system

Abstract

We provide the system. [Solution] A means of receiving requests from clients, A method for generating new recipes based on a taste database, A means of sending the generated recipe to a cooking recreater, A means to support communication between the cooking recreater and the AI, A means of delivering the recreated dishes to the client, A system that includes a means of receiving feedback from clients and reflecting it in the evaluation of the person who recreates the dish.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional cooking largely depends on human knowledge and experience, and there are limitations in discovering and creating new tastes. In addition, there is also a lack of means to quickly and accurately generate a unique recipe that meets the requirements of the requester and reproduce it. Furthermore, there is a lack of a mechanism for appropriately evaluating cooking reproducers, and many reproducers have limited opportunities to demonstrate their skills.

Means for Solving the Problems

[0005] In order to solve the above problems, the present invention provides the following means. That is,

[0006] The system provides a means of receiving requests from clients, generating new recipes based on a taste database, sending the generated recipes to chefs who recreate them, supporting communication between chefs and AI, delivering the recreated dishes to clients, and receiving feedback from clients and reflecting it in the chefs' evaluations. This system makes it possible to quickly generate unique recipes based on client requests, recreate them appropriately, and reflect the feedback in the chefs' evaluations.

[0007] A "client" refers to a user who uses the system to order a specific dish and then receives the result.

[0008] A "request" refers to a preference or request regarding a specific taste or dish that the user sends to the system.

[0009] A "taste database" refers to a collection of information that accumulates data on the taste of various food ingredients and seasonings.

[0010] "Recipe generation" refers to the process of creating unique cooking procedures that meet the client's requirements, based on a taste database.

[0011] A "cooking recreater" refers to a human operator who actually recreates a dish based on a generated recipe.

[0012] "Communication support" refers to a supplementary function that allows the cooking modeler and the AI ​​to exchange information and resolve any questions or points of clarification.

[0013] "Delivery" refers to the process of quickly delivering the recreated meal to the customer.

[0014] "Evaluation" refers to the process where clients provide feedback on the quality of the dishes and service, and the results are reflected in the performance of the chefs who recreate the dishes. [Brief explanation of the drawing]

[0015] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example Ⅰ. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example Ⅱ when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0016] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the 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.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0029] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention relates to a system that generates a unique recipe based on the client's requests, which is then reproduced by a chef and delivered to the client. This system is implemented as follows.

[0037] Request acceptance

[0038] server

[0039] The server receives requests from clients. Clients enter their cooking preferences and taste requests into a form on the website and click the submit button, sending the request to the server. The server analyzes the received request and forwards it to the recipe generation subsystem.

[0040] Specific example

[0041] The client types and submits a request stating, "I want to eat an exotic dish that is very sour and not too spicy."

[0042] Recipe generation

[0043] AI Server

[0044] The server receives the client's request and retrieves information on relevant ingredients and seasonings from the taste database. Based on the data, it generates a recipe suitable for the request. The generated recipe is then sent to the cooking and reproduction subsystem.

[0045] Processing explanation in natural language

[0046] The AI ​​server consults a taste database and selects ingredients associated with "sourness" and "mild spiciness." Based on these selected ingredients, it then creates recipes for exotic dishes.

[0047] Recipe distribution and cooking

[0048] The terminal of the person recreating the cooking recipe.

[0049] The cook's device receives a recipe notification. They review the recipe, organize the necessary ingredients and cooking steps, resolve any uncertainties using the AI ​​server's chat function, and then begin cooking.

[0050] Processing explanation in natural language

[0051] The cooking model receives a recipe and prepares the dish following the displayed cooking steps. If any questions arise during cooking, they can ask them via chat with the AI ​​server and receive answers.

[0052] Arranging delivery

[0053] The terminal of the person recreating the cooking recipe.

[0054] Once cooking is complete, the person recreating the dish sends a cooking completion notification to the server.

[0055] server

[0056] The server receives a notification that cooking is complete and instructs the food delivery company to arrange delivery. The delivery company picks up the food and delivers it to the customer.

[0057] Processing explanation in natural language

[0058] The customer provides the food delivery service with their information and the food, requesting prompt delivery. The delivery service picks up the food and delivers it to the customer's address.

[0059] Receiving and rating the food

[0060] User's terminal

[0061] The customer receives the food and accesses a review form on the website. They then enter and submit a review regarding the quality of the food and the speed of delivery.

[0062] server

[0063] The server receives the evaluations and saves them to the database. Furthermore, the evaluations are reflected in the evaluation points of the cooking recreaters, and the rankings are updated.

[0064] Processing explanation in natural language

[0065] The evaluation results are recorded in a database and used to assess the performance of the recipe recreaters. The recipe recreater rankings are also updated, and outstanding recreaters receive additional rewards.

[0066] Through these processes, the present invention provides a system that generates, quickly reproduces, and delivers unique recipes based on the client's requests.

[0067] The following describes the processing flow.

[0068] Step 1: Accepting the request

[0069] server

[0070] The system recognizes that a user has entered a specific cooking request into a request form on the website and clicked the submit button. The server receives this data and analyzes the request. The analysis results are then transferred to the recipe generation subsystem.

[0071] Step 2: Analyze requirements and generate recipes

[0072] AI Server

[0073] The server analyzes the client's request and consults a taste database. It selects ingredients and seasonings that match the taste characteristics based on the request and generates an original recipe based on them. The generated recipe is then sent to the cooking reproduction subsystem.

[0074] Step 3: Receive and confirm the recipe

[0075] The terminal of the person recreating the cooking recipe.

[0076] The person recreating the recipe receives a notification on their device and confirms that a new recipe has arrived. They view the recipe details and check the required ingredients and cooking instructions.

[0077] Step 4: Communication with AI

[0078] The terminal of the person recreating the cooking recipe.

[0079] The person recreating the recipe asks the AI ​​server any questions or uncertainties. They receive immediate answers from the server using the chat function. This exchange ensures that the information necessary for recipe recreation is accurately conveyed.

[0080] Step 5: Cooking

[0081] The terminal of the person recreating the cooking recipe.

[0082] The cooking replicator prepares the dish according to the recipe. They proceed step by step, checking each step along the way, and communicate with the AI ​​server again if any problems arise.

[0083] Step 6: Notification that cooking is complete

[0084] The terminal of the person recreating the cooking recipe.

[0085] Once cooking is complete, the person reproducing the cooking process notifies the server of the completion. They then transmit the cooking completion status using a communication method.

[0086] Step 7: Arrange delivery

[0087] server

[0088] The server receives a cooking completion notification and instructs the food delivery company to arrange delivery. It also provides the delivery company with information on where to pick up and deliver the food.

[0089] Step 8: Food Delivery

[0090] Delivery company

[0091] A delivery company picks up the food and delivers it quickly to the customer. When the customer receives the food, a delivery completion notification is sent to the server.

[0092] Step 9: Receive and rate your food

[0093] User's terminal

[0094] The customer receives the food and accesses a review form on the website. They then enter and submit a review about the taste, appearance, delivery time, etc.

[0095] Step 10: Reflecting the evaluation

[0096] server

[0097] The server receives the evaluation data and stores it in the database. The evaluation results are reflected in the evaluation of the cooking recreaters, and the recreaters' rankings are updated. In addition, the payment of rewards is processed based on the evaluations.

[0098] These specific processing steps enable the system to efficiently and quickly provide original dishes based on the client's requests.

[0099] (Example 1)

[0100] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0101] The current recipe generation and food delivery system has several problems, including accurately reflecting the client's requests in generating recipes, facilitating smooth communication with the cooks, and managing delivery arrangements and evaluations. Specifically, these include malfunctions in the function for properly analyzing client requests, a lack of means to resolve questions about the generated recipes, and inefficiencies in delivery arrangements. There are also problems with properly reflecting client evaluation data in the performance evaluations and compensation of the cooks.

[0102] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0103] In this invention, the server includes means for receiving requests from clients, means for generating new recipes based on a taste database, means for transmitting the generated recipes to a cooking recreater, means for supporting communication between the cooking recreater and artificial intelligence, means for delivering the recreated dishes to the clients, means for receiving evaluations from clients and reflecting them in the cooking recreater's evaluation, means for arranging delivery with a delivery company, means for inputting questions to help the cooking recreater resolve any doubts based on the generated recipes and obtaining answers, means for analyzing the client's requests and extracting information on seasonings and ingredients, means for saving the client's evaluations in a database and updating the cooking recreater's ranking, and means for providing additional rewards to the cooking recreater based on the client's evaluation. This enables the generation of recipes that accurately reflect the client's requests, smooth communication with cooking recreaters, efficient delivery arrangements, and appropriate reflection of evaluations from clients.

[0104] A "client" is an individual or group that submits a request for a dish to the system.

[0105] A "taste database" is a database that stores and manages information about the taste of various ingredients and seasonings.

[0106] "Recipe generation" is the process of selecting appropriate ingredients and seasonings based on the client's requests and constructing a unique cooking procedure.

[0107] A "cooking recreater" is an individual or group whose role is to actually cook a dish based on a generated recipe.

[0108] "Artificial intelligence" is a technology that performs natural language processing and data analysis within a system to support communication between clients and those who recreate the dishes.

[0109] "Supporting communication" refers to a function that allows cooking enthusiasts to resolve any uncertainties they may have regarding cooking through artificial intelligence.

[0110] "Delivery" refers to the process of delivering the dishes prepared by the chef to the client.

[0111] "Reviews" refer to the process by which clients provide feedback on the quality of the food and the speed of delivery.

[0112] A "delivery service provider" is an individual or company that provides a service to deliver the recreated dishes to the customer.

[0113] "Enter a question and get an answer" refers to the process where a cooking simulator asks artificial intelligence questions that arise during cooking and receives the answers.

[0114] "Extracting information on seasonings and ingredients" is the process of analyzing the client's requests and obtaining data on the most suitable seasonings and ingredients based on those requests.

[0115] A "database" is a system that efficiently stores and manages various types of data, and allows that data to be retrieved as needed.

[0116] "Ranking" is a system that assigns rankings based on the performance evaluation of those who recreate the dishes.

[0117] "Additional rewards" refer to preliminary gratuities or bonuses paid to recipe recreaters who receive outstanding ratings.

[0118] This invention is a system that generates a unique recipe based on the client's request, a chef prepares the dish based on that recipe, and delivers it to the client. This system is implemented through the following main means.

[0119] Request acceptance

[0120] server

[0121] The server provides a means for receiving requests from clients. When a client enters their culinary preferences and taste requests into a form on the website and clicks the submit button, the request is sent to the server. For example, a client might enter and submit, "I want an exotic dish that is very sour and not too spicy." The server analyzes the received request and forwards it to the recipe generation subsystem.

[0122] Recipe generation

[0123] AI Server

[0124] The server receives the client's request and retrieves information on relevant ingredients and seasonings from the taste database. Specifically, the AI ​​server refers to the taste database and selects ingredients associated with "sourness" and "mild spiciness." Then, it creates a recipe for an exotic dish based on the selected ingredients. The generated recipe is sent to the cooking reproduction subsystem. For example, it might select sour ingredients such as "lemon" and "coriander" to construct a recipe for a mildly spicy exotic dish.

[0125] Example of a prompt:

[0126] "Please generate recipes for exotic dishes that are strongly sour and mildly spicy."

[0127] Recipe distribution and cooking

[0128] The terminal of the person recreating the cooking recipe.

[0129] The cooking model's device receives a recipe notification from the AI ​​server. The device displays the recipe details and prepares the necessary ingredients for cooking. The cooking model begins cooking according to the displayed recipe. If any questions arise during cooking, they can use the chat function on the device to ask questions to the AI ​​server. For example, if they are making beef stroganoff and want more detailed instructions about the cooking time, they can ask via chat.

[0130] Example of a prompt:

[0131] "How long do you need to cook beef stroganoff?"

[0132] Arranging delivery

[0133] The terminal of the person recreating the cooking recipe.

[0134] Once cooking is complete, the person recreating the cooking process sends a completion notification to the server. For example, they might click the "Cooking Complete" button on their device to notify the server of the completion status.

[0135] server

[0136] The server receives a cooking completion notification and instructs the food delivery company to arrange delivery. The delivery company picks up the food and delivers it to the customer. For example, the server calls the delivery company's (e.g., Uber Eats) API to arrange food delivery.

[0137] Example of a prompt:

[0138] "Please arrange for beef stroganoff to be delivered to the address XX."

[0139] Receiving and rating the food

[0140] User's terminal

[0141] The customer receives the food and accesses a review form on the website. They enter and submit a review regarding the quality of the food and the speed of delivery. For example, the customer might enter and submit a review stating, "The food was delicious, I would like to use this service again."

[0142] server

[0143] The server receives the evaluations and saves them to the database. Furthermore, it reflects the evaluations in the cooking recreater's evaluation points and updates the rankings. For example, the server analyzes the evaluation data and updates the cooking recreater's evaluation points. It records it in the database as "4.5 points on a 5-point scale."

[0144] In this way, this system utilizes various databases and artificial intelligence to efficiently carry out a series of processes, from generating recipes based on the client's requests to cooking, delivery, and evaluation.

[0145] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0146] Step 1: Accepting requests

[0147] The server provides a form on the website to receive requests from clients. By entering their desired dishes and taste preferences into the form and clicking the submit button, the request is sent to the server. The input data includes specific dish characteristics and desired tastes. The server analyzes the received request, breaks down the client's request into specific keywords, and transfers this as analysis data to the recipe generation subsystem.

[0148] Input: Request from the client (e.g., "An exotic dish with a strong sour taste and mild spiciness")

[0149] Output: Decomposed keywords (e.g., "sourness", "mild spiciness", "exotic")

[0150] Specific operation: The client enters their request into an input form, and the server receives it and breaks it down into keywords.

[0151] Step 2: Recipe Generation

[0152] The server retrieves information on relevant ingredients and seasonings from a taste database based on the client's request. Based on the retrieved data, the AI ​​server generates a recipe suitable for the client. Specifically, the AI ​​model matches the decomposed keywords with data from the taste database to select appropriate ingredients and seasonings. Based on these, it constructs specific cooking steps and completes the recipe.

[0153] Input: Keywords (e.g., "sourness", "mild spiciness", "exotic"), data from a taste database.

[0154] Output: Generated recipe (e.g., "Exotic Chicken Dish with Lemon")

[0155] Specific operation: The AI ​​server accesses the database, and the AI ​​model generates a cooking recipe.

[0156] Step 3: Recipe notification

[0157] The cooking model's device receives a recipe notification from the AI ​​server. The recipe details are displayed on the device, and the model performs the necessary preparations for cooking. The recipe includes a specific list of ingredients and cooking instructions.

[0158] Input: Generated recipe

[0159] Output: Displayed recipe information (list of ingredients and cooking instructions)

[0160] Specific operation: The cooking recreater's device receives and displays the recipe from the AI ​​server.

[0161] Step 4: Cooking

[0162] The person recreating the dish begins cooking according to the displayed recipe. If any questions arise during cooking, they can use the chat function with the AI ​​server via their device to ask questions. The AI ​​server provides answers and resolves the questions.

[0163] Input: Recipe information, questions from the person who recreated the dish.

[0164] Output: Finished dish, response from AI server

[0165] Specific actions: The person recreating the recipe will measure the ingredients and cook according to the recipe. If any questions arise during the process, they will use the chat function.

[0166] Step 5: Notification that cooking is complete

[0167] Once cooking is complete, the person reproducing the cooking sends a completion notification to the server. The server receives the notification and prepares to proceed to the next step.

[0168] Input: Cooking completion notification

[0169] Output: Completion notification to the server

[0170] Specific action: Click the "Cooking Complete" button on the terminal and send a completion notification to the server.

[0171] Step 6: Arrange delivery

[0172] The server receives a notification that cooking is complete and instructs the food delivery company to arrange delivery. The delivery company picks up the food and delivers it to the customer.

[0173] Input: Cooking completion notification, delivery company information

[0174] Output: Execution of delivery arrangements, instructions to the delivery company.

[0175] Specific operation: The server calls the delivery company's API to arrange for food delivery.

[0176] Step 7: Receive and rate your food

[0177] The customer receives the food and accesses a review form on the website. They enter and submit a review regarding the quality of the food and the speed of delivery.

[0178] Input: Client's evaluation

[0179] Output: Evaluation data to the server

[0180] Specific operation: The client enters feedback into the evaluation form and sends it to the server.

[0181] Step 8: Saving and reflecting the evaluation

[0182] The server receives the evaluations and stores them in the database. Furthermore, the evaluations are reflected in the cooking recreater's evaluation points, updating the rankings. Cooking recreaters who receive excellent evaluations are given additional rewards.

[0183] Input: Evaluation data

[0184] Output: Updated evaluation points and rankings, and reflection of additional rewards.

[0185] Specific operation: The server analyzes the evaluation data, saves it to the database, and updates the evaluation points and rankings of the cooking recreaters.

[0186] (Application Example 1)

[0187] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0188] In modern society, it is difficult to easily obtain special dishes tailored to individual tastes and preferences. Furthermore, there is a lack of systems that guarantee that online orders will meet expectations in terms of taste and quality. In addition, the food preparation process and delivery arrangements are time-consuming, creating a need for efficient systems that provide customer satisfaction.

[0189] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0190] In this invention, the server includes means for receiving requests from clients, means for generating new recipes based on a taste database, means for transmitting the generated recipes to a chef who recreates them, means for supporting communication between the chef and the AI, means for delivering the recreated dishes to the clients, means for receiving evaluations from clients and reflecting them in the chef's evaluation, means for receiving requests via a smartphone application, means for generating recipes using an AI server, means for arranging delivery in cooperation with a delivery platform, and means for transmitting evaluation results from the client's terminal to the server and saving them in a database. This enables the efficient generation of special dishes tailored to the individual requests of clients, and allows for the provision of high-quality dishes by chefs and rapid delivery.

[0191] A "client" is an individual or group that makes a special request for a particular dish to the system.

[0192] A "request reception method" is an interface that provides the functionality to collect requests for dishes and taste preferences from clients and send them to the server.

[0193] A "taste database" is a database that stores information on ingredients and seasonings used in cooking, and allows users to refer to the taste characteristics of each.

[0194] A "recipe generation method" is a system that automatically generates unique recipes by selecting appropriate ingredients and seasonings from a taste database based on the client's requests.

[0195] A "cooking recreater" is a person or robot that actually cooks a dish based on a generated recipe.

[0196] A "recipe transmission means" is a communication means for notifying the person who will be cooking and reproducing the generated recipe.

[0197] The "communication support system between cooking replicators and AI" is a mechanism that provides a chat function to allow cooking replicators to resolve any questions they may have by interacting with AI.

[0198] "Delivery methods" refer to food delivery services and systems that quickly deliver recreated dishes to the customer.

[0199] The "evaluation receiving method" is an interface that collects evaluations from clients regarding the quality of the food and the speed of delivery, and sends that data to the server.

[0200] A "smartphone application" is software on a mobile device that allows clients to input their requests and manage their orders.

[0201] An "AI server" is a server equipped with artificial intelligence that analyzes the client's requests and generates recipes by referring to a taste database.

[0202] A "delivery platform" is an online platform that instructs food delivery companies to arrange deliveries and delivers food to customers.

[0203] A "rating and storage method" is a system that stores the client's evaluation results in a database and reflects them in the performance evaluation of the cooking and recipe reproduction team.

[0204] This invention relates to a system that generates a unique recipe according to the client's request, and then a chef prepares the dish based on that recipe and delivers it to the client.

[0205] This system includes the following steps:

[0206] Request acceptance

[0207] server:

[0208] The customer enters their culinary preferences and taste requests via a smartphone application. For example, they might enter a request such as, "I'd like an exotic dish that's quite sour and not too spicy," into the form and click the submit button. This request is sent to the server and stored in the database along with the customer's information.

[0209] Recipe generation

[0210] AI Server:

[0211] Upon receiving a request from a client, the server consults a taste database to obtain information on ingredients and seasonings that match the client's preferences. Based on this data, the AI ​​server generates a recipe that suits the request. For example, it might select ingredients related to "sourness" or "mild spiciness" to create a recipe for an exotic dish.

[0212] Recipe distribution and cooking

[0213] The device of the person recreating the recipe:

[0214] The generated recipe is sent to the cook's device. The cook reviews the recipe on their device and organizes the necessary ingredients and cooking steps. Furthermore, if the cook has any questions during the cooking process, they can use the chat function with the server to ask questions and receive answers from the AI ​​server.

[0215] Arranging delivery

[0216] server:

[0217] Once cooking is complete, the cook sends a completion notification to the server. The server receives the completion notification and, in conjunction with the food delivery platform, issues instructions for delivery. The food delivery company picks up the food and delivers it to the customer.

[0218] Receiving and rating the food

[0219] Client's device:

[0220] After receiving their meal, the customer accesses a review form via a smartphone application. They enter and submit their evaluation regarding the quality of the food and the speed of delivery. The server receives the evaluation and stores it in a database. Furthermore, this evaluation is reflected in the evaluation points of the cook / recipe recreater, and the ranking is updated.

[0221] Examples of specific cases and prompt statements

[0222] For example, if the client requests "spicy but not too hot Indian food," the following prompt will be sent to the AI ​​server:

[0223] text

[0224] User Request:

[0225] Desired Cuisine: Indian

[0226] Taste preferences: Spicy but mild heat level

[0227] AI Task:

[0228] Generate a recipe using the given preferences, including a list of ingredients and step-by-step instructions.

[0229] The hardware and software used include Amazon Web Services (AWS) EC2, S3, RDS, Google Cloud AI Platform, React Native, Node.js (Express framework), PostgreSQL, and the Uber Eats API. By combining these, it becomes possible to efficiently generate special dishes tailored to the individual requests of customers, enabling high-quality food delivery and rapid delivery.

[0230] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0231] Step 1:

[0232] Request acceptance

[0233] Users enter their food preferences and taste requests via a smartphone application. Specifically, a user might enter "I want to eat an exotic dish that is very sour and not too spicy" into a form within the app and click the submit button. The entered data is sent to the server as the user's request. The server receives the request data and stores it in a database along with the requester's information.

[0234] Input: Food request (specific tastes and preferences)

[0235] Output: Saved client request data

[0236] Step 2:

[0237] Recipe generation

[0238] The server receives the client's request data and sends it to the AI ​​server. The AI ​​server consults a taste database to obtain information on relevant ingredients and seasonings. Based on this data, the AI ​​server generates specific prompt statements and creates recipes for exotic dishes based on the relevant ingredients. For example, based on "User Request: Desired Cuisine: Indian, Taste preferences: Spicy but mild heat level," it selects appropriate ingredients and seasonings and creates a recipe.

[0239] Input: Client's request data

[0240] Output: Generated recipe

[0241] Step 3:

[0242] Recipe distribution

[0243] The server receives the generated recipe and sends it to the cook's terminal. The cook reviews the recipe on their terminal and organizes the necessary ingredients and cooking steps. The server sends a notification to the cook's terminal at the same time as sending the recipe.

[0244] Input: Generated recipe

[0245] Output: Recipe notification sent to the cook / recipe recreater

[0246] Step 4:

[0247] Cooking progress

[0248] The cooking model proceeds with cooking according to the recipe sent to their device. If any questions arise during cooking, the model uses the device's chat function to ask questions to the AI ​​server. The AI ​​server receives the questions and provides appropriate answers.

[0249] Input: Recipe, questions from the cook / recipe recreater

[0250] Output: Finished dish, AI server's answers to any questions.

[0251] Step 5:

[0252] Arranging delivery

[0253] The terminal sends a notification to the server indicating that cooking is complete. The server receives this notification and, in cooperation with the food delivery platform, issues instructions for delivery. The food delivery company, having received the delivery instructions, picks up the food and delivers it to the customer.

[0254] Input: Notification of cooking completion

[0255] Output: Delivery arrangement instructions to the food delivery platform.

[0256] Step 6:

[0257] Receiving and rating the food

[0258] After receiving their meal, the client accesses a review form via a smartphone application. The client enters and submits their evaluation regarding the quality of the food and the speed of delivery. The server receives the evaluation and stores it in a database. This evaluation is reflected in the evaluation points of the cook who recreated the meal, and the ranking is updated.

[0259] Input: Client's evaluation

[0260] Output: Evaluation data stored in the database, updated ranking of cooking replicators.

[0261] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0262] This invention relates to a system that generates a unique recipe based on the client's requests, which is then reproduced by a chef and delivered to the client. This system is characterized by its integration of an emotion engine to recognize the client's emotions and to perform the recipe generation and evaluation process more precisely based on those emotions.

[0263] Request acceptance

[0264] server

[0265] The server receives requests from clients. Clients enter their preferences for specific dishes or tastes into a form on the website and click the submit button to send their requests. The server receives this data and analyzes the request.

[0266] Emotional Engine

[0267] The emotion engine analyzes the client's emotions when they input their request. The analysis results are obtained through text and voice analysis and provided to the recipe generation subsystem as information that includes the client's intent and emotional elements.

[0268] Recipe generation

[0269] AI Server

[0270] The server receives the client's request and the analysis results from the emotion engine, and retrieves information on relevant ingredients and seasonings from the taste database. Based on the data, it generates a recipe suitable for the request. The generated recipe is sent to the cooking reproduction subsystem.

[0271] Processing explanation in natural language

[0272] The AI ​​server selects ingredients related to "sourness" and "mild spiciness" from a taste database, and then creates recipes for exotic dishes by making adjustments according to the client's preferences.

[0273] Recipe distribution and cooking

[0274] Terminal of the cooking reproducer

[0275] The cooking reproducer receives a notification on the terminal and confirms that a new recipe has arrived. The details of the recipe are displayed, and the ingredients and cooking procedures are checked. The unclear points are resolved using the chat function with the AI server, and cooking is started.

[0276] Explanation of processing in natural language

[0277] The cooking reproducer receives the recipe and cooks according to the displayed cooking procedures. If a problem occurs during cooking, questions are asked through the chat with the AI server, and cooking is advanced by obtaining answers.

[0278] Arrangement of delivery

[0279] Terminal of the cooking reproducer

[0280] When the cooking is completed, the cooking reproducer sends a cooking completion notification to the server. The cooking completion status is sent to the server using the communication means.

[0281] Server

[0282] The server receives the cooking completion notification and gives instructions for delivery arrangement to the food delivery operator. Information on the receipt of the dish and the delivery destination is provided to the delivery operator.

[0283] Explanation of processing in natural language

[0284] The food delivery operator is given the requester information and the dish, and a prompt delivery is requested. The delivery operator receives the dish and delivers it to the requester's address.

[0285] Receipt and evaluation of the dish

[0286] User's terminal

[0287] The customer receives the food and accesses a review form on the website. They enter and submit a review regarding the quality of the food, delivery time, etc. An emotion engine analyzes the customer's emotions during the review process and incorporates that data into the evaluation process.

[0288] server

[0289] The server receives the evaluations and stores them in the database. The results analyzed by the emotion engine are also stored and reflected in the evaluation of the cooking recreater. Based on the evaluation results, the cooking recreater's performance is assessed and the ranking is updated. In addition, the payment of rewards is also processed based on the evaluation.

[0290] Processing explanation in natural language

[0291] Evaluation data and sentiment analysis results are recorded in a database and reflected in the evaluation points of the cooking recreaters. The recreater rankings are updated, and outstanding recreaters receive additional rewards.

[0292] This configuration allows the system to not only efficiently and quickly provide unique dishes based on the client's requests, but also to deliver service that takes the client's emotions into consideration.

[0293] The following describes the processing flow.

[0294] Step 1: Accepting the request

[0295] server

[0296] The system recognizes that a user has entered specific food requests into a request form on the website and clicked the submit button. The server receives this data and analyzes the request. The data is then sent to the emotion engine through text and voice analysis.

[0297] Emotional Engine

[0298] The emotion engine analyzes the emotions of the requester when the requirements are input. The analysis results are encoded based on the requester's text expression, voice tone, context analysis, etc. The analysis results are provided to the recipe generation subsystem.

[0016] 2>

[0299] Step 2: Analysis of requirements and recipe generation

[0300] AI server

[0301] The server receives the requester's requirements and the analysis results by the emotion engine. It obtains information on related ingredients and seasonings from the taste database and generates a recipe suitable for the requester's emotional state. The generated recipe is further adjusted to reflect the analysis results of the emotion engine.

[0302] Step 3: Receiving and confirming the recipe

[0303] Terminal of the cooking reproducer

[0304] The cooking reproducer receives a notification on the terminal and confirms that a new recipe has been received. The details of the recipe are displayed, and the ingredients and cooking procedures are confirmed. The unclear points are resolved using the chat function with the AI server.

[0305] Step 4: Communication with AI

[0306] Terminal of the cooking reproducer

[0307] The cooking reproducer inquires the AI server about questions and unclear points. The AI server provides an immediate answer. The cooking reproducer proceeds with the work while confirming the appropriate cooking procedures using the chat function.

[0308] Step 5: Implementation of cooking

[0309] Terminal of the cooking reproducer

[0310] The cooking assistant prepares the dish according to the recipe. They proceed while checking each step of the cooking process, and if any problems arise along the way, they communicate with the AI ​​server again via chat. Once cooking is complete, they send a completion notification from their device.

[0311] Step 6: Notification that cooking is complete

[0312] The terminal of the person recreating the cooking recipe.

[0313] Once cooking is complete, the person recreating the dish reports the completion to the server. The report may include photos of the dish and comments.

[0314] Step 7: Arrange delivery

[0315] server

[0316] The server receives a notification that cooking is complete and instructs the food delivery company to arrange delivery. Delivery arrangements include the status of the food, delivery address information, and delivery time.

[0317] Step 8: Food Delivery

[0318] Delivery company

[0319] A delivery company picks up the food and delivers it quickly to the customer. Once the customer receives the food, a delivery completion notification is sent to the server.

[0320] Step 9: Receive and rate your food

[0321] User's terminal

[0322] The customer receives the food and accesses the review form on the website. They enter detailed feedback on the quality of the food, delivery time, etc., and also allow the emotion engine to analyze their feelings. They then submit the review.

[0323] Step 10: Reflecting the evaluation

[0324] server

[0325] The server receives the evaluation and stores it in the database along with the analysis results from the emotion engine. The evaluation points of the cooking recreater are then reflected, including the emotion analysis results. The ranking of the recreaters is updated based on the evaluation results and analysis data, and payment procedures for rewards are carried out as needed.

[0326] These processing steps enable the efficient and rapid delivery of original dishes based on the client's requests and feelings, while also providing a high level of service that takes the client's emotions into consideration.

[0327] (Example 2)

[0328] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0329] Traditionally, generating recipes based on client requests and then recreating those recipes has struggled to take the client's emotions into account. As a result, it was often impossible to provide dishes that matched the client's desired taste and emotions, leading to decreased satisfaction. Furthermore, if communication between the cooking recreater and the artificial intelligence was not smooth, it could potentially affect the quality of the cooking.

[0330] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0331] In this invention, the server includes means for receiving requests from clients, means for analyzing the requests and emotions of the clients, means for generating new recipes based on a taste database, means for transmitting the generated recipes to a chef who will recreate them, means for supporting communication between the chef and artificial intelligence, means for delivering the recreated dishes to the clients, and means for receiving feedback from clients and reflecting it in the chef's evaluation. This makes it possible to generate recipes that take the client's emotions into consideration and to achieve smooth communication between the chef and artificial intelligence. As a result, client satisfaction can be improved and high-quality dishes can be provided.

[0332] A "client" is an individual or group that uses the system to request a specific dish and asks for its preparation and delivery.

[0333] "Requests" refer to the types of dishes and taste preferences that the client desires, and this information is entered into the system by the client.

[0334] A "server" is a computer that receives requests from clients, analyzes them, exchanges data with other subsystems, and manages the entire system.

[0335] An "emotion engine" is a technology that analyzes the client's emotions from input text or audio and provides the analysis results to other parts of the system.

[0336] A "taste database" is a database that stores information about various ingredients and seasonings, and is a collection of data used when generating recipes.

[0337] A "recipe generation method" is a system that, based on the client's requests and the results of emotion analysis, selects appropriate ingredients and seasonings from a taste database and generates a unique recipe.

[0338] A "cook" is the person who receives a generated recipe and actually prepares the dish based on it.

[0339] "Artificial intelligence" is a computing system that can perform specific tasks automatically, and has functions such as suggesting recipes and answering questions during the cooking process.

[0340] "Delivery method" refers to the function or service used to deliver food prepared by a cook to the customer.

[0341] "Rating" refers to the act of a customer expressing their satisfaction level and opinions regarding the food they received and its delivery, and this information is sent to the system as feedback.

[0342] "Chef evaluation" refers to an evaluation that quantifies or ranks the chef's performance based on evaluation data from clients and sentiment analysis results.

[0343] Modes for carrying out the invention

[0344] This invention is a system that generates a unique recipe based on the client's requests, has a chef recreate it, and delivers it to the client. A key feature of this system is that it incorporates an emotion engine to recognize the client's emotions and uses that to refine the recipe generation and evaluation process.

[0345] Request acceptance

[0346] server

[0347] The server receives requests from clients. Clients enter their preferences for specific dishes or tastes into a form on the website and click the submit button to send their requests. The server receives this data and analyzes the request.

[0348] For example, if a client enters their request for a "sweet and sour dessert" and clicks the submit button, the server receives and analyzes that data.

[0349] Emotional Engine

[0350] The emotion engine analyzes the client's emotions when they input their request. The analysis results are obtained through text and voice analysis and provided to the recipe generation subsystem as information that includes the client's intent and emotional elements.

[0351] For example, if a client enters "I'm tired from work today, so I want a dish that will lift my spirits," the emotion engine will identify the emotions "fatigue" and "wanting to lift my spirits" from that sentence and provide that information as analysis results to the recipe generation subsystem.

[0352] Recipe generation

[0353] AI Server

[0354] The server receives the client's request and the analysis results from the emotion engine, and retrieves information on relevant ingredients and seasonings from the taste database. Based on this, it generates a recipe suitable for the request. The generated recipe is then sent to the cook's terminal.

[0355] As a concrete example, the server selects ingredients such as "lemon" and "honey" from a taste database for a client who prefers "sourness" and "sweetness," and then creates an exotic dish recipe based on these ingredients. For example, the prompt might read, "Generate a recipe for a client who wants something sour with a little sweetness."

[0356] Recipe distribution and cooking

[0357] Cook's terminal

[0358] The cook receives a notification on their device and confirms that a new recipe has arrived. They view the recipe details and check the ingredients and cooking instructions. If necessary, they use the chat function with the AI ​​server to resolve any questions and then begin cooking.

[0359] For example, a cook receives a notification for a new recipe and checks it on their device. They carefully examine the ingredients and steps, and then send questions to the AI ​​server via chat, such as, "When is the best time to add this spice?"

[0360] Arranging delivery

[0361] Cook's terminal

[0362] Once cooking is complete, the cook sends a notification to the server indicating completion. The status of cooking completion is sent to the server using a communication method.

[0363] For example, when a cook sends a notification to the server that the cooking is complete, the server automatically instructs the food delivery company to pick up the food and provide the delivery address information (the client's address).

[0364] server

[0365] The server receives a notification that cooking is complete and instructs the food delivery company to arrange delivery. The server provides the delivery company with information on where to pick up the food and the delivery address.

[0366] Receiving and rating the food

[0367] User's terminal

[0368] The customer receives the food and enters their review on a rating form on the website. The review includes the quality of the food and delivery time, and an emotion engine analyzes the emotions felt during the review process.

[0369] For example, if a client enters "The food was delicious, but the delivery was slow" into the review form, the emotion engine analyzes both "satisfied" and "dissatisfied" emotions from this review and incorporates that information into the review data.

[0370] server

[0371] The server receives the evaluations and stores them in the database. The evaluations and sentiment analysis results are reflected in the chef's performance evaluation and are also used for updating rankings and reward procedures.

[0372] For example, the server updates the chef's evaluation points based on the client's evaluation data and the results of their sentiment analysis. If a chef receives many high ratings, they may receive additional compensation.

[0373] Through these processes, the system can efficiently generate dishes that meet the client's requests and provide service that also takes the client's feelings into consideration.

[0374] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0375] Step 1: Receiving the client's request

[0376] The server receives requests from clients through an input form on the website. The entered request (e.g., "sweet and sour dessert") is sent to the server.

[0377] Input: The client's requests regarding specific dishes and taste preferences, entered on the website.

[0378] Specific action: The requester enters their desired "sweet and sour dessert" and clicks the submit button.

[0379] Output: Client's requested data.

[0380] Step 2: Analysis of the requirements

[0381] The server analyzes the request data it receives and understands its content. The analysis results are classified into categories and tastes related to the cuisine.

[0382] Input: Client's request data.

[0383] Specific operation: The server analyzes the request data "sweet and sour dessert" and recognizes the taste "sweet and sour" and the category "dessert".

[0384] Output: Request analysis results (Example: Taste = "Sweet and sour", Category = "Dessert").

[0385] Step 3: Emotional Analysis

[0386] The server passes the request data to the emotion engine, which then analyzes the client's emotions.

[0387] Input: Request data.

[0388] Specific operation: The server passes the text "I'm tired from work today, so I want some food to lift my spirits" to the emotion engine, which identifies the emotions "fatigue" and "want to lift my spirits."

[0389] Output: Emotion analysis results (e.g., emotion = "fatigue", intention = "want to cheer up").

[0390] Step 4: Obtain relevant data

[0391] Based on the client's requests and the results of the emotional analysis, the server retrieves information on relevant ingredients and seasonings from the taste database.

[0392] Input: Request analysis results and emotion analysis results.

[0393] Specific operation: The server searches the taste database for ingredients and seasonings related to "sweet and sour" and "dessert" (e.g., "lemon," "honey").

[0394] Output: Related data (e.g., Ingredient = "Lemon", Seasoning = "Honey").

[0395] Step 5: Recipe Generation

[0396] The server uses relevant data to input prompt messages into the AI ​​model, which then generates a recipe that meets the requirements.

[0397] Input: Related data.

[0398] Specific operation: The server inputs a prompt message to the AI ​​model saying, "Please generate a recipe for a customer who wants something sour with a little sweetness," and the AI ​​generates the recipe.

[0399] Output: Generated recipe (e.g., "Lemon Cheesecake").

[0400] Step 6: Submit the recipe

[0401] The server sends the generated recipe to the cook's terminal.

[0402] Input: The generated recipe.

[0403] Specific operation: The server sends the generated "Lemon Cheesecake" recipe to the cook's terminal.

[0404] Output: The cook's terminal receives the recipe.

[0405] Step 7: Check the recipe

[0406] The cook's device receives a notification and confirms that a new recipe has arrived. They view the recipe details and check the ingredients and cooking instructions.

[0407] Input: The generated recipe.

[0408] Specific action: The cook receives a notification on their device saying "A new recipe has arrived," and then checks the recipe details.

[0409] Output: Recipe details displayed on the cook's terminal.

[0410] Step 8: Communication with the AI ​​Server

[0411] The cook's device uses a chat function with an AI server to resolve any questions or uncertainties.

[0412] Input: Unclear points regarding the cooking procedure.

[0413] Specific operation: The cook asks the AI ​​server, "At what point is it best to add this spice?" and receives an answer.

[0414] Output: Cooking instructions with clarifications.

[0415] Step 9: Cooking

[0416] The cook's device performs the cooking according to the recipe.

[0417] Input: Resolved cooking procedure.

[0418] Specific actions: The cook begins preparing the "lemon cheesecake" according to the instructions in the recipe.

[0419] Output: The finished dish.

[0420] Step 10: Report that cooking is complete.

[0421] The cook's device sends a notification to the server indicating that cooking is complete.

[0422] Input: The state of the finished dish.

[0423] Specific action: The cook clicks a button to notify the server that cooking is complete.

[0424] Output: The server received a cooking completion notification.

[0425] Step 11: Arrange delivery

[0426] The server receives the completion notification and instructs the food delivery company to arrange delivery.

[0427] Input: Cooking completion notification.

[0428] Specific operation: The server issues an instruction to the food delivery company: "Deliver the lemon cheesecake to client X."

[0429] Output: Instructions for the food delivery company to pick up the food.

[0430] Step 12: Food Delivery

[0431] A food delivery company delivers the food to the customer.

[0432] Input: Instructions for delivery arrangements.

[0433] Specific operation: A food delivery company picks up the food and delivers it to the specified address.

[0434] Output: The client receives the food.

[0435] Step 13: Enter the evaluation

[0436] The client's device receives the food, accesses the website's review form, and enters their review information.

[0437] Input: Product or service evaluation.

[0438] Specific action: The client enters "The food was delicious, but the delivery was late" into the review form and clicks the submit button.

[0439] Output: Evaluation data.

[0440] Step 14: Analysis of evaluation data

[0441] The emotion engine analyzes the emotions expressed by the client when they enter their evaluation and provides the results to the server.

[0442] Input: Evaluation data.

[0443] Specific operation: The emotion engine analyzes the emotions of "satisfied" and "dissatisfied" from the evaluation "It was delicious, but the delivery was late."

[0444] Output: Emotion analysis results.

[0445] Step 15: Reflecting the evaluation

[0446] The server incorporates evaluation data and sentiment analysis results into the chef's evaluation and stores them in the database.

[0447] Input: Evaluation data and sentiment analysis results.

[0448] Specific operation: The server saves the evaluation and sentiment analysis results and updates the chef's evaluation points. Simultaneously calculates and arranges the rewards.

[0449] Output: Updated evaluation points and reward information.

[0450] These processing steps enable the system to efficiently produce dishes that meet the client's requests and provide service that also takes the client's feelings into consideration.

[0451] (Application Example 2)

[0452] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0453] In modern food delivery services, providing customized meals tailored to the customer's requests and preferences is challenging. In particular, generating recipes that reflect the customer's emotions is difficult with conventional technology and has not contributed to increased customer satisfaction. Furthermore, insufficient communication between the cook and the AI ​​makes troubleshooting and quality improvement during the cooking process difficult. Additionally, there is a need for a compensation system that accurately reflects customer feedback.

[0454] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0455] In this invention, the server includes means for receiving requests from clients, means for performing emotion analysis, means for generating new recipes based on a taste database, means for sending the generated recipes to a chef who recreates them, means for supporting communication between the chef and artificial intelligence, means for delivering the recreated dishes to clients, means for receiving evaluations from clients and reflecting the emotion analysis results in the chef's evaluation, means for the chef to communicate with the artificial intelligence using a chat function, and means for paying rewards based on the chef's evaluation. This makes it possible to provide customized dishes based on the client's emotions, improve quality through smooth communication between the chef and artificial intelligence, and realize the construction of a reward system that accurately reflects evaluations.

[0456] "Request reception" is a method of receiving and analyzing requests for dishes and flavor preferences from clients.

[0457] "Emotional analysis" is a method of determining a client's emotional state by analyzing their text and audio data.

[0458] A "taste database" is a database that stores information about ingredients and seasonings used in cooking.

[0459] "Recipe generation" is a method of creating new recipes by selecting appropriate ingredients and seasonings based on the client's requests and the results of emotional analysis.

[0460] A "cooking recreater" is someone who actually cooks a dish based on a generated recipe.

[0461] "Artificial intelligence" refers to an AI engine that supports recipe generation, emotion analysis, and communication with those who recreate the dishes.

[0462] "Delivery" refers to the method of delivering prepared and recreated meals to the customer's location.

[0463] "Receiving feedback" refers to the process of receiving feedback on the dishes from clients, analyzing that information, and incorporating it into the service.

[0464] The "chat function" is a means of text or voice communication that allows the cooking replicator to interact with artificial intelligence in real time.

[0465] "Reward payment" refers to a method of paying appropriate compensation based on the evaluation of the person who recreated the dish.

[0466] The system for implementing this invention uses multiple hardware and software components to receive requests from clients, perform emotional analysis, generate recipes based on a taste database, send them to a chef / recipe maker, support the cooking process, and deliver the recreated dishes.

[0467] System Configuration

[0468] 1. Server:

[0469] Request reception method: The system receives requests for dishes and taste preferences entered by the client and saves them as text data.

[0470] Sentiment analysis method: The received text data is analyzed to determine the client's emotions. Natural language processing tools such as TextBlob are used.

[0471] Recipe generation method: Based on the client's requests and emotion analysis results, appropriate ingredients and seasonings are selected from a taste database to generate a unique recipe. By using a generation AI model, flexible recipe suggestions are possible.

[0472] Evaluation reception method: Receive the client's evaluation and the resulting sentiment analysis, and store it in a database.

[0473] 2. The cooking reenactment operator's device:

[0474] Recipe reception method: The generated recipe is notified to the device and displayed.

[0475] AI chat function: You can chat with artificial intelligence in real time to resolve any questions that arise during cooking.

[0476] Cooking completion notification method: Notify the server when cooking is complete.

[0477] 3. Delivery System:

[0478] Delivery arrangement method: After receiving notification that cooking is complete, instruct the food delivery company to arrange delivery.

[0479] Operation details

[0480] The server receives requests from clients using the aforementioned request receiving mechanism and analyzes the client's emotional state using the emotion analysis mechanism. For example, when it receives a request such as "I want to eat something delicious but not spicy," it analyzes the request and determines it to be "positive."

[0481] Next, the recipe generation system generates an appropriate recipe based on the client's requests and the results of the sentiment analysis. For example, the generation AI model might suggest a recipe for a "delicious dish with mild spiciness." This recipe is then sent to the cook's device and displayed.

[0482] The cooking expert checks the recipe and begins cooking. If any questions arise along the way, they communicate with the artificial intelligence in real time using the terminal's chat function.

[0483] Once cooking is complete, the cook sends a completion notification to the server. The server receives this notification and arranges for the food to be delivered to the food delivery company via the delivery system.

[0484] Finally, after the client receives the dish, they access a rating form and submit their evaluation of the dish. This evaluation is also analyzed for sentiment and reflected in the evaluation of the cook who recreated the dish, and payment is made as needed.

[0485] Example of a prompt

[0486] Client's request: "I want to eat something delicious that isn't spicy."

[0487] Emotion analysis result: Positive

[0488] ---

[0489] Please generate: Create a recipe for a delicious dish with mild spiciness.

[0490] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0491] Step 1:

[0492] The server receives the client's request.

[0493] Input: Text data containing the client's cooking preferences and taste requests.

[0494] Processing: Receive data entered from a web form and save it as text data.

[0495] Output: Saved request data.

[0496] Step 2:

[0497] The server performs sentiment analysis.

[0498] Input: Saved request data.

[0499] Processing: Analyze the sentiment of text data using natural language processing tools such as TextBlob. Determine whether the sentiment is positive or negative.

[0500] Output: Sentiment analysis results (e.g., positive).

[0501] Step 3:

[0502] The server generates new recipes based on a taste database.

[0503] Input: Request data and sentiment analysis results.

[0504] Processing: Using a generative AI model, relevant ingredients and seasonings are searched from a taste database, and a recipe is generated based on the client's requests and the results of sentiment analysis.

[0505] Output: The generated recipe.

[0506] Step 4:

[0507] The server sends the generated recipe to the person who will recreate it.

[0508] Input: The generated recipe.

[0509] Processing: A notification is sent to the device of the person recreating the recipe, and the recipe details are displayed.

[0510] Output: The recipe displayed on the cooking reenactment device.

[0511] Step 5:

[0512] The cook's device receives a notification that the recipe has been received and begins cooking.

[0513] Input: The recipe displayed on the cooking reenactment device.

[0514] Process: Review the recipe and begin cooking. If any questions arise along the way, use the device's chat function to communicate with the artificial intelligence.

[0515] Output: A finished dish.

[0516] Step 6:

[0517] The cooking reenactment operator's terminal notifies the server when cooking is complete.

[0518] Input: A finished dish.

[0519] Processing: Notify the server that cooking is complete.

[0520] Output: Cooking completion notification sent to the server.

[0521] Step 7:

[0522] The server arranges for the food to be delivered through a delivery service.

[0523] Input: Cooking completion notification.

[0524] Processing: Provide food delivery service providers with information regarding food pickup and delivery address, and arrange delivery.

[0525] Output: Notification that shipping arrangements have been completed.

[0526] Step 8:

[0527] The user receives the food and accesses the rating form.

[0528] Input: The food received.

[0529] Process: Access the rating form on the website and enter your rating for the dish.

[0530] Output: Input evaluation data.

[0531] Step 9:

[0532] The server stores evaluation data and sentiment analysis results, and uses them to evaluate the cooking recreater.

[0533] Input: The entered evaluation data.

[0534] Processing: Receive evaluation data and perform sentiment analysis again using TextBlob or similar methods. Save the results to a database and reflect them in the evaluation of the cooking recreater. Also, calculate and process payment as needed.

[0535] Output: Updated cooking replicator evaluation and reward data.

[0536] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0537] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0538] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0539] [Second Embodiment]

[0540] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0541] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0542] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0543] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0544] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0545] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0546] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0547] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0548] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0549] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0550] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0551] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0552] This invention relates to a system that generates a unique recipe based on the client's requests, which is then reproduced by a chef and delivered to the client. This system is implemented as follows.

[0553] Request acceptance

[0554] server

[0555] The server receives requests from clients. Clients enter their cooking preferences and taste requests into a form on the website and click the submit button, sending the request to the server. The server analyzes the received request and forwards it to the recipe generation subsystem.

[0556] Specific example

[0557] The client types and submits a request stating, "I want to eat an exotic dish that is very sour and not too spicy."

[0558] Recipe generation

[0559] AI Server

[0560] The server receives the client's request and retrieves information on relevant ingredients and seasonings from the taste database. Based on the data, it generates a recipe suitable for the request. The generated recipe is then sent to the cooking and reproduction subsystem.

[0561] Processing explanation in natural language

[0562] The AI ​​server consults a taste database and selects ingredients associated with "sourness" and "mild spiciness." Based on these selected ingredients, it then creates recipes for exotic dishes.

[0563] Recipe distribution and cooking

[0564] The terminal of the person recreating the cooking recipe.

[0565] The cook's device receives a recipe notification. They review the recipe, organize the necessary ingredients and cooking steps, resolve any uncertainties using the AI ​​server's chat function, and then begin cooking.

[0566] Processing explanation in natural language

[0567] The cooking model receives a recipe and prepares the dish following the displayed cooking steps. If any questions arise during cooking, they can ask them via chat with the AI ​​server and receive answers.

[0568] Arranging delivery

[0569] The terminal of the person recreating the cooking recipe.

[0570] Once cooking is complete, the person recreating the dish sends a cooking completion notification to the server.

[0571] server

[0572] The server receives a notification that cooking is complete and instructs the food delivery company to arrange delivery. The delivery company picks up the food and delivers it to the customer.

[0573] Processing explanation in natural language

[0574] The customer provides the food delivery service with their information and the food, requesting prompt delivery. The delivery service picks up the food and delivers it to the customer's address.

[0575] Receiving and rating the food

[0576] User's terminal

[0577] The customer receives the food and accesses a review form on the website. They then enter and submit a review regarding the quality of the food and the speed of delivery.

[0578] server

[0579] The server receives the evaluations and saves them to the database. Furthermore, the evaluations are reflected in the evaluation points of the cooking recreaters, and the rankings are updated.

[0580] Processing explanation in natural language

[0581] The evaluation results are recorded in a database and used to assess the performance of the recipe recreaters. The recipe recreater rankings are also updated, and outstanding recreaters receive additional rewards.

[0582] Through these processes, the present invention provides a system that generates, quickly reproduces, and delivers unique recipes based on the client's requests.

[0583] The following describes the processing flow.

[0584] Step 1: Accepting the request

[0585] server

[0586] The system recognizes that a user has entered a specific cooking request into a request form on the website and clicked the submit button. The server receives this data and analyzes the request. The analysis results are then transferred to the recipe generation subsystem.

[0587] Step 2: Analyze requirements and generate recipes

[0588] AI Server

[0589] The server analyzes the client's request and consults a taste database. It selects ingredients and seasonings that match the taste characteristics based on the request and generates an original recipe based on them. The generated recipe is then sent to the cooking reproduction subsystem.

[0590] Step 3: Receive and confirm the recipe

[0591] The terminal of the person recreating the cooking recipe.

[0592] The person recreating the recipe receives a notification on their device and confirms that a new recipe has arrived. They view the recipe details and check the required ingredients and cooking instructions.

[0593] Step 4: Communication with AI

[0594] The terminal of the person recreating the cooking recipe.

[0595] The person recreating the recipe asks the AI ​​server any questions or uncertainties. They receive immediate answers from the server using the chat function. This exchange ensures that the information necessary for recipe recreation is accurately conveyed.

[0596] Step 5: Cooking

[0597] The terminal of the person recreating the cooking recipe.

[0598] The cooking replicator prepares the dish according to the recipe. They proceed step by step, checking each step along the way, and communicate with the AI ​​server again if any problems arise.

[0599] Step 6: Notification that cooking is complete

[0600] The terminal of the person recreating the cooking recipe.

[0601] Once cooking is complete, the person reproducing the cooking process notifies the server of the completion. They then transmit the cooking completion status using a communication method.

[0602] Step 7: Arrange delivery

[0603] server

[0604] The server receives a cooking completion notification and instructs the food delivery company to arrange delivery. It also provides the delivery company with information on where to pick up and deliver the food.

[0605] Step 8: Food Delivery

[0606] Delivery company

[0607] A delivery company picks up the food and delivers it quickly to the customer. When the customer receives the food, a delivery completion notification is sent to the server.

[0608] Step 9: Receive and rate your food

[0609] User's terminal

[0610] The customer receives the food and accesses a review form on the website. They then enter and submit a review about the taste, appearance, delivery time, etc.

[0611] Step 10: Reflecting the evaluation

[0612] server

[0613] The server receives the evaluation data and stores it in the database. The evaluation results are reflected in the evaluation of the cooking recreaters, and the recreaters' rankings are updated. In addition, the payment of rewards is processed based on the evaluations.

[0614] These specific processing steps enable the system to efficiently and quickly provide original dishes based on the client's requests.

[0615] (Example 1)

[0616] Next, we will describe Example 1. 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".

[0617] The current recipe generation and food delivery system has several problems, including accurately reflecting the client's requests in generating recipes, facilitating smooth communication with the cooks, and managing delivery arrangements and evaluations. Specifically, these include malfunctions in the function for properly analyzing client requests, a lack of means to resolve questions about the generated recipes, and inefficiencies in delivery arrangements. There are also problems with properly reflecting client evaluation data in the performance evaluations and compensation of the cooks.

[0618] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0619] In this invention, the server includes means for receiving requests from clients, means for generating new recipes based on a taste database, means for transmitting the generated recipes to a cooking recreater, means for supporting communication between the cooking recreater and artificial intelligence, means for delivering the recreated dishes to the clients, means for receiving evaluations from clients and reflecting them in the cooking recreater's evaluation, means for arranging delivery with a delivery company, means for inputting questions to help the cooking recreater resolve any doubts based on the generated recipes and obtaining answers, means for analyzing the client's requests and extracting information on seasonings and ingredients, means for saving the client's evaluations in a database and updating the cooking recreater's ranking, and means for providing additional rewards to the cooking recreater based on the client's evaluation. This enables the generation of recipes that accurately reflect the client's requests, smooth communication with cooking recreaters, efficient delivery arrangements, and appropriate reflection of evaluations from clients.

[0620] A "client" is an individual or group that submits a request for a dish to the system.

[0621] A "taste database" is a database that stores and manages information about the taste of various ingredients and seasonings.

[0622] "Recipe generation" is the process of selecting appropriate ingredients and seasonings based on the client's requests and constructing a unique cooking procedure.

[0623] A "cooking recreater" is an individual or group whose role is to actually cook a dish based on a generated recipe.

[0624] "Artificial intelligence" is a technology that performs natural language processing and data analysis within a system to support communication between clients and those who recreate the dishes.

[0625] "Supporting communication" refers to a function that allows cooking enthusiasts to resolve any uncertainties they may have regarding cooking through artificial intelligence.

[0626] "Delivery" refers to the process of delivering the dishes prepared by the chef to the client.

[0627] "Reviews" refer to the process by which clients provide feedback on the quality of the food and the speed of delivery.

[0628] A "delivery service provider" is an individual or company that provides a service to deliver the recreated dishes to the customer.

[0629] "Enter a question and get an answer" refers to the process where a cooking simulator asks artificial intelligence questions that arise during cooking and receives the answers.

[0630] "Extracting information on seasonings and ingredients" is the process of analyzing the client's requests and obtaining data on the most suitable seasonings and ingredients based on those requests.

[0631] A "database" is a system that efficiently stores and manages various types of data, and allows that data to be retrieved as needed.

[0632] "Ranking" is a system that assigns rankings based on the performance evaluation of those who recreate the dishes.

[0633] "Additional rewards" refer to preliminary gratuities or bonuses paid to recipe recreaters who receive outstanding ratings.

[0634] This invention is a system that generates a unique recipe based on the client's request, a chef prepares the dish based on that recipe, and delivers it to the client. This system is implemented through the following main means.

[0635] Request acceptance

[0636] server

[0637] The server provides a means for receiving requests from clients. When a client enters their culinary preferences and taste requests into a form on the website and clicks the submit button, the request is sent to the server. For example, a client might enter and submit, "I want an exotic dish that is very sour and not too spicy." The server analyzes the received request and forwards it to the recipe generation subsystem.

[0638] Recipe generation

[0639] AI Server

[0640] The server receives the client's request and retrieves information on relevant ingredients and seasonings from the taste database. Specifically, the AI ​​server refers to the taste database and selects ingredients associated with "sourness" and "mild spiciness." Then, it creates a recipe for an exotic dish based on the selected ingredients. The generated recipe is sent to the cooking reproduction subsystem. For example, it might select sour ingredients such as "lemon" and "coriander" to construct a recipe for a mildly spicy exotic dish.

[0641] Example of a prompt:

[0642] "Please generate recipes for exotic dishes that are strongly sour and mildly spicy."

[0643] Recipe distribution and cooking

[0644] The terminal of the person recreating the cooking recipe.

[0645] The cooking model's device receives a recipe notification from the AI ​​server. The device displays the recipe details and prepares the necessary ingredients for cooking. The cooking model begins cooking according to the displayed recipe. If any questions arise during cooking, they can use the chat function on the device to ask questions to the AI ​​server. For example, if they are making beef stroganoff and want more detailed instructions about the cooking time, they can ask via chat.

[0646] Example of a prompt:

[0647] "How long do you need to cook beef stroganoff?"

[0648] Arranging delivery

[0649] The terminal of the person recreating the cooking recipe.

[0650] Once cooking is complete, the person recreating the cooking process sends a completion notification to the server. For example, they might click the "Cooking Complete" button on their device to notify the server of the completion status.

[0651] server

[0652] The server receives a cooking completion notification and instructs the food delivery company to arrange delivery. The delivery company picks up the food and delivers it to the customer. For example, the server calls the delivery company's (e.g., Uber Eats) API to arrange food delivery.

[0653] Example of a prompt:

[0654] "Please arrange for beef stroganoff to be delivered to the address XX."

[0655] Receiving and rating the food

[0656] User's terminal

[0657] The customer receives the food and accesses a review form on the website. They enter and submit a review regarding the quality of the food and the speed of delivery. For example, the customer might enter and submit a review stating, "The food was delicious, I would like to use this service again."

[0658] server

[0659] The server receives the evaluations and saves them to the database. Furthermore, it reflects the evaluations in the cooking recreater's evaluation points and updates the rankings. For example, the server analyzes the evaluation data and updates the cooking recreater's evaluation points. It records it in the database as "4.5 points on a 5-point scale."

[0660] In this way, this system utilizes various databases and artificial intelligence to efficiently carry out a series of processes, from generating recipes based on the client's requests to cooking, delivery, and evaluation.

[0661] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0662] Step 1: Accepting requests

[0663] The server provides a form on the website to receive requests from clients. By entering their desired dishes and taste preferences into the form and clicking the submit button, the request is sent to the server. The input data includes specific dish characteristics and desired tastes. The server analyzes the received request, breaks down the client's request into specific keywords, and transfers this as analysis data to the recipe generation subsystem.

[0664] Input: Request from the client (e.g., "An exotic dish with a strong sour taste and mild spiciness")

[0665] Output: Decomposed keywords (e.g., "sourness", "mild spiciness", "exotic")

[0666] Specific operation: The client enters their request into an input form, and the server receives it and breaks it down into keywords.

[0667] Step 2: Recipe Generation

[0668] The server retrieves information on relevant ingredients and seasonings from a taste database based on the client's request. Based on the retrieved data, the AI ​​server generates a recipe suitable for the client. Specifically, the AI ​​model matches the decomposed keywords with data from the taste database to select appropriate ingredients and seasonings. Based on these, it constructs specific cooking steps and completes the recipe.

[0669] Input: Keywords (e.g., "sourness", "mild spiciness", "exotic"), data from a taste database.

[0670] Output: Generated recipe (e.g., "Exotic Chicken Dish with Lemon")

[0671] Specific operation: The AI ​​server accesses the database, and the AI ​​model generates a cooking recipe.

[0672] Step 3: Recipe notification

[0673] The cooking model's device receives a recipe notification from the AI ​​server. The recipe details are displayed on the device, and the model performs the necessary preparations for cooking. The recipe includes a specific list of ingredients and cooking instructions.

[0674] Input: Generated recipe

[0675] Output: Displayed recipe information (list of ingredients and cooking instructions)

[0676] Specific operation: The cooking recreater's device receives and displays the recipe from the AI ​​server.

[0677] Step 4: Cooking

[0678] The person recreating the dish begins cooking according to the displayed recipe. If any questions arise during cooking, they can use the chat function with the AI ​​server via their device to ask questions. The AI ​​server provides answers and resolves the questions.

[0679] Input: Recipe information, questions from the person who recreated the dish.

[0680] Output: Finished dish, response from AI server

[0681] Specific actions: The person recreating the recipe will measure the ingredients and cook according to the recipe. If any questions arise during the process, they will use the chat function.

[0682] Step 5: Notification that cooking is complete

[0683] Once cooking is complete, the person reproducing the cooking sends a completion notification to the server. The server receives the notification and prepares to proceed to the next step.

[0684] Input: Cooking completion notification

[0685] Output: Completion notification to the server

[0686] Specific action: Click the "Cooking Complete" button on the terminal and send a completion notification to the server.

[0687] Step 6: Arrange delivery

[0688] The server receives a notification that cooking is complete and instructs the food delivery company to arrange delivery. The delivery company picks up the food and delivers it to the customer.

[0689] Input: Cooking completion notification, delivery company information

[0690] Output: Execution of delivery arrangements, instructions to the delivery company.

[0691] Specific operation: The server calls the delivery company's API to arrange for food delivery.

[0692] Step 7: Receive and rate your food

[0693] The customer receives the food and accesses a review form on the website. They enter and submit a review regarding the quality of the food and the speed of delivery.

[0694] Input: Client's evaluation

[0695] Output: Evaluation data to the server

[0696] Specific operation: The client enters feedback into the evaluation form and sends it to the server.

[0697] Step 8: Saving and reflecting the evaluation

[0698] The server receives the evaluations and stores them in the database. Furthermore, the evaluations are reflected in the cooking recreater's evaluation points, updating the rankings. Cooking recreaters who receive excellent evaluations are given additional rewards.

[0699] Input: Evaluation data

[0700] Output: Updated evaluation points and rankings, and reflection of additional rewards.

[0701] Specific operation: The server analyzes the evaluation data, saves it to the database, and updates the evaluation points and rankings of the cooking recreaters.

[0702] (Application Example 1)

[0703] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0704] In modern society, it is difficult to easily obtain special dishes tailored to individual tastes and preferences. Furthermore, there is a lack of systems that guarantee that online orders will meet expectations in terms of taste and quality. In addition, the food preparation process and delivery arrangements are time-consuming, creating a need for efficient systems that provide customer satisfaction.

[0705] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0706] In this invention, the server includes means for receiving requests from clients, means for generating new recipes based on a taste database, means for transmitting the generated recipes to a chef who recreates them, means for supporting communication between the chef and the AI, means for delivering the recreated dishes to the clients, means for receiving evaluations from clients and reflecting them in the chef's evaluation, means for receiving requests via a smartphone application, means for generating recipes using an AI server, means for arranging delivery in cooperation with a delivery platform, and means for transmitting evaluation results from the client's terminal to the server and saving them in a database. This enables the efficient generation of special dishes tailored to the individual requests of clients, and allows for the provision of high-quality dishes by chefs and rapid delivery.

[0707] A "client" is an individual or group that makes a special request for a particular dish to the system.

[0708] A "request reception method" is an interface that provides the functionality to collect requests for dishes and taste preferences from clients and send them to the server.

[0709] A "taste database" is a database that stores information on ingredients and seasonings used in cooking, and allows users to refer to the taste characteristics of each.

[0710] A "recipe generation method" is a system that automatically generates unique recipes by selecting appropriate ingredients and seasonings from a taste database based on the client's requests.

[0711] A "cooking recreater" is a person or robot that actually cooks a dish based on a generated recipe.

[0712] A "recipe transmission means" is a communication means for notifying the person who will be cooking and reproducing the generated recipe.

[0713] The "communication support system between cooking replicators and AI" is a mechanism that provides a chat function to allow cooking replicators to resolve any questions they may have by interacting with AI.

[0714] "Delivery methods" refer to food delivery services and systems that quickly deliver recreated dishes to the customer.

[0715] The "evaluation receiving method" is an interface that collects evaluations from clients regarding the quality of the food and the speed of delivery, and sends that data to the server.

[0716] A "smartphone application" is software on a mobile device that allows clients to input their requests and manage their orders.

[0717] An "AI server" is a server equipped with artificial intelligence that analyzes the client's requests and generates recipes by referring to a taste database.

[0718] A "delivery platform" is an online platform that instructs food delivery companies to arrange deliveries and delivers food to customers.

[0719] A "rating and storage method" is a system that stores the client's evaluation results in a database and reflects them in the performance evaluation of the cooking and recipe reproduction team.

[0720] This invention relates to a system that generates a unique recipe according to the client's request, and then a chef prepares the dish based on that recipe and delivers it to the client.

[0721] This system includes the following steps:

[0722] Request acceptance

[0723] server:

[0724] The customer enters their culinary preferences and taste requests via a smartphone application. For example, they might enter a request such as, "I'd like an exotic dish that's quite sour and not too spicy," into the form and click the submit button. This request is sent to the server and stored in the database along with the customer's information.

[0725] Recipe generation

[0726] AI Server:

[0727] Upon receiving a request from a client, the server consults a taste database to obtain information on ingredients and seasonings that match the client's preferences. Based on this data, the AI ​​server generates a recipe that suits the request. For example, it might select ingredients related to "sourness" or "mild spiciness" to create a recipe for an exotic dish.

[0728] Recipe distribution and cooking

[0729] The device of the person recreating the recipe:

[0730] The generated recipe is sent to the cook's device. The cook reviews the recipe on their device and organizes the necessary ingredients and cooking steps. Furthermore, if the cook has any questions during the cooking process, they can use the chat function with the server to ask questions and receive answers from the AI ​​server.

[0731] Arranging delivery

[0732] server:

[0733] Once cooking is complete, the cook sends a completion notification to the server. The server receives the completion notification and, in conjunction with the food delivery platform, issues instructions for delivery. The food delivery company picks up the food and delivers it to the customer.

[0734] Receiving and rating the food

[0735] Client's device:

[0736] After receiving their meal, the customer accesses a review form via a smartphone application. They enter and submit their evaluation regarding the quality of the food and the speed of delivery. The server receives the evaluation and stores it in a database. Furthermore, this evaluation is reflected in the evaluation points of the cook / recipe recreater, and the ranking is updated.

[0737] Examples of specific cases and prompt statements

[0738] For example, if the client requests "spicy but not too hot Indian food," the following prompt will be sent to the AI ​​server:

[0739] text

[0740] User Request:

[0741] Desired Cuisine: Indian

[0742] Taste preferences: Spicy but mild heat level

[0743] AI Task:

[0744] Generate a recipe using the given preferences, including a list of ingredients and step-by-step instructions.

[0745] The hardware and software used include Amazon Web Services (AWS) EC2, S3, RDS, Google Cloud AI Platform, React Native, Node.js (Express framework), PostgreSQL, and the Uber Eats API. By combining these, it becomes possible to efficiently generate special dishes tailored to the individual requests of customers, enabling high-quality food delivery and rapid delivery.

[0746] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0747] Step 1:

[0748] Request acceptance

[0749] Users enter their food preferences and taste requests via a smartphone application. Specifically, a user might enter "I want to eat an exotic dish that is very sour and not too spicy" into a form within the app and click the submit button. The entered data is sent to the server as the user's request. The server receives the request data and stores it in a database along with the requester's information.

[0750] Input: Food request (specific tastes and preferences)

[0751] Output: Saved client request data

[0752] Step 2:

[0753] Recipe generation

[0754] The server receives the client's request data and sends it to the AI ​​server. The AI ​​server consults a taste database to obtain information on relevant ingredients and seasonings. Based on this data, the AI ​​server generates specific prompt statements and creates recipes for exotic dishes based on the relevant ingredients. For example, based on "User Request: Desired Cuisine: Indian, Taste preferences: Spicy but mild heat level," it selects appropriate ingredients and seasonings and creates a recipe.

[0755] Input: Client's request data

[0756] Output: Generated recipe

[0757] Step 3:

[0758] Recipe distribution

[0759] The server receives the generated recipe and sends it to the cook's terminal. The cook reviews the recipe on their terminal and organizes the necessary ingredients and cooking steps. The server sends a notification to the cook's terminal at the same time as sending the recipe.

[0760] Input: Generated recipe

[0761] Output: Recipe notification sent to the cook / recipe recreater

[0762] Step 4:

[0763] Cooking progress

[0764] The cooking model proceeds with cooking according to the recipe sent to their device. If any questions arise during cooking, the model uses the device's chat function to ask questions to the AI ​​server. The AI ​​server receives the questions and provides appropriate answers.

[0765] Input: Recipe, questions from the cook / recipe recreater

[0766] Output: Finished dish, AI server's answers to any questions.

[0767] Step 5:

[0768] Arranging delivery

[0769] The terminal sends a notification to the server indicating that cooking is complete. The server receives this notification and, in cooperation with the food delivery platform, issues instructions for delivery. The food delivery company, having received the delivery instructions, picks up the food and delivers it to the customer.

[0770] Input: Notification of cooking completion

[0771] Output: Delivery arrangement instructions to the food delivery platform.

[0772] Step 6:

[0773] Receiving and rating the food

[0774] After receiving their meal, the client accesses a review form via a smartphone application. The client enters and submits their evaluation regarding the quality of the food and the speed of delivery. The server receives the evaluation and stores it in a database. This evaluation is reflected in the evaluation points of the cook who recreated the meal, and the ranking is updated.

[0775] Input: Client's evaluation

[0776] Output: Evaluation data stored in the database, updated ranking of cooking replicators.

[0777] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0778] This invention relates to a system that generates a unique recipe based on the client's requests, which is then reproduced by a chef and delivered to the client. This system is characterized by its integration of an emotion engine to recognize the client's emotions and to perform the recipe generation and evaluation process more precisely based on those emotions.

[0779] Request acceptance

[0780] server

[0781] The server receives requests from clients. Clients enter their preferences for specific dishes or tastes into a form on the website and click the submit button to send their requests. The server receives this data and analyzes the request.

[0782] Emotional Engine

[0783] The emotion engine analyzes the client's emotions when they input their request. The analysis results are obtained through text and voice analysis and provided to the recipe generation subsystem as information that includes the client's intent and emotional elements.

[0784] Recipe generation

[0785] AI Server

[0786] The server receives the client's request and the analysis results from the emotion engine, and retrieves information on relevant ingredients and seasonings from the taste database. Based on the data, it generates a recipe suitable for the request. The generated recipe is sent to the cooking reproduction subsystem.

[0787] Processing explanation in natural language

[0788] The AI ​​server selects ingredients related to "sourness" and "mild spiciness" from a taste database, and then creates recipes for exotic dishes by making adjustments according to the client's preferences.

[0789] Recipe distribution and cooking

[0790] The terminal of the person recreating the cooking recipe.

[0791] The person recreating the recipe receives a notification on their device and confirms that a new recipe has arrived. They view the recipe details and check the ingredients and cooking steps. They use the chat function with the AI ​​server to resolve any questions and then begin cooking.

[0792] Processing explanation in natural language

[0793] The cooking assistant receives a recipe and follows the displayed cooking instructions to prepare the dish. If any problems arise along the way, they can ask questions via chat with the AI ​​server and receive answers to continue cooking.

[0794] Arranging delivery

[0795] The terminal of the person recreating the cooking recipe.

[0796] Once cooking is complete, the person reproducing the cooking sends a notification to the server indicating that cooking is finished. The status of cooking completion is sent to the server using a communication method.

[0797] server

[0798] The server receives a cooking completion notification and instructs the food delivery company to arrange delivery. It also provides the delivery company with information on where to pick up and deliver the food.

[0799] Processing explanation in natural language

[0800] The customer provides the food delivery service with their information and the food, requesting prompt delivery. The delivery service picks up the food and delivers it to the customer's address.

[0801] Receiving and rating the food

[0802] User's terminal

[0803] The customer receives the food and accesses a review form on the website. They enter and submit a review regarding the quality of the food, delivery time, etc. An emotion engine analyzes the customer's emotions during the review process and incorporates that data into the evaluation process.

[0804] server

[0805] The server receives the evaluations and stores them in the database. The results analyzed by the emotion engine are also stored and reflected in the evaluation of the cooking recreater. Based on the evaluation results, the cooking recreater's performance is assessed and the ranking is updated. In addition, the payment of rewards is also processed based on the evaluation.

[0806] Processing explanation in natural language

[0807] Evaluation data and sentiment analysis results are recorded in a database and reflected in the evaluation points of the cooking recreaters. The recreater rankings are updated, and outstanding recreaters receive additional rewards.

[0808] This configuration allows the system to not only efficiently and quickly provide unique dishes based on the client's requests, but also to deliver service that takes the client's emotions into consideration.

[0809] The following describes the processing flow.

[0810] Step 1: Accepting the request

[0811] server

[0812] The system recognizes that a user has entered specific food requests into a request form on the website and clicked the submit button. The server receives this data and analyzes the request. The data is then sent to the emotion engine through text and voice analysis.

[0813] Emotional Engine

[0814] The emotion engine analyzes the emotions expressed by the client when they input their request. The analysis results are encoded based on the client's text expression, voice tone, and contextual analysis. The analysis results are then provided to the recipe generation subsystem.

[0815] Step 2: Analyze requirements and generate recipes

[0816] AI Server

[0817] The server receives the client's request and the analysis results from the emotion engine. It retrieves information on relevant ingredients and seasonings from the taste database and generates a recipe suitable for the client's emotional state. The generated recipe is further adjusted to reflect the analysis results from the emotion engine.

[0818] Step 3: Receive and confirm the recipe

[0819] The terminal of the person recreating the cooking recipe.

[0820] The person recreating the recipe receives a notification on their device and confirms that a new recipe has arrived. They view the recipe details and check the ingredients and cooking instructions. They use the chat function with the AI ​​server to resolve any questions.

[0821] Step 4: Communication with AI

[0822] The terminal of the person recreating the cooking recipe.

[0823] The cooking recreater asks the AI ​​server any questions or uncertainties. The AI ​​server provides immediate answers. The cooking recreater uses the chat function to confirm the appropriate cooking procedure as they proceed with the work.

[0824] Step 5: Cooking

[0825] The terminal of the person recreating the cooking recipe.

[0826] The cooking assistant prepares the dish according to the recipe. They proceed while checking each step of the cooking process, and if any problems arise along the way, they communicate with the AI ​​server again via chat. Once cooking is complete, they send a completion notification from their device.

[0827] Step 6: Notification that cooking is complete

[0828] The terminal of the person recreating the cooking recipe.

[0829] Once cooking is complete, the person recreating the dish reports the completion to the server. The report may include photos of the dish and comments.

[0830] Step 7: Arrange delivery

[0831] server

[0832] The server receives a notification that cooking is complete and instructs the food delivery company to arrange delivery. Delivery arrangements include the status of the food, delivery address information, and delivery time.

[0833] Step 8: Food Delivery

[0834] Delivery company

[0835] A delivery company picks up the food and delivers it quickly to the customer. Once the customer receives the food, a delivery completion notification is sent to the server.

[0836] Step 9: Receive and rate your food

[0837] User's terminal

[0838] The customer receives the food and accesses the review form on the website. They enter detailed feedback on the quality of the food, delivery time, etc., and also allow the emotion engine to analyze their feelings. They then submit the review.

[0839] Step 10: Reflecting the evaluation

[0840] server

[0841] The server receives the evaluation and stores it in the database along with the analysis results from the emotion engine. The evaluation points of the cooking recreater are then reflected, including the emotion analysis results. The ranking of the recreaters is updated based on the evaluation results and analysis data, and payment procedures for rewards are carried out as needed.

[0842] These processing steps enable the efficient and rapid delivery of original dishes based on the client's requests and feelings, while also providing a high level of service that takes the client's emotions into consideration.

[0843] (Example 2)

[0844] Next, we will describe Example 2. 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".

[0845] Traditionally, generating recipes based on client requests and then recreating those recipes has struggled to take the client's emotions into account. As a result, it was often impossible to provide dishes that matched the client's desired taste and emotions, leading to decreased satisfaction. Furthermore, if communication between the cooking recreater and the artificial intelligence was not smooth, it could potentially affect the quality of the cooking.

[0846] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0847] In this invention, the server includes means for receiving requests from clients, means for analyzing the requests and emotions of the clients, means for generating new recipes based on a taste database, means for transmitting the generated recipes to a chef who will recreate them, means for supporting communication between the chef and artificial intelligence, means for delivering the recreated dishes to the clients, and means for receiving feedback from clients and reflecting it in the chef's evaluation. This makes it possible to generate recipes that take the client's emotions into consideration and to achieve smooth communication between the chef and artificial intelligence. As a result, client satisfaction can be improved and high-quality dishes can be provided.

[0848] A "client" is an individual or group that uses the system to request a specific dish and asks for its preparation and delivery.

[0849] "Requests" refer to the types of dishes and taste preferences that the client desires, and this information is entered into the system by the client.

[0850] A "server" is a computer that receives requests from clients, analyzes them, exchanges data with other subsystems, and manages the entire system.

[0851] An "emotion engine" is a technology that analyzes the client's emotions from input text or audio and provides the analysis results to other parts of the system.

[0852] A "taste database" is a database that stores information about various ingredients and seasonings, and is a collection of data used when generating recipes.

[0853] A "recipe generation method" is a system that, based on the client's requests and the results of emotion analysis, selects appropriate ingredients and seasonings from a taste database and generates a unique recipe.

[0854] A "cook" is the person who receives a generated recipe and actually prepares the dish based on it.

[0855] "Artificial intelligence" is a computing system that can perform specific tasks automatically, and has functions such as suggesting recipes and answering questions during the cooking process.

[0856] "Delivery method" refers to the function or service used to deliver food prepared by a cook to the customer.

[0857] "Rating" refers to the act of a customer expressing their satisfaction level and opinions regarding the food they received and its delivery, and this information is sent to the system as feedback.

[0858] "Chef evaluation" refers to an evaluation that quantifies or ranks the chef's performance based on evaluation data from clients and sentiment analysis results.

[0859] Modes for carrying out the invention

[0860] This invention is a system that generates a unique recipe based on the client's requests, has a chef recreate it, and delivers it to the client. A key feature of this system is that it incorporates an emotion engine to recognize the client's emotions and uses that to refine the recipe generation and evaluation process.

[0861] Request acceptance

[0862] server

[0863] The server receives requests from clients. Clients enter their preferences for specific dishes or tastes into a form on the website and click the submit button to send their requests. The server receives this data and analyzes the request.

[0864] For example, if a client enters their request for a "sweet and sour dessert" and clicks the submit button, the server receives and analyzes that data.

[0865] Emotional Engine

[0866] The emotion engine analyzes the client's emotions when they input their request. The analysis results are obtained through text and voice analysis and provided to the recipe generation subsystem as information that includes the client's intent and emotional elements.

[0867] For example, if a client enters "I'm tired from work today, so I want a dish that will lift my spirits," the emotion engine will identify the emotions "fatigue" and "wanting to lift my spirits" from that sentence and provide that information as analysis results to the recipe generation subsystem.

[0868] Recipe generation

[0869] AI Server

[0870] The server receives the client's request and the analysis results from the emotion engine, and retrieves information on relevant ingredients and seasonings from the taste database. Based on this, it generates a recipe suitable for the request. The generated recipe is then sent to the cook's terminal.

[0871] As a concrete example, the server selects ingredients such as "lemon" and "honey" from a taste database for a client who prefers "sourness" and "sweetness," and then creates an exotic dish recipe based on these ingredients. For example, the prompt might read, "Generate a recipe for a client who wants something sour with a little sweetness."

[0872] Recipe distribution and cooking

[0873] Cook's terminal

[0874] The cook receives a notification on their device and confirms that a new recipe has arrived. They view the recipe details and check the ingredients and cooking instructions. If necessary, they use the chat function with the AI ​​server to resolve any questions and then begin cooking.

[0875] For example, a cook receives a notification for a new recipe and checks it on their device. They carefully examine the ingredients and steps, and then send questions to the AI ​​server via chat, such as, "When is the best time to add this spice?"

[0876] Arranging delivery

[0877] Cook's terminal

[0878] Once cooking is complete, the cook sends a notification to the server indicating completion. The status of cooking completion is sent to the server using a communication method.

[0879] For example, when a cook sends a notification to the server that the cooking is complete, the server automatically instructs the food delivery company to pick up the food and provide the delivery address information (the client's address).

[0880] server

[0881] The server receives a notification that cooking is complete and instructs the food delivery company to arrange delivery. The server provides the delivery company with information on where to pick up the food and the delivery address.

[0882] Receiving and rating the food

[0883] User's terminal

[0884] The customer receives the food and enters their review on a rating form on the website. The review includes the quality of the food and delivery time, and an emotion engine analyzes the emotions felt during the review process.

[0885] For example, if a client enters "The food was delicious, but the delivery was slow" into the review form, the emotion engine analyzes both "satisfied" and "dissatisfied" emotions from this review and incorporates that information into the review data.

[0886] server

[0887] The server receives the evaluations and stores them in the database. The evaluations and sentiment analysis results are reflected in the chef's performance evaluation and are also used for updating rankings and reward procedures.

[0888] For example, the server updates the chef's evaluation points based on the client's evaluation data and the results of their sentiment analysis. If a chef receives many high ratings, they may receive additional compensation.

[0889] Through these processes, the system can efficiently generate dishes that meet the client's requests and provide service that also takes the client's feelings into consideration.

[0890] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0891] Step 1: Receiving the client's request

[0892] The server receives requests from clients through an input form on the website. The entered request (e.g., "sweet and sour dessert") is sent to the server.

[0893] Input: The client's requests regarding specific dishes and taste preferences, entered on the website.

[0894] Specific action: The requester enters their desired "sweet and sour dessert" and clicks the submit button.

[0895] Output: Client's requested data.

[0896] Step 2: Analysis of the requirements

[0897] The server analyzes the request data it receives and understands its content. The analysis results are classified into categories and tastes related to the cuisine.

[0898] Input: Client's request data.

[0899] Specific operation: The server analyzes the request data "sweet and sour dessert" and recognizes the taste "sweet and sour" and the category "dessert".

[0900] Output: Request analysis results (Example: Taste = "Sweet and sour", Category = "Dessert").

[0901] Step 3: Emotional Analysis

[0902] The server passes the request data to the emotion engine, which then analyzes the client's emotions.

[0903] Input: Request data.

[0904] Specific operation: The server passes the text "I'm tired from work today, so I want some food to lift my spirits" to the emotion engine, which identifies the emotions "fatigue" and "want to lift my spirits."

[0905] Output: Emotion analysis results (e.g., emotion = "fatigue", intention = "want to cheer up").

[0906] Step 4: Obtain relevant data

[0907] Based on the client's requests and the results of the emotional analysis, the server retrieves information on relevant ingredients and seasonings from the taste database.

[0908] Input: Request analysis results and emotion analysis results.

[0909] Specific operation: The server searches the taste database for ingredients and seasonings related to "sweet and sour" and "dessert" (e.g., "lemon," "honey").

[0910] Output: Related data (e.g., Ingredient = "Lemon", Seasoning = "Honey").

[0911] Step 5: Recipe Generation

[0912] The server uses relevant data to input prompt messages into the AI ​​model, which then generates a recipe that meets the requirements.

[0913] Input: Related data.

[0914] Specific operation: The server inputs a prompt message to the AI ​​model saying, "Please generate a recipe for a customer who wants something sour with a little sweetness," and the AI ​​generates the recipe.

[0915] Output: Generated recipe (e.g., "Lemon Cheesecake").

[0916] Step 6: Submit the recipe

[0917] The server sends the generated recipe to the cook's terminal.

[0918] Input: The generated recipe.

[0919] Specific operation: The server sends the generated "Lemon Cheesecake" recipe to the cook's terminal.

[0920] Output: The cook's terminal receives the recipe.

[0921] Step 7: Check the recipe

[0922] The cook's device receives a notification and confirms that a new recipe has arrived. They view the recipe details and check the ingredients and cooking instructions.

[0923] Input: The generated recipe.

[0924] Specific action: The cook receives a notification on their device saying "A new recipe has arrived," and then checks the recipe details.

[0925] Output: Recipe details displayed on the cook's terminal.

[0926] Step 8: Communication with the AI ​​Server

[0927] The cook's device uses a chat function with an AI server to resolve any questions or uncertainties.

[0928] Input: Unclear points regarding the cooking procedure.

[0929] Specific operation: The cook asks the AI ​​server, "At what point is it best to add this spice?" and receives an answer.

[0930] Output: Cooking instructions with clarifications.

[0931] Step 9: Cooking

[0932] The cook's device performs the cooking according to the recipe.

[0933] Input: Resolved cooking procedure.

[0934] Specific actions: The cook begins preparing the "lemon cheesecake" according to the instructions in the recipe.

[0935] Output: The finished dish.

[0936] Step 10: Report that cooking is complete.

[0937] The cook's device sends a notification to the server indicating that cooking is complete.

[0938] Input: The state of the finished dish.

[0939] Specific action: The cook clicks a button to notify the server that cooking is complete.

[0940] Output: The server received a cooking completion notification.

[0941] Step 11: Arrange delivery

[0942] The server receives the completion notification and instructs the food delivery company to arrange delivery.

[0943] Input: Cooking completion notification.

[0944] Specific operation: The server issues an instruction to the food delivery company: "Deliver the lemon cheesecake to client X."

[0945] Output: Instructions for the food delivery company to pick up the food.

[0946] Step 12: Food Delivery

[0947] A food delivery company delivers the food to the customer.

[0948] Input: Instructions for delivery arrangements.

[0949] Specific operation: A food delivery company picks up the food and delivers it to the specified address.

[0950] Output: The client receives the food.

[0951] Step 13: Enter the evaluation

[0952] The client's device receives the food, accesses the website's review form, and enters their review information.

[0953] Input: Product or service evaluation.

[0954] Specific action: The client enters "The food was delicious, but the delivery was late" into the review form and clicks the submit button.

[0955] Output: Evaluation data.

[0956] Step 14: Analysis of evaluation data

[0957] The emotion engine analyzes the emotions expressed by the client when they enter their evaluation and provides the results to the server.

[0958] Input: Evaluation data.

[0959] Specific operation: The emotion engine analyzes the emotions of "satisfied" and "dissatisfied" from the evaluation "It was delicious, but the delivery was late."

[0960] Output: Emotion analysis results.

[0961] Step 15: Reflecting the evaluation

[0962] The server incorporates evaluation data and sentiment analysis results into the chef's evaluation and stores them in the database.

[0963] Input: Evaluation data and sentiment analysis results.

[0964] Specific operation: The server saves the evaluation and sentiment analysis results and updates the chef's evaluation points. Simultaneously calculates and arranges the rewards.

[0965] Output: Updated evaluation points and reward information.

[0966] These processing steps enable the system to efficiently produce dishes that meet the client's requests and provide service that also takes the client's feelings into consideration.

[0967] (Application Example 2)

[0968] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0969] In modern food delivery services, providing customized meals tailored to the customer's requests and preferences is challenging. In particular, generating recipes that reflect the customer's emotions is difficult with conventional technology and has not contributed to increased customer satisfaction. Furthermore, insufficient communication between the cook and the AI ​​makes troubleshooting and quality improvement during the cooking process difficult. Additionally, there is a need for a compensation system that accurately reflects customer feedback.

[0970] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0971] In this invention, the server includes means for receiving requests from clients, means for performing emotion analysis, means for generating new recipes based on a taste database, means for sending the generated recipes to a chef who recreates them, means for supporting communication between the chef and artificial intelligence, means for delivering the recreated dishes to clients, means for receiving evaluations from clients and reflecting the emotion analysis results in the chef's evaluation, means for the chef to communicate with the artificial intelligence using a chat function, and means for paying rewards based on the chef's evaluation. This makes it possible to provide customized dishes based on the client's emotions, improve quality through smooth communication between the chef and artificial intelligence, and realize the construction of a reward system that accurately reflects evaluations.

[0972] "Request reception" is a method of receiving and analyzing requests for dishes and flavor preferences from clients.

[0973] "Emotional analysis" is a method of determining a client's emotional state by analyzing their text and audio data.

[0974] A "taste database" is a database that stores information about ingredients and seasonings used in cooking.

[0975] "Recipe generation" is a method of creating new recipes by selecting appropriate ingredients and seasonings based on the client's requests and the results of emotional analysis.

[0976] A "cooking recreater" is someone who actually cooks a dish based on a generated recipe.

[0977] "Artificial intelligence" refers to an AI engine that supports recipe generation, emotion analysis, and communication with those who recreate the dishes.

[0978] "Delivery" refers to the method of delivering prepared and recreated meals to the customer's location.

[0979] "Receiving feedback" refers to the process of receiving feedback on the dishes from clients, analyzing that information, and incorporating it into the service.

[0980] The "chat function" is a means of text or voice communication that allows the cooking replicator to interact with artificial intelligence in real time.

[0981] "Reward payment" refers to a method of paying appropriate compensation based on the evaluation of the person who recreated the dish.

[0982] The system for implementing this invention uses multiple hardware and software components to receive requests from clients, perform emotional analysis, generate recipes based on a taste database, send them to a chef / recipe maker, support the cooking process, and deliver the recreated dishes.

[0983] System Configuration

[0984] 1. Server:

[0985] Request reception method: The system receives requests for dishes and taste preferences entered by the client and saves them as text data.

[0986] Sentiment analysis method: The received text data is analyzed to determine the client's emotions. Natural language processing tools such as TextBlob are used.

[0987] Recipe generation method: Based on the client's requests and emotion analysis results, appropriate ingredients and seasonings are selected from a taste database to generate a unique recipe. By using a generation AI model, flexible recipe suggestions are possible.

[0988] Evaluation reception method: Receive the client's evaluation and the resulting sentiment analysis, and store it in a database.

[0989] 2. The cooking reenactment operator's device:

[0990] Recipe reception method: The generated recipe is notified to the device and displayed.

[0991] AI chat function: You can chat with artificial intelligence in real time to resolve any questions that arise during cooking.

[0992] Cooking completion notification method: Notify the server when cooking is complete.

[0993] 3. Delivery System:

[0994] Delivery arrangement method: After receiving notification that cooking is complete, instruct the food delivery company to arrange delivery.

[0995] Operation details

[0996] The server receives requests from clients using the aforementioned request receiving mechanism and analyzes the client's emotional state using the emotion analysis mechanism. For example, when it receives a request such as "I want to eat something delicious but not spicy," it analyzes the request and determines it to be "positive."

[0997] Next, the recipe generation system generates an appropriate recipe based on the client's requests and the results of the sentiment analysis. For example, the generation AI model might suggest a recipe for a "delicious dish with mild spiciness." This recipe is then sent to the cook's device and displayed.

[0998] The cooking expert checks the recipe and begins cooking. If any questions arise along the way, they communicate with the artificial intelligence in real time using the terminal's chat function.

[0999] Once cooking is complete, the cook sends a completion notification to the server. The server receives this notification and arranges for the food to be delivered to the food delivery company via the delivery system.

[1000] Finally, after the client receives the dish, they access a rating form and submit their evaluation of the dish. This evaluation is also analyzed for sentiment and reflected in the evaluation of the cook who recreated the dish, and payment is made as needed.

[1001] Example of a prompt

[1002] Client's request: "I want to eat something delicious that isn't spicy."

[1003] Emotion analysis result: Positive

[1004] ---

[1005] Please generate: Create a recipe for a delicious dish with mild spiciness.

[1006] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1007] Step 1:

[1008] The server receives the client's request.

[1009] Input: Text data containing the client's cooking preferences and taste requests.

[1010] Processing: Receive data entered from a web form and save it as text data.

[1011] Output: Saved request data.

[1012] Step 2:

[1013] The server performs sentiment analysis.

[1014] Input: Saved request data.

[1015] Processing: Analyze the sentiment of text data using natural language processing tools such as TextBlob. Determine whether the sentiment is positive or negative.

[1016] Output: Sentiment analysis results (e.g., positive).

[1017] Step 3:

[1018] The server generates new recipes based on a taste database.

[1019] Input: Request data and sentiment analysis results.

[1020] Processing: Using a generative AI model, relevant ingredients and seasonings are searched from a taste database, and a recipe is generated based on the client's requests and the results of sentiment analysis.

[1021] Output: The generated recipe.

[1022] Step 4:

[1023] The server sends the generated recipe to the person who will recreate it.

[1024] Input: The generated recipe.

[1025] Processing: A notification is sent to the device of the person recreating the recipe, and the recipe details are displayed.

[1026] Output: The recipe displayed on the cooking reenactment device.

[1027] Step 5:

[1028] The cook's device receives a notification that the recipe has been received and begins cooking.

[1029] Input: The recipe displayed on the cooking reenactment device.

[1030] Process: Review the recipe and begin cooking. If any questions arise along the way, use the device's chat function to communicate with the artificial intelligence.

[1031] Output: A finished dish.

[1032] Step 6:

[1033] The cooking reenactment operator's terminal notifies the server when cooking is complete.

[1034] Input: A finished dish.

[1035] Processing: Notify the server that cooking is complete.

[1036] Output: Cooking completion notification sent to the server.

[1037] Step 7:

[1038] The server arranges for the food to be delivered through a delivery service.

[1039] Input: Cooking completion notification.

[1040] Processing: Provide food delivery service providers with information regarding food pickup and delivery address, and arrange delivery.

[1041] Output: Notification that shipping arrangements have been completed.

[1042] Step 8:

[1043] The user receives the food and accesses the rating form.

[1044] Input: The food received.

[1045] Process: Access the rating form on the website and enter your rating for the dish.

[1046] Output: Input evaluation data.

[1047] Step 9:

[1048] The server stores evaluation data and sentiment analysis results, and uses them to evaluate the cooking recreater.

[1049] Input: The entered evaluation data.

[1050] Processing: Receive evaluation data and perform sentiment analysis again using TextBlob or similar methods. Save the results to a database and reflect them in the evaluation of the cooking recreater. Also, calculate and process payment as needed.

[1051] Output: Updated cooking replicator evaluation and reward data.

[1052] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1053] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1054] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[1055] [Third Embodiment]

[1056] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1057] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1058] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1059] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1060] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1061] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1062] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1063] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1064] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1065] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1066] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1067] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1068] This invention relates to a system that generates a unique recipe based on the client's requests, which is then reproduced by a chef and delivered to the client. This system is implemented as follows.

[1069] Request acceptance

[1070] server

[1071] The server receives requests from clients. Clients enter their cooking preferences and taste requests into a form on the website and click the submit button, sending the request to the server. The server analyzes the received request and forwards it to the recipe generation subsystem.

[1072] Specific example

[1073] The client types and submits a request stating, "I want to eat an exotic dish that is very sour and not too spicy."

[1074] Recipe generation

[1075] AI Server

[1076] The server receives the client's request and retrieves information on relevant ingredients and seasonings from the taste database. Based on the data, it generates a recipe suitable for the request. The generated recipe is then sent to the cooking and reproduction subsystem.

[1077] Processing explanation in natural language

[1078] The AI ​​server consults a taste database and selects ingredients associated with "sourness" and "mild spiciness." Based on these selected ingredients, it then creates recipes for exotic dishes.

[1079] Recipe distribution and cooking

[1080] The terminal of the person recreating the cooking recipe.

[1081] The cook's device receives a recipe notification. They review the recipe, organize the necessary ingredients and cooking steps, resolve any uncertainties using the AI ​​server's chat function, and then begin cooking.

[1082] Processing explanation in natural language

[1083] The cooking model receives a recipe and prepares the dish following the displayed cooking steps. If any questions arise during cooking, they can ask them via chat with the AI ​​server and receive answers.

[1084] Arranging delivery

[1085] The terminal of the person recreating the cooking recipe.

[1086] Once cooking is complete, the person recreating the dish sends a cooking completion notification to the server.

[1087] server

[1088] The server receives a notification that cooking is complete and instructs the food delivery company to arrange delivery. The delivery company picks up the food and delivers it to the customer.

[1089] Processing explanation in natural language

[1090] The customer provides the food delivery service with their information and the food, requesting prompt delivery. The delivery service picks up the food and delivers it to the customer's address.

[1091] Receiving and rating the food

[1092] User's terminal

[1093] The customer receives the food and accesses a review form on the website. They then enter and submit a review regarding the quality of the food and the speed of delivery.

[1094] server

[1095] The server receives the evaluations and saves them to the database. Furthermore, the evaluations are reflected in the evaluation points of the cooking recreaters, and the rankings are updated.

[1096] Processing explanation in natural language

[1097] The evaluation results are recorded in a database and used to assess the performance of the recipe recreaters. The recipe recreater rankings are also updated, and outstanding recreaters receive additional rewards.

[1098] Through these processes, the present invention provides a system that generates, quickly reproduces, and delivers unique recipes based on the client's requests.

[1099] The following describes the processing flow.

[1100] Step 1: Accepting the request

[1101] server

[1102] The system recognizes that a user has entered a specific cooking request into a request form on the website and clicked the submit button. The server receives this data and analyzes the request. The analysis results are then transferred to the recipe generation subsystem.

[1103] Step 2: Analyze requirements and generate recipes

[1104] AI Server

[1105] The server analyzes the client's request and consults a taste database. It selects ingredients and seasonings that match the taste characteristics based on the request and generates an original recipe based on them. The generated recipe is then sent to the cooking reproduction subsystem.

[1106] Step 3: Receive and confirm the recipe

[1107] The terminal of the person recreating the cooking recipe.

[1108] The person recreating the recipe receives a notification on their device and confirms that a new recipe has arrived. They view the recipe details and check the required ingredients and cooking instructions.

[1109] Step 4: Communication with AI

[1110] The terminal of the person recreating the cooking recipe.

[1111] The person recreating the recipe asks the AI ​​server any questions or uncertainties. They receive immediate answers from the server using the chat function. This exchange ensures that the information necessary for recipe recreation is accurately conveyed.

[1112] Step 5: Cooking

[1113] The terminal of the person recreating the cooking recipe.

[1114] The cooking replicator prepares the dish according to the recipe. They proceed step by step, checking each step along the way, and communicate with the AI ​​server again if any problems arise.

[1115] Step 6: Notification that cooking is complete

[1116] The terminal of the person recreating the cooking recipe.

[1117] Once cooking is complete, the person reproducing the cooking process notifies the server of the completion. They then transmit the cooking completion status using a communication method.

[1118] Step 7: Arrange delivery

[1119] server

[1120] The server receives a cooking completion notification and instructs the food delivery company to arrange delivery. It also provides the delivery company with information on where to pick up and deliver the food.

[1121] Step 8: Food Delivery

[1122] Delivery company

[1123] A delivery company picks up the food and delivers it quickly to the customer. When the customer receives the food, a delivery completion notification is sent to the server.

[1124] Step 9: Receive and rate your food

[1125] User's terminal

[1126] The customer receives the food and accesses a review form on the website. They then enter and submit a review about the taste, appearance, delivery time, etc.

[1127] Step 10: Reflecting the evaluation

[1128] server

[1129] The server receives the evaluation data and stores it in the database. The evaluation results are reflected in the evaluation of the cooking recreaters, and the recreaters' rankings are updated. In addition, the payment of rewards is processed based on the evaluations.

[1130] These specific processing steps enable the system to efficiently and quickly provide original dishes based on the client's requests.

[1131] (Example 1)

[1132] Next, we will describe Example 1. 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."

[1133] The current recipe generation and food delivery system has several problems, including accurately reflecting the client's requests in generating recipes, facilitating smooth communication with the cooks, and managing delivery arrangements and evaluations. Specifically, these include malfunctions in the function for properly analyzing client requests, a lack of means to resolve questions about the generated recipes, and inefficiencies in delivery arrangements. There are also problems with properly reflecting client evaluation data in the performance evaluations and compensation of the cooks.

[1134] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1135] In this invention, the server includes means for receiving requests from clients, means for generating new recipes based on a taste database, means for transmitting the generated recipes to a cooking recreater, means for supporting communication between the cooking recreater and artificial intelligence, means for delivering the recreated dishes to the clients, means for receiving evaluations from clients and reflecting them in the cooking recreater's evaluation, means for arranging delivery with a delivery company, means for inputting questions to help the cooking recreater resolve any doubts based on the generated recipes and obtaining answers, means for analyzing the client's requests and extracting information on seasonings and ingredients, means for saving the client's evaluations in a database and updating the cooking recreater's ranking, and means for providing additional rewards to the cooking recreater based on the client's evaluation. This enables the generation of recipes that accurately reflect the client's requests, smooth communication with cooking recreaters, efficient delivery arrangements, and appropriate reflection of evaluations from clients.

[1136] A "client" is an individual or group that submits a request for a dish to the system.

[1137] A "taste database" is a database that stores and manages information about the taste of various ingredients and seasonings.

[1138] "Recipe generation" is the process of selecting appropriate ingredients and seasonings based on the client's requests and constructing a unique cooking procedure.

[1139] A "cooking recreater" is an individual or group whose role is to actually cook a dish based on a generated recipe.

[1140] "Artificial intelligence" is a technology that performs natural language processing and data analysis within a system to support communication between clients and those who recreate the dishes.

[1141] "Supporting communication" refers to a function that allows cooking enthusiasts to resolve any uncertainties they may have regarding cooking through artificial intelligence.

[1142] "Delivery" refers to the process of delivering the dishes prepared by the chef to the client.

[1143] "Reviews" refer to the process by which clients provide feedback on the quality of the food and the speed of delivery.

[1144] A "delivery service provider" is an individual or company that provides a service to deliver the recreated dishes to the customer.

[1145] "Enter a question and get an answer" refers to the process where a cooking simulator asks artificial intelligence questions that arise during cooking and receives the answers.

[1146] "Extracting information on seasonings and ingredients" is the process of analyzing the client's requests and obtaining data on the most suitable seasonings and ingredients based on those requests.

[1147] A "database" is a system that efficiently stores and manages various types of data, and allows that data to be retrieved as needed.

[1148] "Ranking" is a system that assigns rankings based on the performance evaluation of those who recreate the dishes.

[1149] "Additional rewards" refer to preliminary gratuities or bonuses paid to recipe recreaters who receive outstanding ratings.

[1150] This invention is a system that generates a unique recipe based on the client's request, a chef prepares the dish based on that recipe, and delivers it to the client. This system is implemented through the following main means.

[1151] Request acceptance

[1152] server

[1153] The server provides a means for receiving requests from clients. When a client enters their culinary preferences and taste requests into a form on the website and clicks the submit button, the request is sent to the server. For example, a client might enter and submit, "I want an exotic dish that is very sour and not too spicy." The server analyzes the received request and forwards it to the recipe generation subsystem.

[1154] Recipe generation

[1155] AI Server

[1156] The server receives the client's request and retrieves information on relevant ingredients and seasonings from the taste database. Specifically, the AI ​​server refers to the taste database and selects ingredients associated with "sourness" and "mild spiciness." Then, it creates a recipe for an exotic dish based on the selected ingredients. The generated recipe is sent to the cooking reproduction subsystem. For example, it might select sour ingredients such as "lemon" and "coriander" to construct a recipe for a mildly spicy exotic dish.

[1157] Example of a prompt:

[1158] "Please generate recipes for exotic dishes that are strongly sour and mildly spicy."

[1159] Recipe distribution and cooking

[1160] The terminal of the person recreating the cooking recipe.

[1161] The cooking model's device receives a recipe notification from the AI ​​server. The device displays the recipe details and prepares the necessary ingredients for cooking. The cooking model begins cooking according to the displayed recipe. If any questions arise during cooking, they can use the chat function on the device to ask questions to the AI ​​server. For example, if they are making beef stroganoff and want more detailed instructions about the cooking time, they can ask via chat.

[1162] Example of a prompt:

[1163] "How long do you need to cook beef stroganoff?"

[1164] Arranging delivery

[1165] The terminal of the person recreating the cooking recipe.

[1166] Once cooking is complete, the person recreating the cooking process sends a completion notification to the server. For example, they might click the "Cooking Complete" button on their device to notify the server of the completion status.

[1167] server

[1168] The server receives a cooking completion notification and instructs the food delivery company to arrange delivery. The delivery company picks up the food and delivers it to the customer. For example, the server calls the delivery company's (e.g., Uber Eats) API to arrange food delivery.

[1169] Example of a prompt:

[1170] "Please arrange for beef stroganoff to be delivered to the address XX."

[1171] Receiving and rating the food

[1172] User's terminal

[1173] The customer receives the food and accesses a review form on the website. They enter and submit a review regarding the quality of the food and the speed of delivery. For example, the customer might enter and submit a review stating, "The food was delicious, I would like to use this service again."

[1174] server

[1175] The server receives the evaluations and saves them to the database. Furthermore, it reflects the evaluations in the cooking recreater's evaluation points and updates the rankings. For example, the server analyzes the evaluation data and updates the cooking recreater's evaluation points. It records it in the database as "4.5 points on a 5-point scale."

[1176] In this way, this system utilizes various databases and artificial intelligence to efficiently carry out a series of processes, from generating recipes based on the client's requests to cooking, delivery, and evaluation.

[1177] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1178] Step 1: Accepting requests

[1179] The server provides a form on the website to receive requests from clients. By entering their desired dishes and taste preferences into the form and clicking the submit button, the request is sent to the server. The input data includes specific dish characteristics and desired tastes. The server analyzes the received request, breaks down the client's request into specific keywords, and transfers this as analysis data to the recipe generation subsystem.

[1180] Input: Request from the client (e.g., "An exotic dish with a strong sour taste and mild spiciness")

[1181] Output: Decomposed keywords (e.g., "sourness", "mild spiciness", "exotic")

[1182] Specific operation: The client enters their request into an input form, and the server receives it and breaks it down into keywords.

[1183] Step 2: Recipe Generation

[1184] The server retrieves information on relevant ingredients and seasonings from a taste database based on the client's request. Based on the retrieved data, the AI ​​server generates a recipe suitable for the client. Specifically, the AI ​​model matches the decomposed keywords with data from the taste database to select appropriate ingredients and seasonings. Based on these, it constructs specific cooking steps and completes the recipe.

[1185] Input: Keywords (e.g., "sourness", "mild spiciness", "exotic"), data from a taste database.

[1186] Output: Generated recipe (e.g., "Exotic Chicken Dish with Lemon")

[1187] Specific operation: The AI ​​server accesses the database, and the AI ​​model generates a cooking recipe.

[1188] Step 3: Recipe notification

[1189] The cooking model's device receives a recipe notification from the AI ​​server. The recipe details are displayed on the device, and the model performs the necessary preparations for cooking. The recipe includes a specific list of ingredients and cooking instructions.

[1190] Input: Generated recipe

[1191] Output: Displayed recipe information (list of ingredients and cooking instructions)

[1192] Specific operation: The cooking recreater's device receives and displays the recipe from the AI ​​server.

[1193] Step 4: Cooking

[1194] The person recreating the dish begins cooking according to the displayed recipe. If any questions arise during cooking, they can use the chat function with the AI ​​server via their device to ask questions. The AI ​​server provides answers and resolves the questions.

[1195] Input: Recipe information, questions from the person who recreated the dish.

[1196] Output: Finished dish, response from AI server

[1197] Specific actions: The person recreating the recipe will measure the ingredients and cook according to the recipe. If any questions arise during the process, they will use the chat function.

[1198] Step 5: Notification that cooking is complete

[1199] Once cooking is complete, the person reproducing the cooking sends a completion notification to the server. The server receives the notification and prepares to proceed to the next step.

[1200] Input: Cooking completion notification

[1201] Output: Completion notification to the server

[1202] Specific action: Click the "Cooking Complete" button on the terminal and send a completion notification to the server.

[1203] Step 6: Arrange delivery

[1204] The server receives a notification that cooking is complete and instructs the food delivery company to arrange delivery. The delivery company picks up the food and delivers it to the customer.

[1205] Input: Cooking completion notification, delivery company information

[1206] Output: Execution of delivery arrangements, instructions to the delivery company.

[1207] Specific operation: The server calls the delivery company's API to arrange for food delivery.

[1208] Step 7: Receive and rate your food

[1209] The customer receives the food and accesses a review form on the website. They enter and submit a review regarding the quality of the food and the speed of delivery.

[1210] Input: Client's evaluation

[1211] Output: Evaluation data to the server

[1212] Specific operation: The client enters feedback into the evaluation form and sends it to the server.

[1213] Step 8: Saving and reflecting the evaluation

[1214] The server receives the evaluations and stores them in the database. Furthermore, the evaluations are reflected in the cooking recreater's evaluation points, updating the rankings. Cooking recreaters who receive excellent evaluations are given additional rewards.

[1215] Input: Evaluation data

[1216] Output: Updated evaluation points and rankings, and reflection of additional rewards.

[1217] Specific operation: The server analyzes the evaluation data, saves it to the database, and updates the evaluation points and rankings of the cooking recreaters.

[1218] (Application Example 1)

[1219] Next, we will explain Application Example 1. In the following explanation, 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."

[1220] In modern society, it is difficult to easily obtain special dishes tailored to individual tastes and preferences. Furthermore, there is a lack of systems that guarantee that online orders will meet expectations in terms of taste and quality. In addition, the food preparation process and delivery arrangements are time-consuming, creating a need for efficient systems that provide customer satisfaction.

[1221] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1222] In this invention, the server includes means for receiving requests from clients, means for generating new recipes based on a taste database, means for transmitting the generated recipes to a chef who recreates them, means for supporting communication between the chef and the AI, means for delivering the recreated dishes to the clients, means for receiving evaluations from clients and reflecting them in the chef's evaluation, means for receiving requests via a smartphone application, means for generating recipes using an AI server, means for arranging delivery in cooperation with a delivery platform, and means for transmitting evaluation results from the client's terminal to the server and saving them in a database. This enables the efficient generation of special dishes tailored to the individual requests of clients, and allows for the provision of high-quality dishes by chefs and rapid delivery.

[1223] A "client" is an individual or group that makes a special request for a particular dish to the system.

[1224] A "request reception method" is an interface that provides the functionality to collect requests for dishes and taste preferences from clients and send them to the server.

[1225] A "taste database" is a database that stores information on ingredients and seasonings used in cooking, and allows users to refer to the taste characteristics of each.

[1226] A "recipe generation method" is a system that automatically generates unique recipes by selecting appropriate ingredients and seasonings from a taste database based on the client's requests.

[1227] A "cooking recreater" is a person or robot that actually cooks a dish based on a generated recipe.

[1228] A "recipe transmission means" is a communication means for notifying the person who will be cooking and reproducing the generated recipe.

[1229] The "communication support system between cooking replicators and AI" is a mechanism that provides a chat function to allow cooking replicators to resolve any questions they may have by interacting with AI.

[1230] "Delivery methods" refer to food delivery services and systems that quickly deliver recreated dishes to the customer.

[1231] The "evaluation receiving method" is an interface that collects evaluations from clients regarding the quality of the food and the speed of delivery, and sends that data to the server.

[1232] A "smartphone application" is software on a mobile device that allows clients to input their requests and manage their orders.

[1233] An "AI server" is a server equipped with artificial intelligence that analyzes the client's requests and generates recipes by referring to a taste database.

[1234] A "delivery platform" is an online platform that instructs food delivery companies to arrange deliveries and delivers food to customers.

[1235] A "rating and storage method" is a system that stores the client's evaluation results in a database and reflects them in the performance evaluation of the cooking and recipe reproduction team.

[1236] This invention relates to a system that generates a unique recipe according to the client's request, and then a chef prepares the dish based on that recipe and delivers it to the client.

[1237] This system includes the following steps:

[1238] Request acceptance

[1239] server:

[1240] The customer enters their culinary preferences and taste requests via a smartphone application. For example, they might enter a request such as, "I'd like an exotic dish that's quite sour and not too spicy," into the form and click the submit button. This request is sent to the server and stored in the database along with the customer's information.

[1241] Recipe generation

[1242] AI Server:

[1243] Upon receiving a request from a client, the server consults a taste database to obtain information on ingredients and seasonings that match the client's preferences. Based on this data, the AI ​​server generates a recipe that suits the request. For example, it might select ingredients related to "sourness" or "mild spiciness" to create a recipe for an exotic dish.

[1244] Recipe distribution and cooking

[1245] The device of the person recreating the recipe:

[1246] The generated recipe is sent to the cook's device. The cook reviews the recipe on their device and organizes the necessary ingredients and cooking steps. Furthermore, if the cook has any questions during the cooking process, they can use the chat function with the server to ask questions and receive answers from the AI ​​server.

[1247] Arranging delivery

[1248] server:

[1249] Once cooking is complete, the cook sends a completion notification to the server. The server receives the completion notification and, in conjunction with the food delivery platform, issues instructions for delivery. The food delivery company picks up the food and delivers it to the customer.

[1250] Receiving and rating the food

[1251] Client's device:

[1252] After receiving their meal, the customer accesses a review form via a smartphone application. They enter and submit their evaluation regarding the quality of the food and the speed of delivery. The server receives the evaluation and stores it in a database. Furthermore, this evaluation is reflected in the evaluation points of the cook / recipe recreater, and the ranking is updated.

[1253] Examples of specific cases and prompt statements

[1254] For example, if the client requests "spicy but not too hot Indian food," the following prompt will be sent to the AI ​​server:

[1255] text

[1256] User Request:

[1257] Desired Cuisine: Indian

[1258] Taste preferences: Spicy but mild heat level

[1259] AI Task:

[1260] Generate a recipe using the given preferences, including a list of ingredients and step-by-step instructions.

[1261] The hardware and software used include Amazon Web Services (AWS) EC2, S3, RDS, Google Cloud AI Platform, React Native, Node.js (Express framework), PostgreSQL, and the Uber Eats API. By combining these, it becomes possible to efficiently generate special dishes tailored to the individual requests of customers, enabling high-quality food delivery and rapid delivery.

[1262] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1263] Step 1:

[1264] Request acceptance

[1265] Users enter their food preferences and taste requests via a smartphone application. Specifically, a user might enter "I want to eat an exotic dish that is very sour and not too spicy" into a form within the app and click the submit button. The entered data is sent to the server as the user's request. The server receives the request data and stores it in a database along with the requester's information.

[1266] Input: Food request (specific tastes and preferences)

[1267] Output: Saved client request data

[1268] Step 2:

[1269] Recipe generation

[1270] The server receives the client's request data and sends it to the AI ​​server. The AI ​​server consults a taste database to obtain information on relevant ingredients and seasonings. Based on this data, the AI ​​server generates specific prompt statements and creates recipes for exotic dishes based on the relevant ingredients. For example, based on "User Request: Desired Cuisine: Indian, Taste preferences: Spicy but mild heat level," it selects appropriate ingredients and seasonings and creates a recipe.

[1271] Input: Client's request data

[1272] Output: Generated recipe

[1273] Step 3:

[1274] Recipe distribution

[1275] The server receives the generated recipe and sends it to the cook's terminal. The cook reviews the recipe on their terminal and organizes the necessary ingredients and cooking steps. The server sends a notification to the cook's terminal at the same time as sending the recipe.

[1276] Input: Generated recipe

[1277] Output: Recipe notification sent to the cook / recipe recreater

[1278] Step 4:

[1279] Cooking progress

[1280] The cooking model proceeds with cooking according to the recipe sent to their device. If any questions arise during cooking, the model uses the device's chat function to ask questions to the AI ​​server. The AI ​​server receives the questions and provides appropriate answers.

[1281] Input: Recipe, questions from the cook / recipe recreater

[1282] Output: Finished dish, AI server's answers to any questions.

[1283] Step 5:

[1284] Arranging delivery

[1285] The terminal sends a notification to the server indicating that cooking is complete. The server receives this notification and, in cooperation with the food delivery platform, issues instructions for delivery. The food delivery company, having received the delivery instructions, picks up the food and delivers it to the customer.

[1286] Input: Notification of cooking completion

[1287] Output: Delivery arrangement instructions to the food delivery platform.

[1288] Step 6:

[1289] Receiving and rating the food

[1290] After receiving their meal, the client accesses a review form via a smartphone application. The client enters and submits their evaluation regarding the quality of the food and the speed of delivery. The server receives the evaluation and stores it in a database. This evaluation is reflected in the evaluation points of the cook who recreated the meal, and the ranking is updated.

[1291] Input: Client's evaluation

[1292] Output: Evaluation data stored in the database, updated ranking of cooking replicators.

[1293] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1294] This invention relates to a system that generates a unique recipe based on the client's requests, which is then reproduced by a chef and delivered to the client. This system is characterized by its integration of an emotion engine to recognize the client's emotions and to perform the recipe generation and evaluation process more precisely based on those emotions.

[1295] Request acceptance

[1296] server

[1297] The server receives requests from clients. Clients enter their preferences for specific dishes or tastes into a form on the website and click the submit button to send their requests. The server receives this data and analyzes the request.

[1298] Emotional Engine

[1299] The emotion engine analyzes the client's emotions when they input their request. The analysis results are obtained through text and voice analysis and provided to the recipe generation subsystem as information that includes the client's intent and emotional elements.

[1300] Recipe generation

[1301] AI Server

[1302] The server receives the client's request and the analysis results from the emotion engine, and retrieves information on relevant ingredients and seasonings from the taste database. Based on the data, it generates a recipe suitable for the request. The generated recipe is sent to the cooking reproduction subsystem.

[1303] Processing explanation in natural language

[1304] The AI ​​server selects ingredients related to "sourness" and "mild spiciness" from a taste database, and then creates recipes for exotic dishes by making adjustments according to the client's preferences.

[1305] Recipe distribution and cooking

[1306] The terminal of the person recreating the cooking recipe.

[1307] The person recreating the recipe receives a notification on their device and confirms that a new recipe has arrived. They view the recipe details and check the ingredients and cooking steps. They use the chat function with the AI ​​server to resolve any questions and then begin cooking.

[1308] Processing explanation in natural language

[1309] The cooking assistant receives a recipe and follows the displayed cooking instructions to prepare the dish. If any problems arise along the way, they can ask questions via chat with the AI ​​server and receive answers to continue cooking.

[1310] Arranging delivery

[1311] The terminal of the person recreating the cooking recipe.

[1312] Once cooking is complete, the person reproducing the cooking sends a notification to the server indicating that cooking is finished. The status of cooking completion is sent to the server using a communication method.

[1313] server

[1314] The server receives a cooking completion notification and instructs the food delivery company to arrange delivery. It also provides the delivery company with information on where to pick up and deliver the food.

[1315] Processing explanation in natural language

[1316] The customer provides the food delivery service with their information and the food, requesting prompt delivery. The delivery service picks up the food and delivers it to the customer's address.

[1317] Receiving and rating the food

[1318] User's terminal

[1319] The customer receives the food and accesses a review form on the website. They enter and submit a review regarding the quality of the food, delivery time, etc. An emotion engine analyzes the customer's emotions during the review process and incorporates that data into the evaluation process.

[1320] server

[1321] The server receives the evaluations and stores them in the database. The results analyzed by the emotion engine are also stored and reflected in the evaluation of the cooking recreater. Based on the evaluation results, the cooking recreater's performance is assessed and the ranking is updated. In addition, the payment of rewards is also processed based on the evaluation.

[1322] Processing explanation in natural language

[1323] Evaluation data and sentiment analysis results are recorded in a database and reflected in the evaluation points of the cooking recreaters. The recreater rankings are updated, and outstanding recreaters receive additional rewards.

[1324] This configuration allows the system to not only efficiently and quickly provide unique dishes based on the client's requests, but also to deliver service that takes the client's emotions into consideration.

[1325] The following describes the processing flow.

[1326] Step 1: Accepting the request

[1327] server

[1328] The system recognizes that a user has entered specific food requests into a request form on the website and clicked the submit button. The server receives this data and analyzes the request. The data is then sent to the emotion engine through text and voice analysis.

[1329] Emotional Engine

[1330] The emotion engine analyzes the emotions expressed by the client when they input their request. The analysis results are encoded based on the client's text expression, voice tone, and contextual analysis. The analysis results are then provided to the recipe generation subsystem.

[1331] Step 2: Analyze requirements and generate recipes

[1332] AI Server

[1333] The server receives the client's request and the analysis results from the emotion engine. It retrieves information on relevant ingredients and seasonings from the taste database and generates a recipe suitable for the client's emotional state. The generated recipe is further adjusted to reflect the analysis results from the emotion engine.

[1334] Step 3: Receive and confirm the recipe

[1335] The terminal of the person recreating the cooking recipe.

[1336] The person recreating the recipe receives a notification on their device and confirms that a new recipe has arrived. They view the recipe details and check the ingredients and cooking instructions. They use the chat function with the AI ​​server to resolve any questions.

[1337] Step 4: Communication with AI

[1338] The terminal of the person recreating the cooking recipe.

[1339] The cooking recreater asks the AI ​​server any questions or uncertainties. The AI ​​server provides immediate answers. The cooking recreater uses the chat function to confirm the appropriate cooking procedure as they proceed with the work.

[1340] Step 5: Cooking

[1341] The terminal of the person recreating the cooking recipe.

[1342] The cooking assistant prepares the dish according to the recipe. They proceed while checking each step of the cooking process, and if any problems arise along the way, they communicate with the AI ​​server again via chat. Once cooking is complete, they send a completion notification from their device.

[1343] Step 6: Notification that cooking is complete

[1344] The terminal of the person recreating the cooking recipe.

[1345] Once cooking is complete, the person recreating the dish reports the completion to the server. The report may include photos of the dish and comments.

[1346] Step 7: Arrange delivery

[1347] server

[1348] The server receives a notification that cooking is complete and instructs the food delivery company to arrange delivery. Delivery arrangements include the status of the food, delivery address information, and delivery time.

[1349] Step 8: Food Delivery

[1350] Delivery company

[1351] A delivery company picks up the food and delivers it quickly to the customer. Once the customer receives the food, a delivery completion notification is sent to the server.

[1352] Step 9: Receive and rate your food

[1353] User's terminal

[1354] The customer receives the food and accesses the review form on the website. They enter detailed feedback on the quality of the food, delivery time, etc., and also allow the emotion engine to analyze their feelings. They then submit the review.

[1355] Step 10: Reflecting the evaluation

[1356] server

[1357] The server receives the evaluation and stores it in the database along with the analysis results from the emotion engine. The evaluation points of the cooking recreater are then reflected, including the emotion analysis results. The ranking of the recreaters is updated based on the evaluation results and analysis data, and payment procedures for rewards are carried out as needed.

[1358] These processing steps enable the efficient and rapid delivery of original dishes based on the client's requests and feelings, while also providing a high level of service that takes the client's emotions into consideration.

[1359] (Example 2)

[1360] Next, we will describe Example 2. 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."

[1361] Traditionally, generating recipes based on client requests and then recreating those recipes has struggled to take the client's emotions into account. As a result, it was often impossible to provide dishes that matched the client's desired taste and emotions, leading to decreased satisfaction. Furthermore, if communication between the cooking recreater and the artificial intelligence was not smooth, it could potentially affect the quality of the cooking.

[1362] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1363] In this invention, the server includes means for receiving requests from clients, means for analyzing the requests and emotions of the clients, means for generating new recipes based on a taste database, means for transmitting the generated recipes to a chef who will recreate them, means for supporting communication between the chef and artificial intelligence, means for delivering the recreated dishes to the clients, and means for receiving feedback from clients and reflecting it in the chef's evaluation. This makes it possible to generate recipes that take the client's emotions into consideration and to achieve smooth communication between the chef and artificial intelligence. As a result, client satisfaction can be improved and high-quality dishes can be provided.

[1364] A "client" is an individual or group that uses the system to request a specific dish and asks for its preparation and delivery.

[1365] "Requests" refer to the types of dishes and taste preferences that the client desires, and this information is entered into the system by the client.

[1366] A "server" is a computer that receives requests from clients, analyzes them, exchanges data with other subsystems, and manages the entire system.

[1367] An "emotion engine" is a technology that analyzes the client's emotions from input text or audio and provides the analysis results to other parts of the system.

[1368] A "taste database" is a database that stores information about various ingredients and seasonings, and is a collection of data used when generating recipes.

[1369] A "recipe generation method" is a system that, based on the client's requests and the results of emotion analysis, selects appropriate ingredients and seasonings from a taste database and generates a unique recipe.

[1370] A "cook" is the person who receives a generated recipe and actually prepares the dish based on it.

[1371] "Artificial intelligence" is a computing system that can perform specific tasks automatically, and has functions such as suggesting recipes and answering questions during the cooking process.

[1372] "Delivery method" refers to the function or service used to deliver food prepared by a cook to the customer.

[1373] "Rating" refers to the act of a customer expressing their satisfaction level and opinions regarding the food they received and its delivery, and this information is sent to the system as feedback.

[1374] "Chef evaluation" refers to an evaluation that quantifies or ranks the chef's performance based on evaluation data from clients and sentiment analysis results.

[1375] Modes for carrying out the invention

[1376] This invention is a system that generates a unique recipe based on the client's requests, has a chef recreate it, and delivers it to the client. A key feature of this system is that it incorporates an emotion engine to recognize the client's emotions and uses that to refine the recipe generation and evaluation process.

[1377] Request acceptance

[1378] server

[1379] The server receives requests from clients. Clients enter their preferences for specific dishes or tastes into a form on the website and click the submit button to send their requests. The server receives this data and analyzes the request.

[1380] For example, if a client enters their request for a "sweet and sour dessert" and clicks the submit button, the server receives and analyzes that data.

[1381] Emotional Engine

[1382] The emotion engine analyzes the client's emotions when they input their request. The analysis results are obtained through text and voice analysis and provided to the recipe generation subsystem as information that includes the client's intent and emotional elements.

[1383] For example, if a client enters "I'm tired from work today, so I want a dish that will lift my spirits," the emotion engine will identify the emotions "fatigue" and "wanting to lift my spirits" from that sentence and provide that information as analysis results to the recipe generation subsystem.

[1384] Recipe generation

[1385] AI Server

[1386] The server receives the client's request and the analysis results from the emotion engine, and retrieves information on relevant ingredients and seasonings from the taste database. Based on this, it generates a recipe suitable for the request. The generated recipe is then sent to the cook's terminal.

[1387] As a concrete example, the server selects ingredients such as "lemon" and "honey" from a taste database for a client who prefers "sourness" and "sweetness," and then creates an exotic dish recipe based on these ingredients. For example, the prompt might read, "Generate a recipe for a client who wants something sour with a little sweetness."

[1388] Recipe distribution and cooking

[1389] Cook's terminal

[1390] The cook receives a notification on their device and confirms that a new recipe has arrived. They view the recipe details and check the ingredients and cooking instructions. If necessary, they use the chat function with the AI ​​server to resolve any questions and then begin cooking.

[1391] For example, a cook receives a notification for a new recipe and checks it on their device. They carefully examine the ingredients and steps, and then send questions to the AI ​​server via chat, such as, "When is the best time to add this spice?"

[1392] Arranging delivery

[1393] Cook's terminal

[1394] Once cooking is complete, the cook sends a notification to the server indicating completion. The status of cooking completion is sent to the server using a communication method.

[1395] For example, when a cook sends a notification to the server that the cooking is complete, the server automatically instructs the food delivery company to pick up the food and provide the delivery address information (the client's address).

[1396] server

[1397] The server receives a notification that cooking is complete and instructs the food delivery company to arrange delivery. The server provides the delivery company with information on where to pick up the food and the delivery address.

[1398] Receiving and rating the food

[1399] User's terminal

[1400] The customer receives the food and enters their review on a rating form on the website. The review includes the quality of the food and delivery time, and an emotion engine analyzes the emotions felt during the review process.

[1401] For example, if a client enters "The food was delicious, but the delivery was slow" into the review form, the emotion engine analyzes both "satisfied" and "dissatisfied" emotions from this review and incorporates that information into the review data.

[1402] server

[1403] The server receives the evaluations and stores them in the database. The evaluations and sentiment analysis results are reflected in the chef's performance evaluation and are also used for updating rankings and reward procedures.

[1404] For example, the server updates the chef's evaluation points based on the client's evaluation data and the results of their sentiment analysis. If a chef receives many high ratings, they may receive additional compensation.

[1405] Through these processes, the system can efficiently generate dishes that meet the client's requests and provide service that also takes the client's feelings into consideration.

[1406] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1407] Step 1: Receiving the client's request

[1408] The server receives requests from clients through an input form on the website. The entered request (e.g., "sweet and sour dessert") is sent to the server.

[1409] Input: The client's requests regarding specific dishes and taste preferences, entered on the website.

[1410] Specific action: The requester enters their desired "sweet and sour dessert" and clicks the submit button.

[1411] Output: Client's requested data.

[1412] Step 2: Analysis of the requirements

[1413] The server analyzes the request data it receives and understands its content. The analysis results are classified into categories and tastes related to the cuisine.

[1414] Input: Client's request data.

[1415] Specific operation: The server analyzes the request data "sweet and sour dessert" and recognizes the taste "sweet and sour" and the category "dessert".

[1416] Output: Request analysis results (Example: Taste = "Sweet and sour", Category = "Dessert").

[1417] Step 3: Emotional Analysis

[1418] The server passes the request data to the emotion engine, which then analyzes the client's emotions.

[1419] Input: Request data.

[1420] Specific operation: The server passes the text "I'm tired from work today, so I want some food to lift my spirits" to the emotion engine, which identifies the emotions "fatigue" and "want to lift my spirits."

[1421] Output: Emotion analysis results (e.g., emotion = "fatigue", intention = "want to cheer up").

[1422] Step 4: Obtain relevant data

[1423] Based on the client's requests and the results of the emotional analysis, the server retrieves information on relevant ingredients and seasonings from the taste database.

[1424] Input: Request analysis results and emotion analysis results.

[1425] Specific operation: The server searches the taste database for ingredients and seasonings related to "sweet and sour" and "dessert" (e.g., "lemon," "honey").

[1426] Output: Related data (e.g., Ingredient = "Lemon", Seasoning = "Honey").

[1427] Step 5: Recipe Generation

[1428] The server uses relevant data to input prompt messages into the AI ​​model, which then generates a recipe that meets the requirements.

[1429] Input: Related data.

[1430] Specific operation: The server inputs a prompt message to the AI ​​model saying, "Please generate a recipe for a customer who wants something sour with a little sweetness," and the AI ​​generates the recipe.

[1431] Output: Generated recipe (e.g., "Lemon Cheesecake").

[1432] Step 6: Submit the recipe

[1433] The server sends the generated recipe to the cook's terminal.

[1434] Input: The generated recipe.

[1435] Specific operation: The server sends the generated "Lemon Cheesecake" recipe to the cook's terminal.

[1436] Output: The cook's terminal receives the recipe.

[1437] Step 7: Check the recipe

[1438] The cook's device receives a notification and confirms that a new recipe has arrived. They view the recipe details and check the ingredients and cooking instructions.

[1439] Input: The generated recipe.

[1440] Specific action: The cook receives a notification on their device saying "A new recipe has arrived," and then checks the recipe details.

[1441] Output: Recipe details displayed on the cook's terminal.

[1442] Step 8: Communication with the AI ​​Server

[1443] The cook's device uses a chat function with an AI server to resolve any questions or uncertainties.

[1444] Input: Unclear points regarding the cooking procedure.

[1445] Specific operation: The cook asks the AI ​​server, "At what point is it best to add this spice?" and receives an answer.

[1446] Output: Cooking instructions with clarifications.

[1447] Step 9: Cooking

[1448] The cook's device performs the cooking according to the recipe.

[1449] Input: Resolved cooking procedure.

[1450] Specific actions: The cook begins preparing the "lemon cheesecake" according to the instructions in the recipe.

[1451] Output: The finished dish.

[1452] Step 10: Report that cooking is complete.

[1453] The cook's device sends a notification to the server indicating that cooking is complete.

[1454] Input: The state of the finished dish.

[1455] Specific action: The cook clicks a button to notify the server that cooking is complete.

[1456] Output: The server received a cooking completion notification.

[1457] Step 11: Arrange delivery

[1458] The server receives the completion notification and instructs the food delivery company to arrange delivery.

[1459] Input: Cooking completion notification.

[1460] Specific operation: The server issues an instruction to the food delivery company: "Deliver the lemon cheesecake to client X."

[1461] Output: Instructions for the food delivery company to pick up the food.

[1462] Step 12: Food Delivery

[1463] A food delivery company delivers the food to the customer.

[1464] Input: Instructions for delivery arrangements.

[1465] Specific operation: A food delivery company picks up the food and delivers it to the specified address.

[1466] Output: The client receives the food.

[1467] Step 13: Enter the evaluation

[1468] The client's device receives the food, accesses the website's review form, and enters their review information.

[1469] Input: Product or service evaluation.

[1470] Specific action: The client enters "The food was delicious, but the delivery was late" into the review form and clicks the submit button.

[1471] Output: Evaluation data.

[1472] Step 14: Analysis of evaluation data

[1473] The emotion engine analyzes the emotions expressed by the client when they enter their evaluation and provides the results to the server.

[1474] Input: Evaluation data.

[1475] Specific operation: The emotion engine analyzes the emotions of "satisfied" and "dissatisfied" from the evaluation "It was delicious, but the delivery was late."

[1476] Output: Emotion analysis results.

[1477] Step 15: Reflecting the evaluation

[1478] The server incorporates evaluation data and sentiment analysis results into the chef's evaluation and stores them in the database.

[1479] Input: Evaluation data and sentiment analysis results.

[1480] Specific operation: The server saves the evaluation and sentiment analysis results and updates the chef's evaluation points. Simultaneously calculates and arranges the rewards.

[1481] Output: Updated evaluation points and reward information.

[1482] These processing steps enable the system to efficiently produce dishes that meet the client's requests and provide service that also takes the client's feelings into consideration.

[1483] (Application Example 2)

[1484] Next, we will explain application example 2. In the following explanation, 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."

[1485] In modern food delivery services, providing customized meals tailored to the customer's requests and preferences is challenging. In particular, generating recipes that reflect the customer's emotions is difficult with conventional technology and has not contributed to increased customer satisfaction. Furthermore, insufficient communication between the cook and the AI ​​makes troubleshooting and quality improvement during the cooking process difficult. Additionally, there is a need for a compensation system that accurately reflects customer feedback.

[1486] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1487] In this invention, the server includes means for receiving requests from clients, means for performing emotion analysis, means for generating new recipes based on a taste database, means for sending the generated recipes to a chef who recreates them, means for supporting communication between the chef and artificial intelligence, means for delivering the recreated dishes to clients, means for receiving evaluations from clients and reflecting the emotion analysis results in the chef's evaluation, means for the chef to communicate with the artificial intelligence using a chat function, and means for paying rewards based on the chef's evaluation. This makes it possible to provide customized dishes based on the client's emotions, improve quality through smooth communication between the chef and artificial intelligence, and realize the construction of a reward system that accurately reflects evaluations.

[1488] "Request reception" is a method of receiving and analyzing requests for dishes and flavor preferences from clients.

[1489] "Emotional analysis" is a method of determining a client's emotional state by analyzing their text and audio data.

[1490] A "taste database" is a database that stores information about ingredients and seasonings used in cooking.

[1491] "Recipe generation" is a method of creating new recipes by selecting appropriate ingredients and seasonings based on the client's requests and the results of emotional analysis.

[1492] A "cooking recreater" is someone who actually cooks a dish based on a generated recipe.

[1493] "Artificial intelligence" refers to an AI engine that supports recipe generation, emotion analysis, and communication with those who recreate the dishes.

[1494] "Delivery" refers to the method of delivering prepared and recreated meals to the customer's location.

[1495] "Receiving feedback" refers to the process of receiving feedback on the dishes from clients, analyzing that information, and incorporating it into the service.

[1496] The "chat function" is a means of text or voice communication that allows the cooking replicator to interact with artificial intelligence in real time.

[1497] "Reward payment" refers to a method of paying appropriate compensation based on the evaluation of the person who recreated the dish.

[1498] The system for implementing this invention uses multiple hardware and software components to receive requests from clients, perform emotional analysis, generate recipes based on a taste database, send them to a chef / recipe maker, support the cooking process, and deliver the recreated dishes.

[1499] System Configuration

[1500] 1. Server:

[1501] Request reception method: The system receives requests for dishes and taste preferences entered by the client and saves them as text data.

[1502] Sentiment analysis method: The received text data is analyzed to determine the client's emotions. Natural language processing tools such as TextBlob are used.

[1503] Recipe generation method: Based on the client's requests and emotion analysis results, appropriate ingredients and seasonings are selected from a taste database to generate a unique recipe. By using a generation AI model, flexible recipe suggestions are possible.

[1504] Evaluation reception method: Receive the client's evaluation and the resulting sentiment analysis, and store it in a database.

[1505] 2. The cooking reenactment operator's device:

[1506] Recipe reception method: The generated recipe is notified to the device and displayed.

[1507] AI chat function: You can chat with artificial intelligence in real time to resolve any questions that arise during cooking.

[1508] Cooking completion notification method: Notify the server when cooking is complete.

[1509] 3. Delivery System:

[1510] Delivery arrangement method: After receiving notification that cooking is complete, instruct the food delivery company to arrange delivery.

[1511] Operation details

[1512] The server receives requests from clients using the aforementioned request receiving mechanism and analyzes the client's emotional state using the emotion analysis mechanism. For example, when it receives a request such as "I want to eat something delicious but not spicy," it analyzes the request and determines it to be "positive."

[1513] Next, the recipe generation system generates an appropriate recipe based on the client's requests and the results of the sentiment analysis. For example, the generation AI model might suggest a recipe for a "delicious dish with mild spiciness." This recipe is then sent to the cook's device and displayed.

[1514] The cooking expert checks the recipe and begins cooking. If any questions arise along the way, they communicate with the artificial intelligence in real time using the terminal's chat function.

[1515] Once cooking is complete, the cook sends a completion notification to the server. The server receives this notification and arranges for the food to be delivered to the food delivery company via the delivery system.

[1516] Finally, after the client receives the dish, they access a rating form and submit their evaluation of the dish. This evaluation is also analyzed for sentiment and reflected in the evaluation of the cook who recreated the dish, and payment is made as needed.

[1517] Example of a prompt

[1518] Client's request: "I want to eat something delicious that isn't spicy."

[1519] Emotion analysis result: Positive

[1520] ---

[1521] Please generate: Create a recipe for a delicious dish with mild spiciness.

[1522] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1523] Step 1:

[1524] The server receives the client's request.

[1525] Input: Text data containing the client's cooking preferences and taste requests.

[1526] Processing: Receive data entered from a web form and save it as text data.

[1527] Output: Saved request data.

[1528] Step 2:

[1529] The server performs sentiment analysis.

[1530] Input: Saved request data.

[1531] Processing: Analyze the sentiment of text data using natural language processing tools such as TextBlob. Determine whether the sentiment is positive or negative.

[1532] Output: Sentiment analysis results (e.g., positive).

[1533] Step 3:

[1534] The server generates new recipes based on a taste database.

[1535] Input: Request data and sentiment analysis results.

[1536] Processing: Using a generative AI model, relevant ingredients and seasonings are searched from a taste database, and a recipe is generated based on the client's requests and the results of sentiment analysis.

[1537] Output: The generated recipe.

[1538] Step 4:

[1539] The server sends the generated recipe to the person who will recreate it.

[1540] Input: The generated recipe.

[1541] Processing: A notification is sent to the device of the person recreating the recipe, and the recipe details are displayed.

[1542] Output: The recipe displayed on the cooking reenactment device.

[1543] Step 5:

[1544] The cook's device receives a notification that the recipe has been received and begins cooking.

[1545] Input: The recipe displayed on the cooking reenactment device.

[1546] Process: Review the recipe and begin cooking. If any questions arise along the way, use the device's chat function to communicate with the artificial intelligence.

[1547] Output: A finished dish.

[1548] Step 6:

[1549] The cooking reenactment operator's terminal notifies the server when cooking is complete.

[1550] Input: A finished dish.

[1551] Processing: Notify the server that cooking is complete.

[1552] Output: Cooking completion notification sent to the server.

[1553] Step 7:

[1554] The server arranges for the food to be delivered through a delivery service.

[1555] Input: Cooking completion notification.

[1556] Processing: Provide food delivery service providers with information regarding food pickup and delivery address, and arrange delivery.

[1557] Output: Notification that shipping arrangements have been completed.

[1558] Step 8:

[1559] The user receives the food and accesses the rating form.

[1560] Input: The food received.

[1561] Process: Access the rating form on the website and enter your rating for the dish.

[1562] Output: Input evaluation data.

[1563] Step 9:

[1564] The server stores evaluation data and sentiment analysis results, and uses them to evaluate the cooking recreater.

[1565] Input: The entered evaluation data.

[1566] Processing: Receive evaluation data and perform sentiment analysis again using TextBlob or similar methods. Save the results to a database and reflect them in the evaluation of the cooking recreater. Also, calculate and process payment as needed.

[1567] Output: Updated cooking replicator evaluation and reward data.

[1568] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1569] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1570] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1571] [Fourth Embodiment]

[1572] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1573] As shown in Figure 7, the 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.

[1574] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1575] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1576] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1577] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1578] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1579] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1580] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1581] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1582] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1583] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1584] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1585] This invention relates to a system that generates a unique recipe based on the client's requests, which is then reproduced by a chef and delivered to the client. This system is implemented as follows.

[1586] Request acceptance

[1587] server

[1588] The server receives requests from clients. Clients enter their cooking preferences and taste requests into a form on the website and click the submit button, sending the request to the server. The server analyzes the received request and forwards it to the recipe generation subsystem.

[1589] Specific example

[1590] The client types and submits a request stating, "I want to eat an exotic dish that is very sour and not too spicy."

[1591] Recipe generation

[1592] AI Server

[1593] The server receives the client's request and retrieves information on relevant ingredients and seasonings from the taste database. Based on the data, it generates a recipe suitable for the request. The generated recipe is then sent to the cooking and reproduction subsystem.

[1594] Processing explanation in natural language

[1595] The AI ​​server consults a taste database and selects ingredients associated with "sourness" and "mild spiciness." Based on these selected ingredients, it then creates recipes for exotic dishes.

[1596] Recipe distribution and cooking

[1597] The terminal of the person recreating the cooking recipe.

[1598] The cook's device receives a recipe notification. They review the recipe, organize the necessary ingredients and cooking steps, resolve any uncertainties using the AI ​​server's chat function, and then begin cooking.

[1599] Processing explanation in natural language

[1600] The cooking model receives a recipe and prepares the dish following the displayed cooking steps. If any questions arise during cooking, they can ask them via chat with the AI ​​server and receive answers.

[1601] Arranging delivery

[1602] The terminal of the person recreating the cooking recipe.

[1603] Once cooking is complete, the person recreating the dish sends a cooking completion notification to the server.

[1604] server

[1605] The server receives a notification that cooking is complete and instructs the food delivery company to arrange delivery. The delivery company picks up the food and delivers it to the customer.

[1606] Processing explanation in natural language

[1607] The customer provides the food delivery service with their information and the food, requesting prompt delivery. The delivery service picks up the food and delivers it to the customer's address.

[1608] Receiving and rating the food

[1609] User's terminal

[1610] The customer receives the food and accesses a review form on the website. They then enter and submit a review regarding the quality of the food and the speed of delivery.

[1611] server

[1612] The server receives the evaluations and saves them to the database. Furthermore, the evaluations are reflected in the evaluation points of the cooking recreaters, and the rankings are updated.

[1613] Processing explanation in natural language

[1614] The evaluation results are recorded in a database and used to assess the performance of the recipe recreaters. The recipe recreater rankings are also updated, and outstanding recreaters receive additional rewards.

[1615] Through these processes, the present invention provides a system that generates, quickly reproduces, and delivers unique recipes based on the client's requests.

[1616] The following describes the processing flow.

[1617] Step 1: Accepting the request

[1618] server

[1619] The system recognizes that a user has entered a specific cooking request into a request form on the website and clicked the submit button. The server receives this data and analyzes the request. The analysis results are then transferred to the recipe generation subsystem.

[1620] Step 2: Analyze requirements and generate recipes

[1621] AI Server

[1622] The server analyzes the client's request and consults a taste database. It selects ingredients and seasonings that match the taste characteristics based on the request and generates an original recipe based on them. The generated recipe is then sent to the cooking reproduction subsystem.

[1623] Step 3: Receive and confirm the recipe

[1624] The terminal of the person recreating the cooking recipe.

[1625] The person recreating the recipe receives a notification on their device and confirms that a new recipe has arrived. They view the recipe details and check the required ingredients and cooking instructions.

[1626] Step 4: Communication with AI

[1627] The terminal of the person recreating the cooking recipe.

[1628] The person recreating the recipe asks the AI ​​server any questions or uncertainties. They receive immediate answers from the server using the chat function. This exchange ensures that the information necessary for recipe recreation is accurately conveyed.

[1629] Step 5: Cooking

[1630] The terminal of the person recreating the cooking recipe.

[1631] The cooking replicator prepares the dish according to the recipe. They proceed step by step, checking each step along the way, and communicate with the AI ​​server again if any problems arise.

[1632] Step 6: Notification that cooking is complete

[1633] The terminal of the person recreating the cooking recipe.

[1634] Once cooking is complete, the person reproducing the cooking process notifies the server of the completion. They then transmit the cooking completion status using a communication method.

[1635] Step 7: Arrange delivery

[1636] server

[1637] The server receives a cooking completion notification and instructs the food delivery company to arrange delivery. It also provides the delivery company with information on where to pick up and deliver the food.

[1638] Step 8: Food Delivery

[1639] Delivery company

[1640] A delivery company picks up the food and delivers it quickly to the customer. When the customer receives the food, a delivery completion notification is sent to the server.

[1641] Step 9: Receive and rate your food

[1642] User's terminal

[1643] The customer receives the food and accesses a review form on the website. They then enter and submit a review about the taste, appearance, delivery time, etc.

[1644] Step 10: Reflecting the evaluation

[1645] server

[1646] The server receives the evaluation data and stores it in the database. The evaluation results are reflected in the evaluation of the cooking recreaters, and the recreaters' rankings are updated. In addition, the payment of rewards is processed based on the evaluations.

[1647] These specific processing steps enable the system to efficiently and quickly provide original dishes based on the client's requests.

[1648] (Example 1)

[1649] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1650] The current recipe generation and food delivery system has several problems, including accurately reflecting the client's requests in generating recipes, facilitating smooth communication with the cooks, and managing delivery arrangements and evaluations. Specifically, these include malfunctions in the function for properly analyzing client requests, a lack of means to resolve questions about the generated recipes, and inefficiencies in delivery arrangements. There are also problems with properly reflecting client evaluation data in the performance evaluations and compensation of the cooks.

[1651] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1652] In this invention, the server includes means for receiving requests from clients, means for generating new recipes based on a taste database, means for transmitting the generated recipes to a cooking recreater, means for supporting communication between the cooking recreater and artificial intelligence, means for delivering the recreated dishes to the clients, means for receiving evaluations from clients and reflecting them in the cooking recreater's evaluation, means for arranging delivery with a delivery company, means for inputting questions to help the cooking recreater resolve any doubts based on the generated recipes and obtaining answers, means for analyzing the client's requests and extracting information on seasonings and ingredients, means for saving the client's evaluations in a database and updating the cooking recreater's ranking, and means for providing additional rewards to the cooking recreater based on the client's evaluation. This enables the generation of recipes that accurately reflect the client's requests, smooth communication with cooking recreaters, efficient delivery arrangements, and appropriate reflection of evaluations from clients.

[1653] A "client" is an individual or group that submits a request for a dish to the system.

[1654] A "taste database" is a database that stores and manages information about the taste of various ingredients and seasonings.

[1655] "Recipe generation" is the process of selecting appropriate ingredients and seasonings based on the client's requests and constructing a unique cooking procedure.

[1656] A "cooking recreater" is an individual or group whose role is to actually cook a dish based on a generated recipe.

[1657] "Artificial intelligence" is a technology that performs natural language processing and data analysis within a system to support communication between clients and those who recreate the dishes.

[1658] "Supporting communication" refers to a function that allows cooking enthusiasts to resolve any uncertainties they may have regarding cooking through artificial intelligence.

[1659] "Delivery" refers to the process of delivering the dishes prepared by the chef to the client.

[1660] "Reviews" refer to the process by which clients provide feedback on the quality of the food and the speed of delivery.

[1661] A "delivery service provider" is an individual or company that provides a service to deliver the recreated dishes to the customer.

[1662] "Enter a question and get an answer" refers to the process where a cooking simulator asks artificial intelligence questions that arise during cooking and receives the answers.

[1663] "Extracting information on seasonings and ingredients" is the process of analyzing the client's requests and obtaining data on the most suitable seasonings and ingredients based on those requests.

[1664] A "database" is a system that efficiently stores and manages various types of data, and allows that data to be retrieved as needed.

[1665] "Ranking" is a system that assigns rankings based on the performance evaluation of those who recreate the dishes.

[1666] "Additional rewards" refer to preliminary gratuities or bonuses paid to recipe recreaters who receive outstanding ratings.

[1667] This invention is a system that generates a unique recipe based on the client's request, a chef prepares the dish based on that recipe, and delivers it to the client. This system is implemented through the following main means.

[1668] Request acceptance

[1669] server

[1670] The server provides a means for receiving requests from clients. When a client enters their culinary preferences and taste requests into a form on the website and clicks the submit button, the request is sent to the server. For example, a client might enter and submit, "I want an exotic dish that is very sour and not too spicy." The server analyzes the received request and forwards it to the recipe generation subsystem.

[1671] Recipe generation

[1672] AI Server

[1673] The server receives the client's request and retrieves information on relevant ingredients and seasonings from the taste database. Specifically, the AI ​​server refers to the taste database and selects ingredients associated with "sourness" and "mild spiciness." Then, it creates a recipe for an exotic dish based on the selected ingredients. The generated recipe is sent to the cooking reproduction subsystem. For example, it might select sour ingredients such as "lemon" and "coriander" to construct a recipe for a mildly spicy exotic dish.

[1674] Example of a prompt:

[1675] "Please generate recipes for exotic dishes that are strongly sour and mildly spicy."

[1676] Recipe distribution and cooking

[1677] The terminal of the person recreating the cooking recipe.

[1678] The cooking model's device receives a recipe notification from the AI ​​server. The device displays the recipe details and prepares the necessary ingredients for cooking. The cooking model begins cooking according to the displayed recipe. If any questions arise during cooking, they can use the chat function on the device to ask questions to the AI ​​server. For example, if they are making beef stroganoff and want more detailed instructions about the cooking time, they can ask via chat.

[1679] Example of a prompt:

[1680] "How long do you need to cook beef stroganoff?"

[1681] Arranging delivery

[1682] The terminal of the person recreating the cooking recipe.

[1683] Once cooking is complete, the person recreating the cooking process sends a completion notification to the server. For example, they might click the "Cooking Complete" button on their device to notify the server of the completion status.

[1684] server

[1685] The server receives a cooking completion notification and instructs the food delivery company to arrange delivery. The delivery company picks up the food and delivers it to the customer. For example, the server calls the delivery company's (e.g., Uber Eats) API to arrange food delivery.

[1686] Example of a prompt:

[1687] "Please arrange for beef stroganoff to be delivered to the address XX."

[1688] Receiving and rating the food

[1689] User's terminal

[1690] The customer receives the food and accesses a review form on the website. They enter and submit a review regarding the quality of the food and the speed of delivery. For example, the customer might enter and submit a review stating, "The food was delicious, I would like to use this service again."

[1691] server

[1692] The server receives the evaluations and saves them to the database. Furthermore, it reflects the evaluations in the cooking recreater's evaluation points and updates the rankings. For example, the server analyzes the evaluation data and updates the cooking recreater's evaluation points. It records it in the database as "4.5 points on a 5-point scale."

[1693] In this way, this system utilizes various databases and artificial intelligence to efficiently carry out a series of processes, from generating recipes based on the client's requests to cooking, delivery, and evaluation.

[1694] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1695] Step 1: Accepting requests

[1696] The server provides a form on the website to receive requests from clients. By entering their desired dishes and taste preferences into the form and clicking the submit button, the request is sent to the server. The input data includes specific dish characteristics and desired tastes. The server analyzes the received request, breaks down the client's request into specific keywords, and transfers this as analysis data to the recipe generation subsystem.

[1697] Input: Request from the client (e.g., "An exotic dish with a strong sour taste and mild spiciness")

[1698] Output: Decomposed keywords (e.g., "sourness", "mild spiciness", "exotic")

[1699] Specific operation: The client enters their request into an input form, and the server receives it and breaks it down into keywords.

[1700] Step 2: Recipe Generation

[1701] The server retrieves information on relevant ingredients and seasonings from a taste database based on the client's request. Based on the retrieved data, the AI ​​server generates a recipe suitable for the client. Specifically, the AI ​​model matches the decomposed keywords with data from the taste database to select appropriate ingredients and seasonings. Based on these, it constructs specific cooking steps and completes the recipe.

[1702] Input: Keywords (e.g., "sourness", "mild spiciness", "exotic"), data from a taste database.

[1703] Output: Generated recipe (e.g., "Exotic Chicken Dish with Lemon")

[1704] Specific operation: The AI ​​server accesses the database, and the AI ​​model generates a cooking recipe.

[1705] Step 3: Recipe notification

[1706] The cooking model's device receives a recipe notification from the AI ​​server. The recipe details are displayed on the device, and the model performs the necessary preparations for cooking. The recipe includes a specific list of ingredients and cooking instructions.

[1707] Input: Generated recipe

[1708] Output: Displayed recipe information (list of ingredients and cooking instructions)

[1709] Specific operation: The cooking recreater's device receives and displays the recipe from the AI ​​server.

[1710] Step 4: Cooking

[1711] The person recreating the dish begins cooking according to the displayed recipe. If any questions arise during cooking, they can use the chat function with the AI ​​server via their device to ask questions. The AI ​​server provides answers and resolves the questions.

[1712] Input: Recipe information, questions from the person who recreated the dish.

[1713] Output: Finished dish, response from AI server

[1714] Specific actions: The person recreating the recipe will measure the ingredients and cook according to the recipe. If any questions arise during the process, they will use the chat function.

[1715] Step 5: Notification that cooking is complete

[1716] Once cooking is complete, the person reproducing the cooking sends a completion notification to the server. The server receives the notification and prepares to proceed to the next step.

[1717] Input: Cooking completion notification

[1718] Output: Completion notification to the server

[1719] Specific action: Click the "Cooking Complete" button on the terminal and send a completion notification to the server.

[1720] Step 6: Arrange delivery

[1721] The server receives a notification that cooking is complete and instructs the food delivery company to arrange delivery. The delivery company picks up the food and delivers it to the customer.

[1722] Input: Cooking completion notification, delivery company information

[1723] Output: Execution of delivery arrangements, instructions to the delivery company.

[1724] Specific operation: The server calls the delivery company's API to arrange for food delivery.

[1725] Step 7: Receive and rate your food

[1726] The customer receives the food and accesses a review form on the website. They enter and submit a review regarding the quality of the food and the speed of delivery.

[1727] Input: Client's evaluation

[1728] Output: Evaluation data to the server

[1729] Specific operation: The client enters feedback into the evaluation form and sends it to the server.

[1730] Step 8: Saving and reflecting the evaluation

[1731] The server receives the evaluations and stores them in the database. Furthermore, the evaluations are reflected in the cooking recreater's evaluation points, updating the rankings. Cooking recreaters who receive excellent evaluations are given additional rewards.

[1732] Input: Evaluation data

[1733] Output: Updated evaluation points and rankings, and reflection of additional rewards.

[1734] Specific operation: The server analyzes the evaluation data, saves it to the database, and updates the evaluation points and rankings of the cooking recreaters.

[1735] (Application Example 1)

[1736] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1737] In modern society, it is difficult to easily obtain special dishes tailored to individual tastes and preferences. Furthermore, there is a lack of systems that guarantee that online orders will meet expectations in terms of taste and quality. In addition, the food preparation process and delivery arrangements are time-consuming, creating a need for efficient systems that provide customer satisfaction.

[1738] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1739] In this invention, the server includes means for receiving requests from clients, means for generating new recipes based on a taste database, means for transmitting the generated recipes to a chef who recreates them, means for supporting communication between the chef and the AI, means for delivering the recreated dishes to the clients, means for receiving evaluations from clients and reflecting them in the chef's evaluation, means for receiving requests via a smartphone application, means for generating recipes using an AI server, means for arranging delivery in cooperation with a delivery platform, and means for transmitting evaluation results from the client's terminal to the server and saving them in a database. This enables the efficient generation of special dishes tailored to the individual requests of clients, and allows for the provision of high-quality dishes by chefs and rapid delivery.

[1740] A "client" is an individual or group that makes a special request for a particular dish to the system.

[1741] A "request reception method" is an interface that provides the functionality to collect requests for dishes and taste preferences from clients and send them to the server.

[1742] A "taste database" is a database that stores information on ingredients and seasonings used in cooking, and allows users to refer to the taste characteristics of each.

[1743] A "recipe generation method" is a system that automatically generates unique recipes by selecting appropriate ingredients and seasonings from a taste database based on the client's requests.

[1744] A "cooking recreater" is a person or robot that actually cooks a dish based on a generated recipe.

[1745] A "recipe transmission means" is a communication means for notifying the person who will be cooking and reproducing the generated recipe.

[1746] The "communication support system between cooking replicators and AI" is a mechanism that provides a chat function to allow cooking replicators to resolve any questions they may have by interacting with AI.

[1747] "Delivery methods" refer to food delivery services and systems that quickly deliver recreated dishes to the customer.

[1748] The "evaluation receiving method" is an interface that collects evaluations from clients regarding the quality of the food and the speed of delivery, and sends that data to the server.

[1749] A "smartphone application" is software on a mobile device that allows clients to input their requests and manage their orders.

[1750] An "AI server" is a server equipped with artificial intelligence that analyzes the client's requests and generates recipes by referring to a taste database.

[1751] A "delivery platform" is an online platform that instructs food delivery companies to arrange deliveries and delivers food to customers.

[1752] A "rating and storage method" is a system that stores the client's evaluation results in a database and reflects them in the performance evaluation of the cooking and recipe reproduction team.

[1753] This invention relates to a system that generates a unique recipe according to the client's request, and then a chef prepares the dish based on that recipe and delivers it to the client.

[1754] This system includes the following steps:

[1755] Request acceptance

[1756] server:

[1757] The customer enters their culinary preferences and taste requests via a smartphone application. For example, they might enter a request such as, "I'd like an exotic dish that's quite sour and not too spicy," into the form and click the submit button. This request is sent to the server and stored in the database along with the customer's information.

[1758] Recipe generation

[1759] AI Server:

[1760] Upon receiving a request from a client, the server consults a taste database to obtain information on ingredients and seasonings that match the client's preferences. Based on this data, the AI ​​server generates a recipe that suits the request. For example, it might select ingredients related to "sourness" or "mild spiciness" to create a recipe for an exotic dish.

[1761] Recipe distribution and cooking

[1762] The device of the person recreating the recipe:

[1763] The generated recipe is sent to the cook's device. The cook reviews the recipe on their device and organizes the necessary ingredients and cooking steps. Furthermore, if the cook has any questions during the cooking process, they can use the chat function with the server to ask questions and receive answers from the AI ​​server.

[1764] Arranging delivery

[1765] server:

[1766] Once cooking is complete, the cook sends a completion notification to the server. The server receives the completion notification and, in conjunction with the food delivery platform, issues instructions for delivery. The food delivery company picks up the food and delivers it to the customer.

[1767] Receiving and rating the food

[1768] Client's device:

[1769] After receiving their meal, the customer accesses a review form via a smartphone application. They enter and submit their evaluation regarding the quality of the food and the speed of delivery. The server receives the evaluation and stores it in a database. Furthermore, this evaluation is reflected in the evaluation points of the cook / recipe recreater, and the ranking is updated.

[1770] Examples of specific cases and prompt statements

[1771] For example, if the client requests "spicy but not too hot Indian food," the following prompt will be sent to the AI ​​server:

[1772] text

[1773] User Request:

[1774] Desired Cuisine: Indian

[1775] Taste preferences: Spicy but mild heat level

[1776] AI Task:

[1777] Generate a recipe using the given preferences, including a list of ingredients and step-by-step instructions.

[1778] The hardware and software used include Amazon Web Services (AWS) EC2, S3, RDS, Google Cloud AI Platform, React Native, Node.js (Express framework), PostgreSQL, and the Uber Eats API. By combining these, it becomes possible to efficiently generate special dishes tailored to the individual requests of customers, enabling high-quality food delivery and rapid delivery.

[1779] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1780] Step 1:

[1781] Request acceptance

[1782] Users enter their food preferences and taste requests via a smartphone application. Specifically, a user might enter "I want to eat an exotic dish that is very sour and not too spicy" into a form within the app and click the submit button. The entered data is sent to the server as the user's request. The server receives the request data and stores it in a database along with the requester's information.

[1783] Input: Food request (specific tastes and preferences)

[1784] Output: Saved client request data

[1785] Step 2:

[1786] Recipe generation

[1787] The server receives the client's request data and sends it to the AI ​​server. The AI ​​server consults a taste database to obtain information on relevant ingredients and seasonings. Based on this data, the AI ​​server generates specific prompt statements and creates recipes for exotic dishes based on the relevant ingredients. For example, based on "User Request: Desired Cuisine: Indian, Taste preferences: Spicy but mild heat level," it selects appropriate ingredients and seasonings and creates a recipe.

[1788] Input: Client's request data

[1789] Output: Generated recipe

[1790] Step 3:

[1791] Recipe distribution

[1792] The server receives the generated recipe and sends it to the cook's terminal. The cook reviews the recipe on their terminal and organizes the necessary ingredients and cooking steps. The server sends a notification to the cook's terminal at the same time as sending the recipe.

[1793] Input: Generated recipe

[1794] Output: Recipe notification sent to the cook / recipe recreater

[1795] Step 4:

[1796] Cooking progress

[1797] The cooking model proceeds with cooking according to the recipe sent to their device. If any questions arise during cooking, the model uses the device's chat function to ask questions to the AI ​​server. The AI ​​server receives the questions and provides appropriate answers.

[1798] Input: Recipe, questions from the cook / recipe recreater

[1799] Output: Finished dish, AI server's answers to any questions.

[1800] Step 5:

[1801] Arranging delivery

[1802] The terminal sends a notification to the server indicating that cooking is complete. The server receives this notification and, in cooperation with the food delivery platform, issues instructions for delivery. The food delivery company, having received the delivery instructions, picks up the food and delivers it to the customer.

[1803] Input: Notification of cooking completion

[1804] Output: Delivery arrangement instructions to the food delivery platform.

[1805] Step 6:

[1806] Receiving and rating the food

[1807] After receiving their meal, the client accesses a review form via a smartphone application. The client enters and submits their evaluation regarding the quality of the food and the speed of delivery. The server receives the evaluation and stores it in a database. This evaluation is reflected in the evaluation points of the cook who recreated the meal, and the ranking is updated.

[1808] Input: Client's evaluation

[1809] Output: Evaluation data stored in the database, updated ranking of cooking replicators.

[1810] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1811] This invention relates to a system that generates a unique recipe based on the client's requests, which is then reproduced by a chef and delivered to the client. This system is characterized by its integration of an emotion engine to recognize the client's emotions and to perform the recipe generation and evaluation process more precisely based on those emotions.

[1812] Request acceptance

[1813] server

[1814] The server receives requests from clients. Clients enter their preferences for specific dishes or tastes into a form on the website and click the submit button to send their requests. The server receives this data and analyzes the request.

[1815] Emotional Engine

[1816] The emotion engine analyzes the client's emotions when they input their request. The analysis results are obtained through text and voice analysis and provided to the recipe generation subsystem as information that includes the client's intent and emotional elements.

[1817] Recipe generation

[1818] AI Server

[1819] The server receives the client's request and the analysis results from the emotion engine, and retrieves information on relevant ingredients and seasonings from the taste database. Based on the data, it generates a recipe suitable for the request. The generated recipe is sent to the cooking reproduction subsystem.

[1820] Processing explanation in natural language

[1821] The AI ​​server selects ingredients related to "sourness" and "mild spiciness" from a taste database, and then creates recipes for exotic dishes by making adjustments according to the client's preferences.

[1822] Recipe distribution and cooking

[1823] The terminal of the person recreating the cooking recipe.

[1824] The person recreating the recipe receives a notification on their device and confirms that a new recipe has arrived. They view the recipe details and check the ingredients and cooking steps. They use the chat function with the AI ​​server to resolve any questions and then begin cooking.

[1825] Processing explanation in natural language

[1826] The cooking assistant receives a recipe and follows the displayed cooking instructions to prepare the dish. If any problems arise along the way, they can ask questions via chat with the AI ​​server and receive answers to continue cooking.

[1827] Arranging delivery

[1828] The terminal of the person recreating the cooking recipe.

[1829] Once cooking is complete, the person reproducing the cooking sends a notification to the server indicating that cooking is finished. The status of cooking completion is sent to the server using a communication method.

[1830] server

[1831] The server receives a cooking completion notification and instructs the food delivery company to arrange delivery. It also provides the delivery company with information on where to pick up and deliver the food.

[1832] Processing explanation in natural language

[1833] The customer provides the food delivery service with their information and the food, requesting prompt delivery. The delivery service picks up the food and delivers it to the customer's address.

[1834] Receiving and rating the food

[1835] User's terminal

[1836] The customer receives the food and accesses a review form on the website. They enter and submit a review regarding the quality of the food, delivery time, etc. An emotion engine analyzes the customer's emotions during the review process and incorporates that data into the evaluation process.

[1837] server

[1838] The server receives the evaluations and stores them in the database. The results analyzed by the emotion engine are also stored and reflected in the evaluation of the cooking recreater. Based on the evaluation results, the cooking recreater's performance is assessed and the ranking is updated. In addition, the payment of rewards is also processed based on the evaluation.

[1839] Processing explanation in natural language

[1840] Evaluation data and sentiment analysis results are recorded in a database and reflected in the evaluation points of the cooking recreaters. The recreater rankings are updated, and outstanding recreaters receive additional rewards.

[1841] This configuration allows the system to not only efficiently and quickly provide unique dishes based on the client's requests, but also to deliver service that takes the client's emotions into consideration.

[1842] The following describes the processing flow.

[1843] Step 1: Accepting the request

[1844] server

[1845] The system recognizes that a user has entered specific food requests into a request form on the website and clicked the submit button. The server receives this data and analyzes the request. The data is then sent to the emotion engine through text and voice analysis.

[1846] Emotional Engine

[1847] The emotion engine analyzes the emotions expressed by the client when they input their request. The analysis results are encoded based on the client's text expression, voice tone, and contextual analysis. The analysis results are then provided to the recipe generation subsystem.

[1848] Step 2: Analyze requirements and generate recipes

[1849] AI Server

[1850] The server receives the client's request and the analysis results from the emotion engine. It retrieves information on relevant ingredients and seasonings from the taste database and generates a recipe suitable for the client's emotional state. The generated recipe is further adjusted to reflect the analysis results from the emotion engine.

[1851] Step 3: Receive and confirm the recipe

[1852] The terminal of the person recreating the cooking recipe.

[1853] The person recreating the recipe receives a notification on their device and confirms that a new recipe has arrived. They view the recipe details and check the ingredients and cooking instructions. They use the chat function with the AI ​​server to resolve any questions.

[1854] Step 4: Communication with AI

[1855] The terminal of the person recreating the cooking recipe.

[1856] The cooking recreater asks the AI ​​server any questions or uncertainties. The AI ​​server provides immediate answers. The cooking recreater uses the chat function to confirm the appropriate cooking procedure as they proceed with the work.

[1857] Step 5: Cooking

[1858] The terminal of the person recreating the cooking recipe.

[1859] The cooking assistant prepares the dish according to the recipe. They proceed while checking each step of the cooking process, and if any problems arise along the way, they communicate with the AI ​​server again via chat. Once cooking is complete, they send a completion notification from their device.

[1860] Step 6: Notification that cooking is complete

[1861] The terminal of the person recreating the cooking recipe.

[1862] Once cooking is complete, the person recreating the dish reports the completion to the server. The report may include photos of the dish and comments.

[1863] Step 7: Arrange delivery

[1864] server

[1865] The server receives a notification that cooking is complete and instructs the food delivery company to arrange delivery. Delivery arrangements include the status of the food, delivery address information, and delivery time.

[1866] Step 8: Food Delivery

[1867] Delivery company

[1868] A delivery company picks up the food and delivers it quickly to the customer. Once the customer receives the food, a delivery completion notification is sent to the server.

[1869] Step 9: Receive and rate your food

[1870] User's terminal

[1871] The customer receives the food and accesses the review form on the website. They enter detailed feedback on the quality of the food, delivery time, etc., and also allow the emotion engine to analyze their feelings. They then submit the review.

[1872] Step 10: Reflecting the evaluation

[1873] server

[1874] The server receives the evaluation and stores it in the database along with the analysis results from the emotion engine. The evaluation points of the cooking recreater are then reflected, including the emotion analysis results. The ranking of the recreaters is updated based on the evaluation results and analysis data, and payment procedures for rewards are carried out as needed.

[1875] These processing steps enable the efficient and rapid delivery of original dishes based on the client's requests and feelings, while also providing a high level of service that takes the client's emotions into consideration.

[1876] (Example 2)

[1877] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1878] Traditionally, generating recipes based on client requests and then recreating those recipes has struggled to take the client's emotions into account. As a result, it was often impossible to provide dishes that matched the client's desired taste and emotions, leading to decreased satisfaction. Furthermore, if communication between the cooking recreater and the artificial intelligence was not smooth, it could potentially affect the quality of the cooking.

[1879] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1880] In this invention, the server includes means for receiving requests from clients, means for analyzing the requests and emotions of the clients, means for generating new recipes based on a taste database, means for transmitting the generated recipes to a chef who will recreate them, means for supporting communication between the chef and artificial intelligence, means for delivering the recreated dishes to the clients, and means for receiving feedback from clients and reflecting it in the chef's evaluation. This makes it possible to generate recipes that take the client's emotions into consideration and to achieve smooth communication between the chef and artificial intelligence. As a result, client satisfaction can be improved and high-quality dishes can be provided.

[1881] A "client" is an individual or group that uses the system to request a specific dish and asks for its preparation and delivery.

[1882] "Requests" refer to the types of dishes and taste preferences that the client desires, and this information is entered into the system by the client.

[1883] A "server" is a computer that receives requests from clients, analyzes them, exchanges data with other subsystems, and manages the entire system.

[1884] An "emotion engine" is a technology that analyzes the client's emotions from input text or audio and provides the analysis results to other parts of the system.

[1885] A "taste database" is a database that stores information about various ingredients and seasonings, and is a collection of data used when generating recipes.

[1886] A "recipe generation method" is a system that, based on the client's requests and the results of emotion analysis, selects appropriate ingredients and seasonings from a taste database and generates a unique recipe.

[1887] A "cook" is the person who receives a generated recipe and actually prepares the dish based on it.

[1888] "Artificial intelligence" is a computing system that can perform specific tasks automatically, and has functions such as suggesting recipes and answering questions during the cooking process.

[1889] "Delivery method" refers to the function or service used to deliver food prepared by a cook to the customer.

[1890] "Rating" refers to the act of a customer expressing their satisfaction level and opinions regarding the food they received and its delivery, and this information is sent to the system as feedback.

[1891] "Chef evaluation" refers to an evaluation that quantifies or ranks the chef's performance based on evaluation data from clients and sentiment analysis results.

[1892] Modes for carrying out the invention

[1893] This invention is a system that generates a unique recipe based on the client's requests, has a chef recreate it, and delivers it to the client. A key feature of this system is that it incorporates an emotion engine to recognize the client's emotions and uses that to refine the recipe generation and evaluation process.

[1894] Request acceptance

[1895] server

[1896] The server receives requests from clients. Clients enter their preferences for specific dishes or tastes into a form on the website and click the submit button to send their requests. The server receives this data and analyzes the request.

[1897] For example, if a client enters their request for a "sweet and sour dessert" and clicks the submit button, the server receives and analyzes that data.

[1898] Emotional Engine

[1899] The emotion engine analyzes the client's emotions when they input their request. The analysis results are obtained through text and voice analysis and provided to the recipe generation subsystem as information that includes the client's intent and emotional elements.

[1900] For example, if a client enters "I'm tired from work today, so I want a dish that will lift my spirits," the emotion engine will identify the emotions "fatigue" and "wanting to lift my spirits" from that sentence and provide that information as analysis results to the recipe generation subsystem.

[1901] Recipe generation

[1902] AI Server

[1903] The server receives the client's request and the analysis results from the emotion engine, and retrieves information on relevant ingredients and seasonings from the taste database. Based on this, it generates a recipe suitable for the request. The generated recipe is then sent to the cook's terminal.

[1904] As a concrete example, the server selects ingredients such as "lemon" and "honey" from a taste database for a client who prefers "sourness" and "sweetness," and then creates an exotic dish recipe based on these ingredients. For example, the prompt might read, "Generate a recipe for a client who wants something sour with a little sweetness."

[1905] Recipe distribution and cooking

[1906] Cook's terminal

[1907] The cook receives a notification on their device and confirms that a new recipe has arrived. They view the recipe details and check the ingredients and cooking instructions. If necessary, they use the chat function with the AI ​​server to resolve any questions and then begin cooking.

[1908] For example, a cook receives a notification for a new recipe and checks it on their device. They carefully examine the ingredients and steps, and then send questions to the AI ​​server via chat, such as, "When is the best time to add this spice?"

[1909] Arranging delivery

[1910] Cook's terminal

[1911] Once cooking is complete, the cook sends a notification to the server indicating completion. The status of cooking completion is sent to the server using a communication method.

[1912] For example, when a cook sends a notification to the server that the cooking is complete, the server automatically instructs the food delivery company to pick up the food and provide the delivery address information (the client's address).

[1913] server

[1914] The server receives a notification that cooking is complete and instructs the food delivery company to arrange delivery. The server provides the delivery company with information on where to pick up the food and the delivery address.

[1915] Receiving and rating the food

[1916] User's terminal

[1917] The customer receives the food and enters their review on a rating form on the website. The review includes the quality of the food and delivery time, and an emotion engine analyzes the emotions felt during the review process.

[1918] For example, if a client enters "The food was delicious, but the delivery was slow" into the review form, the emotion engine analyzes both "satisfied" and "dissatisfied" emotions from this review and incorporates that information into the review data.

[1919] server

[1920] The server receives the evaluations and stores them in the database. The evaluations and sentiment analysis results are reflected in the chef's performance evaluation and are also used for updating rankings and reward procedures.

[1921] For example, the server updates the chef's evaluation points based on the client's evaluation data and the results of their sentiment analysis. If a chef receives many high ratings, they may receive additional compensation.

[1922] Through these processes, the system can efficiently generate dishes that meet the client's requests and provide service that also takes the client's feelings into consideration.

[1923] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1924] Step 1: Receiving the client's request

[1925] The server receives requests from clients through an input form on the website. The entered request (e.g., "sweet and sour dessert") is sent to the server.

[1926] Input: The client's requests regarding specific dishes and taste preferences, entered on the website.

[1927] Specific action: The requester enters their desired "sweet and sour dessert" and clicks the submit button.

[1928] Output: Client's requested data.

[1929] Step 2: Analysis of the requirements

[1930] The server analyzes the request data it receives and understands its content. The analysis results are classified into categories and tastes related to the cuisine.

[1931] Input: Client's request data.

[1932] Specific operation: The server analyzes the request data "sweet and sour dessert" and recognizes the taste "sweet and sour" and the category "dessert".

[1933] Output: Request analysis results (Example: Taste = "Sweet and sour", Category = "Dessert").

[1934] Step 3: Emotional Analysis

[1935] The server passes the request data to the emotion engine, which then analyzes the client's emotions.

[1936] Input: Request data.

[1937] Specific operation: The server passes the text "I'm tired from work today, so I want some food to lift my spirits" to the emotion engine, which identifies the emotions "fatigue" and "want to lift my spirits."

[1938] Output: Emotion analysis results (e.g., emotion = "fatigue", intention = "want to cheer up").

[1939] Step 4: Obtain relevant data

[1940] Based on the client's requests and the results of the emotional analysis, the server retrieves information on relevant ingredients and seasonings from the taste database.

[1941] Input: Request analysis results and emotion analysis results.

[1942] Specific operation: The server searches the taste database for ingredients and seasonings related to "sweet and sour" and "dessert" (e.g., "lemon," "honey").

[1943] Output: Related data (e.g., Ingredient = "Lemon", Seasoning = "Honey").

[1944] Step 5: Recipe Generation

[1945] The server uses relevant data to input prompt messages into the AI ​​model, which then generates a recipe that meets the requirements.

[1946] Input: Related data.

[1947] Specific operation: The server inputs a prompt message to the AI ​​model saying, "Please generate a recipe for a customer who wants something sour with a little sweetness," and the AI ​​generates the recipe.

[1948] Output: Generated recipe (e.g., "Lemon Cheesecake").

[1949] Step 6: Submit the recipe

[1950] The server sends the generated recipe to the cook's terminal.

[1951] Input: The generated recipe.

[1952] Specific operation: The server sends the generated "Lemon Cheesecake" recipe to the cook's terminal.

[1953] Output: The cook's terminal receives the recipe.

[1954] Step 7: Check the recipe

[1955] The cook's device receives a notification and confirms that a new recipe has arrived. They view the recipe details and check the ingredients and cooking instructions.

[1956] Input: The generated recipe.

[1957] Specific action: The cook receives a notification on their device saying "A new recipe has arrived," and then checks the recipe details.

[1958] Output: Recipe details displayed on the cook's terminal.

[1959] Step 8: Communication with the AI ​​Server

[1960] The cook's device uses a chat function with an AI server to resolve any questions or uncertainties.

[1961] Input: Unclear points regarding the cooking procedure.

[1962] Specific operation: The cook asks the AI ​​server, "At what point is it best to add this spice?" and receives an answer.

[1963] Output: Cooking instructions with clarifications.

[1964] Step 9: Cooking

[1965] The cook's device performs the cooking according to the recipe.

[1966] Input: Resolved cooking procedure.

[1967] Specific actions: The cook begins preparing the "lemon cheesecake" according to the instructions in the recipe.

[1968] Output: The finished dish.

[1969] Step 10: Report that cooking is complete.

[1970] The cook's device sends a notification to the server indicating that cooking is complete.

[1971] Input: The state of the finished dish.

[1972] Specific action: The cook clicks a button to notify the server that cooking is complete.

[1973] Output: The server received a cooking completion notification.

[1974] Step 11: Arrange delivery

[1975] The server receives the completion notification and instructs the food delivery company to arrange delivery.

[1976] Input: Cooking completion notification.

[1977] Specific operation: The server issues an instruction to the food delivery company: "Deliver the lemon cheesecake to client X."

[1978] Output: Instructions for the food delivery company to pick up the food.

[1979] Step 12: Food Delivery

[1980] A food delivery company delivers the food to the customer.

[1981] Input: Instructions for delivery arrangements.

[1982] Specific operation: A food delivery company picks up the food and delivers it to the specified address.

[1983] Output: The client receives the food.

[1984] Step 13: Enter the evaluation

[1985] The client's device receives the food, accesses the website's review form, and enters their review information.

[1986] Input: Product or service evaluation.

[1987] Specific action: The client enters "The food was delicious, but the delivery was late" into the review form and clicks the submit button.

[1988] Output: Evaluation data.

[1989] Step 14: Analysis of evaluation data

[1990] The emotion engine analyzes the emotions of the client when they enter their evaluation and provides the results to the server.

[1991] Input: Evaluation data.

[1992] Specific operation: The emotion engine analyzes the emotions of "satisfied" and "dissatisfied" from the evaluation "It was delicious, but the delivery was late."

[1993] Output: Emotion analysis results.

[1994] Step 15: Reflecting the evaluation

[1995] The server incorporates evaluation data and sentiment analysis results into the chef's evaluation and stores them in the database.

[1996] Input: Evaluation data and sentiment analysis results.

[1997] Specific operation: The server saves the evaluation and sentiment analysis results and updates the chef's evaluation points. Simultaneously calculates and arranges the rewards.

[1998] Output: Updated evaluation points and reward information.

[1999] These processing steps enable the system to efficiently produce dishes that meet the client's requests and provide service that also takes the client's feelings into consideration.

[2000] (Application Example 2)

[2001] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[2002] In modern food delivery services, providing customized meals tailored to the customer's requests and preferences is challenging. In particular, generating recipes that reflect the customer's emotions is difficult with conventional technology and has not contributed to increased customer satisfaction. Furthermore, insufficient communication between the cook and the AI ​​makes troubleshooting and quality improvement during the cooking process difficult. Additionally, there is a need for a compensation system that accurately reflects customer feedback.

[2003] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[2004] In this invention, the server includes means for receiving requests from clients, means for performing emotion analysis, means for generating new recipes based on a taste database, means for sending the generated recipes to a chef who recreates them, means for supporting communication between the chef and artificial intelligence, means for delivering the recreated dishes to clients, means for receiving evaluations from clients and reflecting the emotion analysis results in the chef's evaluation, means for the chef to communicate with the artificial intelligence using a chat function, and means for paying rewards based on the chef's evaluation. This makes it possible to provide customized dishes based on the client's emotions, improve quality through smooth communication between the chef and artificial intelligence, and realize the construction of a reward system that accurately reflects evaluations.

[2005] "Request reception" is a method of receiving and analyzing requests for dishes and flavor preferences from clients.

[2006] "Emotional analysis" is a method of determining a client's emotional state by analyzing their text and audio data.

[2007] A "taste database" is a database that stores information about ingredients and seasonings used in cooking.

[2008] "Recipe generation" is a method of creating new recipes by selecting appropriate ingredients and seasonings based on the client's requests and the results of emotional analysis.

[2009] A "cooking recreater" is someone who actually cooks a dish based on a generated recipe.

[2010] "Artificial intelligence" refers to an AI engine that supports recipe generation, emotion analysis, and communication with those who recreate the dishes.

[2011] "Delivery" refers to the method of delivering prepared and recreated meals to the customer's location.

[2012] "Receiving feedback" refers to the process of receiving feedback on the dishes from clients, analyzing that information, and incorporating it into the service.

[2013] The "chat function" is a means of text or voice communication that allows the cooking replicator to interact with artificial intelligence in real time.

[2014] "Reward payment" refers to a method of paying appropriate compensation based on the evaluation of the person who recreated the dish.

[2015] The system for implementing this invention uses multiple hardware and software components to receive requests from clients, perform emotional analysis, generate recipes based on a taste database, send them to a chef / recipe maker, support the cooking process, and deliver the recreated dishes.

[2016] System Configuration

[2017] 1. Server:

[2018] Request reception method: The system receives requests for dishes and taste preferences entered by the client and saves them as text data.

[2019] Sentiment analysis method: The received text data is analyzed to determine the client's emotions. Natural language processing tools such as TextBlob are used.

[2020] Recipe generation method: Based on the client's requests and emotion analysis results, appropriate ingredients and seasonings are selected from a taste database to generate a unique recipe. By using a generation AI model, flexible recipe suggestions are possible.

[2021] Evaluation reception method: Receive the client's evaluation and the resulting sentiment analysis, and store it in a database.

[2022] 2. The cooking reenactment operator's device:

[2023] Recipe reception method: The generated recipe is notified to the device and displayed.

[2024] AI chat function: You can chat with artificial intelligence in real time to resolve any questions that arise during cooking.

[2025] Cooking completion notification method: Notify the server when cooking is complete.

[2026] 3. Delivery System:

[2027] Delivery arrangement method: After receiving notification that cooking is complete, instruct the food delivery company to arrange delivery.

[2028] Operation details

[2029] The server receives requests from clients using the aforementioned request receiving mechanism and analyzes the client's emotional state using the emotion analysis mechanism. For example, when it receives a request such as "I want to eat something delicious but not spicy," it analyzes the request and determines it to be "positive."

[2030] Next, the recipe generation system generates an appropriate recipe based on the client's requests and the results of the sentiment analysis. For example, the generation AI model might suggest a recipe for a "delicious dish with mild spiciness." This recipe is then sent to the cook's device and displayed.

[2031] The cooking expert checks the recipe and begins cooking. If any questions arise along the way, they communicate with the artificial intelligence in real time using the terminal's chat function.

[2032] Once cooking is complete, the cook sends a completion notification to the server. The server receives this notification and arranges for the food to be delivered to the food delivery company via the delivery system.

[2033] Finally, after the client receives the dish, they access a rating form and submit their evaluation of the dish. This evaluation is also analyzed for sentiment and reflected in the evaluation of the cook who recreated the dish, and payment is made as needed.

[2034] Example of a prompt

[2035] Client's request: "I want to eat something delicious that isn't spicy."

[2036] Emotion analysis result: Positive

[2037] ---

[2038] Please generate: Create a recipe for a delicious dish with mild spiciness.

[2039] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[2040] Step 1:

[2041] The server receives the client's request.

[2042] Input: Text data containing the client's cooking preferences and taste requests.

[2043] Processing: Receive data entered from a web form and save it as text data.

[2044] Output: Saved request data.

[2045] Step 2:

[2046] The server performs sentiment analysis.

[2047] Input: Saved request data.

[2048] Processing: Analyze the sentiment of text data using natural language processing tools such as TextBlob. Determine whether the sentiment is positive or negative.

[2049] Output: Sentiment analysis results (e.g., positive).

[2050] Step 3:

[2051] The server generates new recipes based on a taste database.

[2052] Input: Request data and sentiment analysis results.

[2053] Processing: Using a generative AI model, relevant ingredients and seasonings are searched from a taste database, and a recipe is generated based on the client's requests and the results of sentiment analysis.

[2054] Output: The generated recipe.

[2055] Step 4:

[2056] The server sends the generated recipe to the person who will recreate it.

[2057] Input: The generated recipe.

[2058] Processing: A notification is sent to the device of the person recreating the recipe, and the recipe details are displayed.

[2059] Output: The recipe displayed on the cooking reenactment device.

[2060] Step 5:

[2061] The cook's device receives a notification that the recipe has been received and begins cooking.

[2062] Input: The recipe displayed on the cooking reenactment device.

[2063] Process: Review the recipe and begin cooking. If any questions arise along the way, use the device's chat function to communicate with the artificial intelligence.

[2064] Output: A finished dish.

[2065] Step 6:

[2066] The cooking reenactment operator's terminal notifies the server when cooking is complete.

[2067] Input: A finished dish.

[2068] Processing: Notify the server that cooking is complete.

[2069] Output: Cooking completion notification sent to the server.

[2070] Step 7:

[2071] The server arranges for the food to be delivered through a delivery service.

[2072] Input: Cooking completion notification.

[2073] Processing: Provide food delivery service providers with information regarding food pickup and delivery address, and arrange delivery.

[2074] Output: Notification that shipping arrangements have been completed.

[2075] Step 8:

[2076] The user receives the food and accesses the rating form.

[2077] Input: The food received.

[2078] Process: Access the rating form on the website and enter your rating for the dish.

[2079] Output: Input evaluation data.

[2080] Step 9:

[2081] The server stores evaluation data and sentiment analysis results, and uses them to evaluate the cooking recreater.

[2082] Input: The entered evaluation data.

[2083] Processing: Receive evaluation data and perform sentiment analysis again using TextBlob or similar methods. Save the results to a database and reflect them in the evaluation of the cooking recreater. Also, calculate and process payment as needed.

[2084] Output: Updated cooking replicator evaluation and reward data.

[2085] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[2086] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2087] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[2088] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2089] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[2090] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[2091] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[2092] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Toku...

Claims

1. A means of receiving requests from clients, A method for generating new recipes based on a taste database, A means of sending the generated recipe to a cooking recreater, A means to support communication between the cooking recreater and the AI, A means of delivering the recreated dishes to the client, A system that includes a means of receiving feedback from clients and reflecting it in the evaluation of the person who recreates the dish.

2. The system according to claim 1, wherein the recipe generation means includes means for selecting appropriate ingredients and seasonings based on the client's requests and generating a unique recipe.

3. The system according to claim 1, comprising means for a cooking recreater to receive a recipe and proceed with cooking using a chat function with AI.

Images