1997] Data processing: Accumulation in the database, reflection in next recipe generation

[1998] Output: Accumulated feedback data

[1999] Step 5:

[2000] When a user enters feedback, the emotion engine recognizes and analyzes the user's emotions. It analyzes facial expressions and voice data captured using a camera and microphone to determine whether the user is satisfied with the cooking or stressed. The server analyzes and saves the emotion data and takes it into consideration when generating recipes in the future.

[2001] Input: Feedback text, facial expression data, voice data

[2002] Data processing: text analysis, facial expression and voice analysis, emotion data generation

[2003] Output: Parsed emotion data

[2004] Step 6:

[2005] The server uses the accumulated feedback data and analyzed emotion data and takes this information into account when generating new recipes, so that future recipes will be further optimized based on the user's emotions and feedback.

[2006] Input: Accumulated feedback data, analyzed emotion data

[2007] Data processing: Integrating feedback and sentiment data and reflecting it in recipe generation

[2008] Output: New optimized recipe data

[2009] 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.

[2010] 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.

[2011] 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.

[2012] 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.

[2013] 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.

[2014] 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.

[2015] 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).

[2016] 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.

[2017] 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."

[2018] 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.

[2019] 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).

[2020] 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.

[2021] 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.

[2022] 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.

[2023] 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.

[2024] 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.

[2025] 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.

[2026] 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.

[2027] 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.

[2028] 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.

[2029] 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.

[2030] The following is further disclosed regarding the above embodiment.

[2031] (Claim 1)

[2032] A means for the user to input the ingredients, number of people, seasoning, and cooking time conditions selected;

[2033] means for generating original recipe data based on the conditions;

[2034] a means for displaying detailed cooking steps based on the generated original recipe;

[2035] A means to collect user feedback and reflect it in future recipe generation,

[2036] A system including:

[2037] (Claim 2)

[2038] 2. The system according to claim 1, wherein the original recipe data is generated based on past similar recipes and seasoning distribution data.

[2039] (Claim 3)

[2040] The system according to claim 1, wherein the collected user feedback data is stored in a database and reflected in subsequent recipe suggestions.

[2041] "Example 1"

[2042] (Claim 1)

[2043] A means for users to input ingredients, number of people, seasoning, and cooking time.

[2044] means for using a generative AI model to generate original recipe data based on the conditions;

[2045] A means for displaying detailed cooking instructions based on the generated original recipe;

[2046] A means to collect user feedback in the form of prompt sentences and reflect it in future recipe generation.

[2047] A system including:

[2048] (Claim 2)

[2049] 2. The system according to claim 1, wherein the original recipe data is generated based on past similar recipes, seasoning distribution data, and user feedback data.

[2050] (Claim 3)

[2051] The system of claim 1 stores the collected user feedback data in a database and uses a generative AI model to reflect this in future recipe suggestions.

[2052] "Application Example 1"

[2053] (Claim 1)

[2054] A means for the user to input the ingredients, number of people, seasoning, and cooking time conditions selected;

[2055] means for generating original recipe data based on the conditions;

[2056] a means for displaying detailed cooking steps based on the generated original recipe;

[2057] A means to collect user feedback and reflect it in future recipe generation,

[2058] a means for transmitting the original recipe data and cooking procedures to an automatic cooking device, and for the automatic cooking device to carry out cooking;

[2059] A system including:

[2060] (Claim 2)

[2061] 2. The system according to claim 1, wherein the original recipe data is generated based on past similar recipes and seasoning distribution data.

[2062] (Claim 3)

[2063] The system according to claim 1, wherein the collected user feedback data is stored in a database and reflected in subsequent recipe suggestions.

[2064] "Example 2: Combining Emotion Engines"

[2065] (Claim 1)

[2066] A means for the user to input the ingredients, number of people, seasoning, and cooking time conditions selected;

[2067] means for generating original recipe data based on the conditions;

[2068] a means for displaying detailed cooking steps based on the generated original recipe;

[2069] A means to collect feedback from users and reflect it in future original recipe generation.

[2070] A means of recognizing user emotional data and reflecting that data in generating original recipes;

[2071] A system including:

[2072] (Claim 2)

[2073] 2. The system according to claim 1, wherein the original recipe data is generated based on past similar recipes and seasoning distribution data.

[2074] (Claim 3)

[2075] The system according to claim 1, wherein the collected user feedback data and emotion data are stored in a database and reflected in subsequent original recipe suggestions.

[2076] "Application example 2 when combining emotion engines"

[2077] (Claim 1)

[2078] A means for the user to input the ingredients, number of people, seasoning, and cooking time conditions selected;

[2079] means for generating original recipe data based on the conditions;

[2080] a means for displaying detailed cooking steps based on the generated original recipe;

[2081] A means to collect user feedback and reflect it in future recipe generation,

[2082] A means of analyzing sentiment data and optimizing recipes based on user sentiment;

[2083] A system including:

[2084] (Claim 2)

[2085] 2. The system according to claim 1, wherein the original recipe data is generated based on past similar recipes and seasoning distribution data.

[2086] (Claim 3)

[2087] The system according to claim 1, wherein the collected user feedback data and emotion data are stored in a database and reflected in subsequent recipe suggestions. [Explanation of symbols]

[2088] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for the user to input the ingredients, number of people, seasoning, and cooking time conditions selected; means for generating original recipe data based on the conditions; a means for displaying detailed cooking steps based on the generated original recipe; A means to collect user feedback and reflect it in future recipe generation, A system including:

2. The system according to claim 1, wherein the original recipe data is generated based on past similar recipes and seasoning distribution data.

3. 2. The system according to claim 1, wherein the collected user feedback data is stored in a database and reflected in subsequent recipe suggestions.

Images