System

Abstract

A system is provided.SOLUTION: A system comprising: means for generating; means for selecting; means for indicating; means for serving; and means for collecting feedback.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In the modern restaurant industry, there is a problem that customers get tired of the same dishes easily. In addition, the labor shortage is becoming serious, making it difficult to provide stable service. For this reason, there is a need to continue offering innovative dishes that incorporate new ideas and to alleviate the labor shortage. [Means for solving the problem]

[0005] The present invention relates to a system that includes a generating means, a selecting means, an instructing means, a serving means, and a feedback collecting means. The generating means analyzes past data and automatically generates new recipes. The selecting means selects a recipe to serve from the generated recipe ideas based on evaluation criteria. The instructing means sends specific cooking instructions to an AI robot based on the selected recipe. The serving means instructs a serving robot to serve the food once it has been cooked. The feedback collecting means collects post-meal evaluations from users and uses them to generate the next recipe. This system makes it possible to continue providing innovative and new dishes, and by automating cooking and serving, it also solves the problem of labor shortages.

[0006] The "generating means" is a device or program that automatically creates a new recipe based on data entered by the user or past data.

[0007] The "selecting means" is a device or program that uses evaluation criteria to select the optimal recipe from among the multiple recipe plans that have been generated.

[0008] The "means for giving instructions" refers to a device or program that sends specific cooking steps based on the selected recipe to the AI ​​robot and instructs it to perform the task.

[0009] The "delivery means" is a device or program that instructs the delivery robot to deliver the cooked food to a specified table.

[0010] A "means for collecting feedback" is a device or program that allows users to input ratings and comments after eating, and the collected data is used to create the next recipe. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2]1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0012] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0013] First, the terms used in the following description will be explained.

[0014] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0015] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0016] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0017] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0019] [First embodiment]

[0020] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0021] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0022] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0024] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0025] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0027] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0031] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0032] The present invention is specifically embodied in a system including a generating means, a selecting means, an instructing means, a serving means, and a feedback collecting means. How the system of the present invention is implemented will be described below with specific examples.

[0033] System Overview

[0034] The system consists of three main components: a server, a terminal, and a user. The server is primarily responsible for processing data and sending instructions, while the terminal provides the user interface and feedback collection. The user actually uses the service and provides feedback.

[0035] Means of generation

[0036] The first thing the server does is generate a new recipe for each day. To do this, the server uses the following data:

[0037] Past recipe data

[0038] Popular food data

[0039] User feedback data

[0040] By analyzing this data, the generative AI creates multiple new recipe ideas. During this process, the server automatically generates ingredient combinations and cooking methods, proposing innovative and unique dishes.

[0041] Means of selection

[0042] The server evaluates the generated recipes to select the recipe to serve that day. The server uses the following criteria to select the recipe:

[0043] Ingredient availability

[0044] seasonality

[0045] Past user feedback

[0046] The server scores each recipe based on these criteria and selects the recipe with the highest score.

[0047] Means of instruction

[0048] Based on the selected recipe, the server instructs the AI ​​robot on the cooking steps. Specifically, the server generates detailed cooking instructions and sends them to the AI ​​robot, which then cooks the food according to them.

[0049] Means of serving food

[0050] Once cooking is complete, the server issues delivery instructions to the delivery robot. Specifically, the server sends information about the food's location and the designated table to the delivery robot, and the delivery robot then transports and delivers the food via the optimal route.

[0051] A means of gathering feedback

[0052] After the meal, the device asks the user for feedback via a tablet placed on the table. The user enters their meal rating and comments, and the device sends the data to the server. The server stores this feedback in a database and uses it as reference data for the next recipe generation.

[0053] Specific examples

[0054] For example, the server analyzes past data to determine that "avocado cheese sandwiches" are popular, and generates a new recipe: "avocado and grilled chicken tacos." This recipe idea receives the highest score, so it is decided to serve it that day. The server sends specific cooking instructions to the AI ​​robot, which then cooks the food according to the recipe. After cooking, the server gives serving instructions to the food delivery robot, and the food is brought to the user's table. After eating, the user enters feedback via their device, saying, "The avocado and grilled chicken tacos were very delicious." The server saves this feedback and uses it to generate future recipes.

[0055] As a result, this system can provide new dishes every day, solve the problem of labor shortages, and always provide high-quality service.

[0056] The processing flow will be explained below.

[0057] Step 1:

[0058] The server starts the generation AI at the start of business each day, retrieving past recipe data, popular ingredients data, and user feedback data from its internal database.

[0059] Step 2:

[0060] The server inputs the acquired data into the generation AI, which analyzes the data and generates new recipes. The generation AI generates multiple new recipe ideas based on "randomly selected combinations of ingredients" and "combinations of cooking methods."

[0061] Step 3:

[0062] The server saves the generated recipe plan and the list of ingredients and cooking utensils required in the database.

[0063] Step 4:

[0064] The server evaluates multiple saved recipe ideas and assigns a score to each recipe, taking into account ingredient availability, seasonality, and past user feedback.

[0065] Step 5:

[0066] Based on the scoring results, the server selects the recipes to serve that day in order of highest score.

[0067] Step 6:

[0068] The server generates specific cooking instructions (instructions) based on the selected recipe.

[0069] Step 7:

[0070] The server sends the generated cooking instructions to the AI ​​robot, which then checks the instructions, prepares the necessary ingredients, and cooks the food.

[0071] Step 8:

[0072] Once cooking is complete, the AI ​​robot places the food on a serving tray and contacts the serving robot.

[0073] Step 9:

[0074] The server issues instructions to the delivery robot, which then sends instructions to deliver the finished dish to the designated table. The delivery robot uses a map of the restaurant to transport the dish along the optimal route and deliver it to the table.

[0075] Step 10:

[0076] After the meal, the device asks the user for feedback via a tablet installed on each table. The user operates the tablet to input their meal rating and comments.

[0077] Step 11:

[0078] The device sends the collected feedback data to the server, which stores the received feedback in a database and uses it as reference data for the next recipe generation.

[0079] Example 1

[0080] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0081] Conventional systems have been inefficient in the entire process from proposing dishes to cooking, serving, and collecting feedback, resulting in labor shortages and time-consuming tasks due to the high level of manual work. Furthermore, the lack of a mechanism for reflecting user preferences and past feedback has led to inconsistent food quality. The present invention aims to solve these problems and provide a system for providing efficient, high-quality food.

[0082] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0083] In this invention, the server

[0084] a means of collecting data;

[0085] A means for generating new proposals using a generative AI model; and

[0086] means for selecting from among the generated proposals based on evaluation criteria;

[0087] means for transmitting instructions based on the selected suggestions;

[0088] means for transporting the goods in accordance with the instructions;

[0089] a means of collecting feedback;

[0090] This will automate a series of processes and reflect user preferences and feedback, enabling efficient and high-quality food delivery.

[0091] "Means for collecting data" refers to means for capturing historical information, popular information, and user opinions from a database and making them available for the next stage of processing.

[0092] "Means for generating new proposals using generative AI models" refers to means for automatically creating new ideas and recipes using generative AI models based on collected data.

[0093] The "means for selecting from among the generated proposals based on evaluation criteria" refers to a means for evaluating the generated proposals based on inventory status, seasonality, and past opinions, and selecting the most suitable one.

[0094] The "means for transmitting instructions based on the selected suggestion" is a means for transmitting specific instructions to an appropriate device for automating cooking or other tasks in accordance with the selected suggestion.

[0095] "Means for transporting goods in accordance with the instructions" means the equipment or devices for properly transporting goods to the designated location in accordance with the instructions.

[0096] The "means for collecting feedback" is a means for collecting opinions and evaluations from users and storing them in the system so that they can be used when generating the next proposal.

[0097] This invention relates to a system that automates a series of processes: collecting data, generating new proposals using a generative AI model, making selections and instructions based on evaluation criteria, transporting goods according to the instructions, and collecting feedback. This system consists of three main elements: a server, a terminal, and a user.

[0098] Server Roles

[0099] The server is mainly responsible for processing data and sending instructions. Each of these methods will be explained in detail below.

[0100] How data is collected

[0101] The server collects past recipe data, popular ingredient data, and user feedback data from a database, which are then used in the process of utilizing the generative AI model.

[0102] A means of generating new proposals using generative AI models

[0103] The server creates prompts for the generative AI model based on the collected data and sends them to the model to generate multiple new recipe ideas. Examples of prompts include:

[0104] "Generate new recipes based on past popular ingredients and user feedback."

[0105] When the generative AI model receives this prompt, it analyzes the input data and generates new recipe ideas.

[0106] A means of selecting from the generated proposals based on evaluation criteria

[0107] The server evaluates the generated recipe ideas, using criteria such as ingredient availability, seasonality, and past user feedback. The recipe with the highest score is selected as the result of the evaluation.

[0108] A means of sending instructions based on the selected suggestion

[0109] The server creates detailed cooking instructions based on the selected recipe and sends them to the AI ​​robot, which then begins cooking according to the instructions.

[0110] A means of transporting goods based on that instruction

[0111] Once cooking is complete, the server sends serving instructions to the food delivery robot, including information on where to place the food and the designated table. The food delivery robot receives instructions from the server and transports and serves the food to the user's table.

[0112] Device Role

[0113] The terminal mainly handles the user interface and feedback collection.

[0114] A means of gathering feedback

[0115] After the meal, the device asks the user for feedback via a tablet placed on the table. The user enters their rating and comments on the food, and the device sends the data to the server. The server stores this feedback in a database and uses it as reference data when generating the next recipe.

[0116] User Roles

[0117] Users actually use the system and provide feedback on the food served.

[0118] As a concrete example, consider the case where the server analyzes from past data that "avocado cheese sandwiches" are popular, and then uses a new generative AI model to generate "avocado and grilled chicken tacos." This recipe idea received the highest score, so it is selected as the dish to be served that day. The server sends cooking instructions to the AI ​​robot, which follows those instructions to cook the dish. After cooking is complete, the server gives serving instructions to the food delivery robot, and the dish is brought to the user's table. After eating, the user enters feedback via their device, saying, "The avocado and grilled chicken tacos were very delicious." The server saves this feedback and uses it to generate the next recipe.

[0119] In this way, the system of the present invention not only realizes efficient and high-quality food provision, but also has the function of reflecting user preferences and feedback.

[0120] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0121] Program processing steps

[0122] Step 1:

[0123] The server collects past recipe data, popular ingredient data, and user feedback data from the database. The input for this data collection is past data from various databases and external data sources. The collected data is used in the next step.

[0124] Step 2:

[0125] The server creates a prompt for the generative AI model based on the collected data. The input here is the data collected in step 1, and the output is a text prompt to be sent to the generative AI model. A specific prompt generated is "Please generate a new recipe based on past popular ingredients and user feedback."

[0126] Step 3:

[0127] The server sends a prompt to the generative AI model to generate multiple new recipe ideas. The input is the prompt created in step 2, and the output is multiple new recipe ideas. The generative AI model processes and calculates data based on these recipe ideas to provide new recipe ideas.

[0128] Step 4:

[0129] The server evaluates the generated recipe ideas. Evaluation criteria include ingredient availability, seasonality, and past user feedback. The input is the recipe ideas generated in step 3 and the evaluation criteria data, and the output is an evaluation score. Specifically, each recipe is multiplied by the availability data and seasonality information, and the feedback data is weighted to calculate the score.

[0130] Step 5:

[0131] The server selects the recipe with the highest score. The input is the evaluation score calculated in step 4, and the output is the selected recipe. Here, an algorithm is used to automatically select the recipe with the highest score.

[0132] Step 6:

[0133] The server creates detailed cooking instructions based on the selected recipe and sends them to the AI ​​robot. The input is the selected recipe, and the output is data on the specific cooking instructions. The server breaks down the steps of the selected recipe, converts them into a format that the AI ​​robot can understand, and sends them.

[0134] Step 7:

[0135] The AI ​​robot receives the cooking instructions and starts cooking. The input is the detailed cooking instructions sent in step 6, and the output is the cooked food. The AI ​​robot follows the cooking instructions to process the ingredients, cook, and serve.

[0136] Step 8:

[0137] Once cooking is complete, the server sends serving instructions to the delivery robot. The input is the cooked food and serving instructions data, and the output is serving instructions to the delivery robot. The server combines the recipe and table information to calculate the optimal route and sends it to the delivery robot.

[0138] Step 9:

[0139] The delivery robot receives instructions from the server and transports and serves food to the user's table. The input is the delivery instruction data from the server, and the output is the food being served to the correct table. The delivery robot follows the instructions and accurately delivers the food to the user's table.

[0140] Step 10:

[0141] After the meal, the device asks the user for feedback via a tablet installed on the table. The input is the user's dining experience, and the output is feedback data. The device allows users to easily input ratings and comments via the tablet.

[0142] Step 11:

[0143] The user inputs ratings and comments on the meal. The input is the user's feedback, and the output is the rating data stored on the device.

[0144] Step 12:

[0145] The terminal sends the collected feedback to the server. The input is the user's evaluation data, and the output is the feedback sent to the server. The server stores this data in a database and uses it the next time it generates a recipe.

[0146] Through this series of processes, the system enables efficient and high-quality food delivery.

[0147] (Application example 1)

[0148] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0149] Current food delivery services often lack a wide variety of menu items, making it difficult for users to enjoy new dishes every day. Furthermore, the process from cooking to delivery is not streamlined, making it difficult to maintain a high level of service. Furthermore, there is no mechanism for incorporating user feedback into future service improvements.

[0150] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0151] In this invention, the server includes a generating means, a selecting means, an instructing means, a delivering means, and a feedback collecting means. This makes it possible to analyze past data to automatically generate new recipes every day and notify users of a different recipe each day. Furthermore, an efficient and high-quality food delivery service can be realized by having an AI robot provide cooking instructions and manage delivery. Furthermore, since feedback from users can be collected and reflected in future services, continuous improvement of the service can be expected.

[0152] The "means of generation" is a function that analyzes past data to automatically generate new recipes and notifies users of them on a daily basis.

[0153] The "means of selection" is a function that selects the optimal recipe from the multiple recipe ideas generated based on evaluation criteria and instructs the AI ​​robot on specific cooking steps.

[0154] The "means of giving instructions" is a function that sends detailed cooking instructions to the AI ​​robot based on the selected recipe, allowing it to cook appropriately.

[0155] The "delivery means" is a function that transports cooked food to a location designated by the user and manages the delivery progress in real time.

[0156] The "means of collecting feedback" refers to a function that allows users to input ratings and comments on the delivered food, and sends that data to the server, which uses it to generate the next recipe and improve the service.

[0157] A "server" is a central computer that processes data, sends instructions, and manages the entire system.

[0158] A "terminal" is a device that acts as a user interface and collects feedback from the user.

[0159] "Users" are individuals or corporations who actually use the food delivery service and provide feedback.

[0160] An "AI robot" is a machine equipped with artificial intelligence that automatically cooks based on instructions from a server.

[0161] A "delivery robot" is an automated delivery device designed to deliver cooked food to users.

[0162] The present invention relates to a food delivery system including a generating means, a selecting means, a directing means, a delivering means, and a feedback collecting means. How to implement the present invention will be specifically described below.

[0163] System Overview

[0164] The system consists of three main components: a server, a terminal, and a user. The server is primarily responsible for processing data and sending instructions, while the terminal provides the user interface and feedback collection. The user actually uses the service and provides feedback.

[0165] Means of generation

[0166] The first thing the server does is generate a new recipe for each day. To do this, the server uses the following data:

[0167] Past recipe data

[0168] Popular food data

[0169] User feedback data

[0170] By analyzing this data, the generative AI creates multiple new recipe ideas. During this process, the server automatically generates ingredient combinations and cooking methods to suggest innovative and unique dishes. For example, the following prompts can be used:

[0171] Generate a new recipe based on the following data:

[0172] Past recipe data: Avocado Cheese Sandwich, Tomato Soup, Grilled Steak

[0173] Popular ingredients: avocado, chicken, cheese

[0174] User Feedback Data:

[0175] Avocado and Cheese Sandwich: 4.5

[0176] Tomato soup: 4.0

[0177] Grilled Steak: 5.0

[0178] Means of selection

[0179] The server evaluates the generated recipes to select the recipe to serve that day. The server uses the following criteria to select the recipe:

[0180] Ingredient availability

[0181] seasonality

[0182] Past user feedback

[0183] The server scores each recipe based on these criteria, selects the highest-scoring recipe, and then provides detailed cooking instructions to the AI ​​robot based on the selected recipe.

[0184] Means of instruction

[0185] Based on the selected recipe, the server instructs the AI ​​robot on the cooking steps. Specifically, the server generates detailed cooking instructions and sends them to the AI ​​robot, which then cooks the food according to them.

[0186] Means of delivery

[0187] Once cooking is complete, the server issues delivery instructions to the delivery robot. Specifically, the server sends the delivery location and address information to the delivery robot, and the delivery robot then transports and delivers the food via the optimal route. Users can check the delivery progress in real time through the application.

[0188] A means of gathering feedback

[0189] After delivery, the user can enter their rating and comments using a smartphone application. This feedback is sent from the device to the server, which stores the data and uses it as reference data when generating the next recipe.

[0190] Specific examples

[0191] For example, the server analyzes past data to determine that "avocado cheese sandwiches" are popular, and generates a new recipe: "avocado and grilled chicken tacos." This recipe idea receives the highest score, so it is decided to serve it that day. The server sends specific cooking instructions to the AI ​​robot, which then cooks the food according to the recipe. After cooking, the server gives delivery instructions to the delivery robot, and the food is delivered to the location specified by the user. After delivery, the user enters feedback through the application, saying, "The avocado and grilled chicken tacos were very delicious." The server saves this feedback and uses it to generate future recipes.

[0192] As a result, this system can provide new dishes every day, realize an efficient and high-quality food delivery service, and always provide high-quality service.

[0193] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0194] Step 1:

[0195] Data collection and analysis

[0196] The server collects past recipe data, popular ingredient data, and user feedback data. Using this data as input, the generative AI model begins analysis to automatically generate new recipes. Specifically, it analyzes ingredient combinations and cooking methods to generate recipe suggestions that take into account novelty and user preferences.

[0197] input:

[0198] Past recipe data

[0199] Popular food data

[0200] User feedback data

[0201] output:

[0202] Newly generated recipe ideas

[0203] Step 2:

[0204] Recipe Selection

[0205] The server scores the generated recipe ideas based on evaluation criteria and selects the recipe to be served that day. Each recipe is scored based on ingredient availability, seasonality, and past user feedback. The recipe with the highest score is then selected.

[0206] input:

[0207] Newly generated recipe ideas

[0208] Ingredient inventory data

[0209] Seasonal Data

[0210] User feedback data

[0211] output:

[0212] Selected Recipes

[0213] Step 3:

[0214] Cooking instructions

[0215] The server sends detailed cooking instructions to the AI ​​robot based on the selected recipe. Specifically, it instructs the AI ​​robot on which ingredients to use, in what order, and what cooking method to use. Based on these instructions, the AI ​​robot begins cooking.

[0216] input:

[0217] Selected Recipes

[0218] Detailed cooking instructions

[0219] output:

[0220] Send cooking instructions

[0221] Step 4:

[0222] Cooking and delivery preparation

[0223] The AI ​​robot prepares the food according to the cooking instructions received from the server. At the same time, the server sends delivery preparation instructions to the delivery robot, which receives information about the food pick-up location and the user's designated address.

[0224] input:

[0225] Cooking instructions

[0226] Delivery Information

[0227] output:

[0228] Start cooking

[0229] Send delivery preparation instructions

[0230] Step 5:

[0231] Delivery and progress tracking

[0232] Once the food is ready, the server sends instructions to the delivery robot to pick it up. The delivery robot then takes the optimal route and delivers the food to the location specified by the user. Users can check the delivery progress in real time through a smartphone application.

[0233] input:

[0234] The finished dish

[0235] Delivery instructions

[0236] output:

[0237] Food delivery

[0238] Delivery progress information

[0239] Step 6:

[0240] Gathering feedback

[0241] After receiving the food, the user can enter their rating and comments using a smartphone application. The feedback is sent from the device to the server, which stores this data and uses it as reference data when generating the next recipe.

[0242] input:

[0243] User Feedback

[0244] output:

[0245] Feedback Data Storage

[0246] In this way, the server, terminals, and users work together to realize an efficient and high-quality food delivery service. By utilizing generative AI models, users can enjoy new dishes every day, and the service can be expected to continuously improve.

[0247] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0248] The present invention is specifically embodied by a system including a generating means, a selecting means, an instructing means, a serving means, a feedback collecting means, and an emotion engine that recognizes the emotion of a user. An embodiment of the system of the present invention will be described below with specific examples.

[0249] System Overview

[0250] The system consists of three main components: a server, a terminal, and a user, as well as an emotion engine. The server is primarily responsible for data processing and instruction transmission, while the terminal provides the user interface and feedback collection, and the emotion engine analyzes user emotions. Users actually use the service and provide feedback and emotion data.

[0251] Means of generation

[0252] This is the generation method the server uses to generate new recipes each day. The server uses the following data:

[0253] Past recipe data

[0254] Popular food data

[0255] User Feedback Data

[0256] Emotion data from emotion engine

[0257] By analyzing this data, the generative AI creates multiple new recipe ideas. During this process, the server automatically generates ingredient combinations and cooking methods, proposing innovative and unique dishes.

[0258] Means of selection

[0259] The server evaluates the generated recipes to select the recipe to serve that day. The server uses the following criteria to select the recipe:

[0260] Ingredient availability

[0261] seasonality

[0262] Past feedback including user emotional data

[0263] The server scores each recipe based on these criteria and selects the recipe with the highest score.

[0264] Means of instruction

[0265] Based on the selected recipe, the server instructs the AI ​​robot on the cooking steps. Specifically, the server generates detailed cooking instructions and sends them to the AI ​​robot, which then cooks the food according to them.

[0266] Means of serving food

[0267] Once cooking is complete, the server issues delivery instructions to the delivery robot. Specifically, the server sends information about the food's location and the designated table to the delivery robot, and the delivery robot then transports and delivers the food via the optimal route.

[0268] A means of gathering feedback

[0269] After the meal, the device asks the user for feedback via a tablet placed on the table. The user enters their meal rating and comments, and the device sends the data to the server. The server stores this feedback in a database and uses it as reference data for the next recipe generation.

[0270] Emotion Engine

[0271] The emotion engine is particularly important. During and after the meal, the emotion engine analyzes the user's facial expressions, voice, gestures, etc. using the device's built-in camera and voice recognition system. It then compiles detailed data on how the user felt about the food and stores it as feedback. This emotion data is taken into consideration when generating the next recipe.

[0272] Specific examples

[0273] For example, the server analyzes past data to determine that "avocado cheese sandwiches" are popular, and generates a new recipe: "avocado and grilled chicken tacos." This recipe idea receives the highest score, so it is decided to serve it that day. The server sends specific cooking instructions to the AI ​​robot, which then cooks the food according to the recipe. After cooking, the server gives serving instructions to the food delivery robot, and the food is brought to the user's table. During the meal, the emotion engine analyzes the user's facial expressions and voice, and the user later inputs feedback, such as "The avocado and grilled chicken tacos were very delicious." The server saves this feedback and emotion data and uses it to generate future recipes.

[0274] As a result, this system can provide new dishes every day, solve the problem of labor shortages, and always provide high-quality service and a cooking experience based on the user's emotions.

[0275] The processing flow will be explained below.

[0276] Step 1:

[0277] The server starts the generation AI at the start of business every day. The server retrieves past recipe data, popular ingredient data, user feedback data, and emotion data from the emotion engine from its internal database.

[0278] Step 2:

[0279] The server inputs the acquired data into the generation AI, which analyzes the data and generates new recipes. The generation AI generates multiple new recipe ideas based on "randomly selected combinations of ingredients" and "combinations of cooking methods."

[0280] Step 3:

[0281] The server saves the generated recipe plan and the list of ingredients and cooking utensils required in the database.

[0282] Step 4:

[0283] The server evaluates the stored recipe ideas and assigns a score to each recipe based on past feedback, including ingredient availability, seasonality, and user sentiment data.

[0284] Step 5:

[0285] Based on the scoring results, the server selects the recipes to serve that day in order of highest score.

[0286] Step 6:

[0287] The server generates specific cooking instructions (instructions) based on the selected recipe.

[0288] Step 7:

[0289] The server sends the generated cooking instructions to the AI ​​robot, which then checks the instructions, prepares the necessary ingredients, and cooks the food.

[0290] Step 8:

[0291] Once cooking is complete, the AI ​​robot places the food on a serving tray and contacts the serving robot.

[0292] Step 9:

[0293] The server issues instructions to the delivery robot, instructing it to deliver the finished dish to the designated table. The delivery robot uses a map of the restaurant to transport the dish along the optimal route and deliver it to the table.

[0294] Step 10:

[0295] During and after the meal, the device uses a camera and microphone installed on the table to analyze the user's facial expressions, voice, gestures, etc., and the emotion engine saves the analysis results as feedback.

[0296] Step 11:

[0297] After eating, the device asks the user for feedback, and the user operates the tablet to input their meal rating and comments.

[0298] Step 12:

[0299] The device sends the collected feedback data and the emotion data analyzed by the emotion engine to the server, which stores this data in a database and uses it as reference data for the next recipe generation.

[0300] This allows the entire system to work together, offering new dishes every day while collecting and analyzing user feedback based on emotions, allowing for continuous improvement in the quality of service.

[0301] Example 2

[0302] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0303] Conventional recipe suggestion systems and cooking services have difficulty providing optimal recipes based on users' tastes and preferences, and have also been unable to provide services that take users' emotions into consideration.In addition, labor shortages have made it difficult to operate efficiently in cooking and serving food.

[0304] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for generating a new recipe using a generative AI model, a means for selecting a recipe to be provided from the generated recipes based on evaluation criteria, a means for sending cooking instructions to a cooking device based on the selected recipe, a means for sending serving instructions to a food serving device after cooking is completed, a means for collecting evaluations from the user after eating, and a means for collecting emotion data by analyzing the user's facial expressions and voice. This enables the provision of optimal recipes that take into account the user's preferences and emotions, and efficient cooking and food serving operations.

[0305] A "generative AI model" is an artificial intelligence algorithm that analyzes past data and automatically generates new recipes.

[0306] "Evaluation criteria" are the criteria used to select which recipes to offer from the generated recipe ideas. Examples include ingredient availability, seasonality, and past feedback including user emotional data.

[0307] A "cooking device" is an automated mechanical device that cooks food according to cooking instructions received from the server.

[0308] A "serving device" is an automated machine that transports food after cooking is complete and serves it to a designated location based on instructions from the server.

[0309] "User feedback data" is information provided by the user as ratings and comments after eating, and is used as reference for creating the next recipe.

[0310] "Emotion data" is information about emotions obtained by analyzing the user's facial expressions, voice, gestures, etc.

[0311] A "server" is a central computer system that processes data, sends instructions, generates and selects recipes, processes feedback, etc.

[0312] This system generates new recipes using a generative AI model, selects recipes based on evaluation criteria, and sends instructions to cooking devices and serving devices to provide meals based on the user's preferences and emotions. This system is composed of a server, a terminal, a user, and an emotion engine.

[0313] The server processes and calculates data using the following hardware and software:

[0314] The hardware and software used includes:

[0315] Hardware: High-performance computer servers, database servers, and network equipment

[0316] Software: Generative AI models, database management systems, sentiment analysis engines

[0317] Recipe Generation

[0318] The server generates new recipes using a generative AI model. Specifically, it collects and analyzes past recipe data, popular ingredient data, user feedback data, and sentiment data to create multiple new recipe suggestions. An example prompt is as follows:

[0319] "Generate new recipes based on popular recipes from the past week and user feedback"

[0320] Recipe Selection

[0321] The server selects the best recipe from the multiple recipe ideas generated based on evaluation criteria, including ingredient availability, seasonality, and past feedback including user sentiment data. The server assigns a score to each recipe based on these criteria and selects the recipe with the highest score.

[0322] cooking instructions

[0323] The server sends cooking instructions to the cooking device based on the selected recipe. Specifically, it sends the generated detailed cooking instructions to the AI ​​robot, which then cooks the food according to the instructions.

[0324] Serving instructions

[0325] Once cooking is complete, the server sends instructions to the serving device. Specifically, the server sends information about the food placement location and the designated table to the serving robot, and the serving robot then transports and serves the food along the optimal route.

[0326] Feedback collection

[0327] After the meal, the device asks the user for feedback. The user enters their meal rating and comments on a tablet placed on the table, and the device sends the data to the server. The server stores this feedback in a database and uses it as reference data for the next recipe generation.

[0328] Emotion analysis

[0329] Emotion analysis is particularly important. During and after a meal, the emotion engine analyzes the user's facial expressions, voice, and gestures using the device's built-in camera and voice recognition system. The analyzed emotion data is converted into detailed data and saved as feedback. This emotion data is taken into consideration when generating the next recipe.

[0330] Specific examples

[0331] For example, the server analyzes past data to determine that "avocado cheese sandwiches" are popular, and generates a new recipe: "avocado and grilled chicken tacos." This recipe idea receives the highest score, so it is decided to serve it that day. The server sends specific cooking instructions to the AI ​​robot, which then cooks the food according to the recipe. After cooking, the server gives serving instructions to the food delivery robot, and the food is brought to the user's table. During the meal, the emotion engine analyzes the user's facial expressions and voice, and the user later inputs feedback, such as "The avocado and grilled chicken tacos were very delicious." The server saves this feedback and emotion data and uses it to generate future recipes.

[0332] Through the above processing, the system can propose and serve new dishes that take into account the user's preferences and emotions, enabling efficient cooking and serving.

[0333] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0334] Step 1: Data collection

[0335] The server collects past recipe data, popular ingredient data, user feedback data, and sentiment data from a database. This data serves as input data for generating new recipes using a generative AI model. The server accesses the database using SQL queries to extract the necessary information. Specifically, it executes the query "Get recipe data from the past week" and retrieves the results from the database. The output is a set of collected data.

[0336] Step 2: Recipe generation

[0337] The server inputs the collected data into the generative AI model to generate new recipe suggestions. Specifically, the server inputs a prompt to the generative AI model: "Generate a new recipe based on the popular recipes from the past week and user feedback." The generative AI model generates multiple new recipe suggestions based on this prompt. The input is the collected data set and the prompt, and the output is the generated multiple new recipe suggestions.

[0338] Step 3: Recipe Selection

[0339] The server evaluates the generated recipe ideas to select the most appropriate one. Evaluation criteria include ingredient availability, seasonality, and past feedback including user sentiment data. The server uses these criteria to assign a score to each recipe and selects the recipe with the highest score. For example, if the server selects "Avocado and Grilled Chicken Tacos," it indicates that the recipe received a high score. The input is the generated recipe ideas and evaluation criteria, and the output is the selected recipe.

[0340] Step 4: Cooking Instructions

[0341] The server sends cooking instructions to the cooking device based on the selected recipe. The server then sends the generated detailed cooking instructions to the AI ​​robot, which then follows the instructions to cook. Specifically, the server sends specific instructions to the AI ​​robot, such as "Slice the avocado and prepare the grilled chicken." The input is the selected recipe, and the output is the cooking instructions sent to the cooking device.

[0342] Step 5: Serving instructions

[0343] Once cooking is complete, the server sends serving instructions to the food delivery device. The server sends information about the food's location and the specified table to the food delivery robot, which then transports and delivers the food along the optimal route. For example, the server sends the instruction "Deliver avocado and grilled chicken tacos to table number 5" to the food delivery robot. The input is the completed cooking information and the target table information, and the output is the serving instructions sent to the food delivery device.

[0344] Step 6: Gather feedback

[0345] After eating, the device provides an interface to ask the user for feedback. The user inputs their meal rating and comments using a tablet placed on the table, and the device sends the data to the server. The server stores this feedback in a database and uses it as a reference when generating the next recipe. Specifically, the user inputs a rating such as "The tacos were delicious," and this is sent to the server. The input is the feedback provided by the user, and the output is the feedback data stored in the database.

[0346] Step 7: Sentiment Analysis

[0347] The device analyzes the user's emotions during and after the meal. The device's camera and voice recognition system record the user's facial expressions and voice, and the emotion engine analyzes the data. The analysis results are sent to the server and saved as feedback. For example, if a user smiles and says "delicious," this is converted into data as a positive emotion. The input is the user's facial expression and voice data acquired from the device, and the output is emotion data saved on the server.

[0348] (Application example 2)

[0349] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0350] Modern food delivery services often fail to fully utilize user preferences, past order history, and real-time sentiment data, resulting in low user satisfaction. Furthermore, the lack of automation in cooking and serving food leads to labor shortages and reduced efficiency. This results in inconsistent user experience. The purpose of this invention is to solve these issues and provide a high-quality food delivery service.

[0351] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a generating means, a selecting means, an instructing means, a serving means, a feedback collecting means, an emotion engine that recognizes the user's emotions, and a means for proposing new dishes by taking into account the user's past order data, popular ingredient data, and emotion data. This makes it possible to provide personalized dishes based on the user's preferences and emotion data, and furthermore, by automating cooking and serving, it is possible to achieve improved efficiency and consistent quality.

[0352] The "generating means" is a device or program that has the function of analyzing past data and automatically generating new recipes.

[0353] The "selecting means" is a device or program that has the function of selecting a recipe to provide from the generated recipe plans based on evaluation criteria.

[0354] The "means for instructing" is a device or program that has the function of instructing related equipment or robots on cooking procedures based on the selected recipe.

[0355] The "serving means" refers to a device or program that has the function of transporting and serving the cooked food to a designated location or table.

[0356] The "means for collecting feedback" is a device or program that has the function of collecting and storing feedback data from users.

[0357] An "emotion engine" is a device or program that has the function of analyzing a user's facial expressions, voice, gestures, etc. and recognizing emotions.

[0358] "User's past order data" refers to historical information such as dishes that the user has ordered in the past and their ratings.

[0359] "Popular food data" refers to data that includes information about food that is highly popular during a specific period or in a specific region.

[0360] "Emotion data" refers to data that indicates information about a user's emotions analyzed using an emotion engine.

[0361] The "means for suggesting new dishes" is a device or program that has the function of suggesting new dishes personalized to the user based on the user's past order data, popular ingredient data, and emotional data.

[0362] MODE FOR CARRYING OUT THE INVENTION

[0363] System Overview

[0364] The system consists of three main components: a server, a terminal, and a user, as well as an emotion engine. The server is primarily responsible for data processing and instruction transmission, while the terminal provides the user interface and feedback collection, and the emotion engine analyzes user emotions. Users actually use the service and provide feedback and emotion data.

[0365] Server Processing

[0366] 1. Data Collection:

[0367] The server collects and stores the user's past order data, popular ingredients data, and emotional data, including cooking history, ordering ratings, and the user's facial expressions and voice data.

[0368] 2. Means of generation:

[0369] The server analyzes the collected data and automatically generates new recipes using a generative AI model, taking into account past order data and popular ingredients.

[0370] 3. Choose your method:

[0371] The server evaluates the generated recipe ideas based on inventory, seasonality, and past feedback data, assigning a score to each recipe idea, and the recipe with the highest score is selected.

[0372] 4. Means of instruction:

[0373] Based on the selected recipe, the server instructs the cooking robot on specific cooking steps, which causes the cooking robot to automatically start cooking.

[0374] 5. Means of serving:

[0375] After cooking is complete, the server instructs the serving robot to transport and serve the food to the designated table.

[0376] 6. Feedback Collection:

[0377] The server collects feedback from users through their terminals, allowing users to input their ratings and comments on the food they have been served.

[0378] Emotion engine processing

[0379] The emotion engine uses the device's built-in camera and microphone to analyze the user's facial expressions and voice data and generate emotion data. For example, it evaluates the user's level of satisfaction from their facial expressions while they are eating and sends this data to the server.

[0380] Terminal handling

[0381] The terminal is a device such as a tablet placed on a table and used by the user as an interface. The terminal not only collects feedback but also acquires emotional data from the user.

[0382] Specific examples

[0383] The server analyzes past data to determine that "Spicy Chicken Curry" is popular, and generates a new recipe called "Spicy Chicken Curry Wrap." This recipe idea received the highest score, so it is decided to serve it that day. The server sends specific cooking instructions to the cooking robot, and after cooking, a serving robot brings the food to the user. While eating, the device's camera analyzes the user's facial expressions, and an emotion engine evaluates their level of satisfaction. The user then inputs feedback, such as "The spicy chicken curry wrap was very delicious." This data is used to generate the next recipe.

[0384] Example prompts for generative AI models

[0385] "Suggest new recipes based on the user's past order data, popular ingredients, and sentiment data. For example, if the user has previously ordered 'Spicy Chicken Curry,' use that data to generate a new 'Spicy Chicken Curry Wrap.'"

[0386] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0387] Step 1:

[0388] The server collects users' past order data, popular ingredient data, and emotional data. This includes cooking history, ordering ratings, and the user's facial and voice data. The server reads this data from the database and prepares it for analysis. It uses past order data, popular ingredient data, and emotional data as inputs and generates an integrated dataset that can be used for analysis as output.

[0389] Step 2:

[0390] The server uses the generated means to analyze the collected data and automatically generate new recipes using a generative AI model. This process also takes into account the user's past preferences and emotional data. The integrated dataset is used as input, and multiple new recipe suggestions are generated as output. Specifically, the server sends a prompt to the generative AI model and receives the returned recipe suggestions.

[0391] Step 3:

[0392] The server evaluates the generated recipe ideas using a method selected by the server. Evaluation criteria include inventory status, seasonality, and past feedback data. The generated recipe ideas and evaluation criteria data are used as input, and the recipe with the highest score is selected as output. Specifically, the server calculates a score based on the evaluation criteria for each recipe idea, and selects the recipe with the highest score.

[0393] Step 4:

[0394] Using the means instructed by the server, the cooking robot is instructed on specific cooking steps based on the selected recipe. The selected recipe is used as input, and commands including the cooking steps are generated and sent as output. Specifically, the cooking steps are extracted from the recipe data and instructions are sent to the cooking robot.

[0395] Step 5:

[0396] The server uses the means of serving to instruct the serving robot to transport and serve the cooked food to the specified table. It uses the cooking completion notification and serving information as input, and generates and sends serving instructions as output. Specifically, it receives the cooking completion notification from the cooking robot and sends the food location and table information to the serving robot.

[0397] Step 6:

[0398] The device collects feedback from users. After collecting the feedback, the server stores the data. The system uses the ratings and comments entered by users on the tablet device as input, generates feedback data as output, and stores it in a database. Specifically, the device collects the feedback information entered by users on the tablet device and sends it to the server.

[0399] Step 7:

[0400] The device uses an emotion engine to analyze the user's facial expression and voice data and generate emotion data. The device uses the user's facial expression and voice data acquired from a camera or microphone as input, and generates and saves emotion data as output. Specifically, the device captures the user's facial expression and voice with a camera or microphone during and after a meal, and the emotion engine analyzes this to generate emotion data, which is then sent to the server.

[0401] Step 8:

[0402] The server saves the collected feedback and emotion data and uses it for the next recipe generation. The feedback and emotion data are used as input, and reference data for the next recipe generation is generated and saved as output. Specifically, the server stores the collected data in a database and converts it into a usable format for the next analysis.

[0403] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0404] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0405] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0406] [Second embodiment]

[0407] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0408] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0409] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0410] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0411] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0412] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0413] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0414] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0415] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0416] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0417] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0418] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0419] The present invention is specifically embodied in a system including a generating means, a selecting means, an instructing means, a serving means, and a feedback collecting means. How the system of the present invention is implemented will be described below with specific examples.

[0420] System Overview

[0421] The system consists of three main components: a server, a terminal, and a user. The server is primarily responsible for processing data and sending instructions, while the terminal provides the user interface and feedback collection. The user actually uses the service and provides feedback.

[0422] Means of generation

[0423] The first thing the server does is generate a new recipe for each day. To do this, the server uses the following data:

[0424] Past recipe data

[0425] Popular food data

[0426] User feedback data

[0427] By analyzing this data, the generative AI creates multiple new recipe ideas. During this process, the server automatically generates ingredient combinations and cooking methods, proposing innovative and unique dishes.

[0428] Means of selection

[0429] The server evaluates the generated recipes to select the recipe to serve that day. The server uses the following criteria to select the recipe:

[0430] Ingredient availability

[0431] seasonality

[0432] Past user feedback

[0433] The server scores each recipe based on these criteria and selects the recipe with the highest score.

[0434] Means of instruction

[0435] Based on the selected recipe, the server instructs the AI ​​robot on the cooking steps. Specifically, the server generates detailed cooking instructions and sends them to the AI ​​robot, which then cooks the food according to them.

[0436] Means of serving food

[0437] Once cooking is complete, the server issues delivery instructions to the delivery robot. Specifically, the server sends information about the food's location and the designated table to the delivery robot, and the delivery robot then transports and delivers the food via the optimal route.

[0438] A means of gathering feedback

[0439] After the meal, the device asks the user for feedback via a tablet placed on the table. The user enters their meal rating and comments, and the device sends the data to the server. The server stores this feedback in a database and uses it as reference data for the next recipe generation.

[0440] Specific examples

[0441] For example, the server analyzes past data to determine that "avocado cheese sandwiches" are popular, and generates a new recipe: "avocado and grilled chicken tacos." This recipe idea receives the highest score, so it is decided to serve it that day. The server sends specific cooking instructions to the AI ​​robot, which then cooks the food according to the recipe. After cooking, the server gives serving instructions to the food delivery robot, and the food is brought to the user's table. After eating, the user enters feedback via their device, saying, "The avocado and grilled chicken tacos were very delicious." The server saves this feedback and uses it to generate future recipes.

[0442] As a result, this system can provide new dishes every day, solve the problem of labor shortages, and always provide high-quality service.

[0443] The processing flow will be explained below.

[0444] Step 1:

[0445] The server starts the generation AI at the start of business each day, retrieving past recipe data, popular ingredients data, and user feedback data from its internal database.

[0446] Step 2:

[0447] The server inputs the acquired data into the generation AI, which analyzes the data and generates new recipes. The generation AI generates multiple new recipe ideas based on "randomly selected combinations of ingredients" and "combinations of cooking methods."

[0448] Step 3:

[0449] The server saves the generated recipe plan and the list of ingredients and cooking utensils required in the database.

[0450] Step 4:

[0451] The server evaluates multiple saved recipe ideas and assigns a score to each recipe, taking into account ingredient availability, seasonality, and past user feedback.

[0452] Step 5:

[0453] Based on the scoring results, the server selects the recipes to serve that day in order of highest score.

[0454] Step 6:

[0455] The server generates specific cooking instructions (instructions) based on the selected recipe.

[0456] Step 7:

[0457] The server sends the generated cooking instructions to the AI ​​robot, which then checks the instructions, prepares the necessary ingredients, and cooks the food.

[0458] Step 8:

[0459] Once cooking is complete, the AI ​​robot places the food on a serving tray and contacts the serving robot.

[0460] Step 9:

[0461] The server issues instructions to the delivery robot, which then sends instructions to deliver the finished dish to the designated table. The delivery robot uses a map of the restaurant to transport the dish along the optimal route and deliver it to the table.

[0462] Step 10:

[0463] After the meal, the device asks the user for feedback via a tablet installed on each table. The user operates the tablet to input their meal rating and comments.

[0464] Step 11:

[0465] The device sends the collected feedback data to the server, which stores the received feedback in a database and uses it as reference data for the next recipe generation.

[0466] Example 1

[0467] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0468] Conventional systems have been inefficient in the entire process from proposing dishes to cooking, serving, and collecting feedback, resulting in labor shortages and time-consuming tasks due to the high level of manual work. Furthermore, the lack of a mechanism for reflecting user preferences and past feedback has led to inconsistent food quality. The present invention aims to solve these problems and provide a system for providing efficient, high-quality food.

[0469] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0470] In this invention, the server

[0471] a means of collecting data;

[0472] A means for generating new proposals using a generative AI model; and

[0473] means for selecting from among the generated proposals based on evaluation criteria;

[0474] means for transmitting instructions based on the selected suggestions;

[0475] means for transporting the goods in accordance with the instructions;

[0476] a means of collecting feedback;

[0477] This will automate a series of processes and reflect user preferences and feedback, enabling efficient and high-quality food delivery.

[0478] "Means for collecting data" refers to means for capturing historical information, popular information, and user opinions from a database and making them available for the next stage of processing.

[0479] "Means for generating new proposals using generative AI models" refers to means for automatically creating new ideas and recipes using generative AI models based on collected data.

[0480] The "means for selecting from among the generated proposals based on evaluation criteria" refers to a means for evaluating the generated proposals based on inventory status, seasonality, and past opinions, and selecting the most suitable one.

[0481] The "means for transmitting instructions based on the selected suggestion" is a means for transmitting specific instructions to an appropriate device for automating cooking or other tasks in accordance with the selected suggestion.

[0482] "Means for transporting goods in accordance with the instructions" means the equipment or devices for properly transporting goods to the designated location in accordance with the instructions.

[0483] The "means for collecting feedback" is a means for collecting opinions and evaluations from users and storing them in the system so that they can be used when generating the next proposal.

[0484] This invention relates to a system that automates a series of processes: collecting data, generating new proposals using a generative AI model, making selections and instructions based on evaluation criteria, transporting goods according to the instructions, and collecting feedback. This system consists of three main elements: a server, a terminal, and a user.

[0485] Server Roles

[0486] The server is mainly responsible for processing data and sending instructions. Each of these methods will be explained in detail below.

[0487] How data is collected

[0488] The server collects past recipe data, popular ingredient data, and user feedback data from a database, which are then used in the process of utilizing the generative AI model.

[0489] A means of generating new proposals using generative AI models

[0490] The server creates prompts for the generative AI model based on the collected data and sends them to the model to generate multiple new recipe ideas. Examples of prompts include:

[0491] "Generate new recipes based on past popular ingredients and user feedback."

[0492] When the generative AI model receives this prompt, it analyzes the input data and generates new recipe ideas.

[0493] A means of selecting from the generated proposals based on evaluation criteria

[0494] The server evaluates the generated recipe ideas, using criteria such as ingredient availability, seasonality, and past user feedback. The recipe with the highest score is selected as the result of the evaluation.

[0495] A means of sending instructions based on the selected suggestion

[0496] The server creates detailed cooking instructions based on the selected recipe and sends them to the AI ​​robot, which then begins cooking according to the instructions.

[0497] A means of transporting goods based on that instruction

[0498] Once cooking is complete, the server sends serving instructions to the food delivery robot, including information on where to place the food and the designated table. The food delivery robot receives instructions from the server and transports and serves the food to the user's table.

[0499] Device Role

[0500] The terminal mainly handles the user interface and feedback collection.

[0501] A means of gathering feedback

[0502] After the meal, the device asks the user for feedback via a tablet placed on the table. The user enters their rating and comments on the food, and the device sends the data to the server. The server stores this feedback in a database and uses it as reference data when generating the next recipe.

[0503] User Roles

[0504] Users actually use the system and provide feedback on the food served.

[0505] As a concrete example, consider the case where the server analyzes from past data that "avocado cheese sandwiches" are popular, and then uses a new generative AI model to generate "avocado and grilled chicken tacos." This recipe idea received the highest score, so it is selected as the dish to be served that day. The server sends cooking instructions to the AI ​​robot, which follows those instructions to cook the dish. After cooking is complete, the server gives serving instructions to the food delivery robot, and the dish is brought to the user's table. After eating, the user enters feedback via their device, saying, "The avocado and grilled chicken tacos were very delicious." The server saves this feedback and uses it to generate the next recipe.

[0506] In this way, the system of the present invention not only realizes efficient and high-quality food provision, but also has the function of reflecting user preferences and feedback.

[0507] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0508] Program processing steps

[0509] Step 1:

[0510] The server collects past recipe data, popular ingredient data, and user feedback data from the database. The input for this data collection is past data from various databases and external data sources. The collected data is used in the next step.

[0511] Step 2:

[0512] The server creates a prompt for the generative AI model based on the collected data. The input here is the data collected in step 1, and the output is a text prompt to be sent to the generative AI model. A specific prompt generated is "Please generate a new recipe based on past popular ingredients and user feedback."

[0513] Step 3:

[0514] The server sends a prompt to the generative AI model to generate multiple new recipe ideas. The input is the prompt created in step 2, and the output is multiple new recipe ideas. The generative AI model processes and calculates data based on these recipe ideas to provide new recipe ideas.

[0515] Step 4:

[0516] The server evaluates the generated recipe ideas. Evaluation criteria include ingredient availability, seasonality, and past user feedback. The input is the recipe ideas generated in step 3 and the evaluation criteria data, and the output is an evaluation score. Specifically, each recipe is multiplied by the availability data and seasonality information, and the feedback data is weighted to calculate the score.

[0517] Step 5:

[0518] The server selects the recipe with the highest score. The input is the evaluation score calculated in step 4, and the output is the selected recipe. Here, an algorithm is used to automatically select the recipe with the highest score.

[0519] Step 6:

[0520] The server creates detailed cooking instructions based on the selected recipe and sends them to the AI ​​robot. The input is the selected recipe, and the output is data on the specific cooking instructions. The server breaks down the steps of the selected recipe, converts them into a format that the AI ​​robot can understand, and sends them.

[0521] Step 7:

[0522] The AI ​​robot receives the cooking instructions and starts cooking. The input is the detailed cooking instructions sent in step 6, and the output is the cooked food. The AI ​​robot follows the cooking instructions to process the ingredients, cook, and serve.

[0523] Step 8:

[0524] Once cooking is complete, the server sends serving instructions to the delivery robot. The input is the cooked food and serving instructions data, and the output is serving instructions to the delivery robot. The server combines the recipe and table information to calculate the optimal route and sends it to the delivery robot.

[0525] Step 9:

[0526] The delivery robot receives instructions from the server and transports and serves food to the user's table. The input is the delivery instruction data from the server, and the output is the food being served to the correct table. The delivery robot follows the instructions and accurately delivers the food to the user's table.

[0527] Step 10:

[0528] After the meal, the device asks the user for feedback via a tablet installed on the table. The input is the user's dining experience, and the output is feedback data. The device allows users to easily input ratings and comments via the tablet.

[0529] Step 11:

[0530] The user inputs ratings and comments on the meal. The input is the user's feedback, and the output is the rating data stored on the device.

[0531] Step 12:

[0532] The terminal sends the collected feedback to the server. The input is the user's evaluation data, and the output is the feedback sent to the server. The server stores this data in a database and uses it the next time it generates a recipe.

[0533] Through this series of processes, the system enables efficient and high-quality food delivery.

[0534] (Application example 1)

[0535] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0536] Current food delivery services often lack a wide variety of menu items, making it difficult for users to enjoy new dishes every day. Furthermore, the process from cooking to delivery is not streamlined, making it difficult to maintain a high level of service. Furthermore, there is no mechanism for incorporating user feedback into future service improvements.

[0537] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0538] In this invention, the server includes a generating means, a selecting means, an instructing means, a delivering means, and a feedback collecting means. This makes it possible to analyze past data to automatically generate new recipes every day and notify users of a different recipe each day. Furthermore, an efficient and high-quality food delivery service can be realized by having an AI robot provide cooking instructions and manage delivery. Furthermore, since feedback from users can be collected and reflected in future services, continuous improvement of the service can be expected.

[0539] The "means of generation" is a function that analyzes past data to automatically generate new recipes and notifies users of them on a daily basis.

[0540] The "means of selection" is a function that selects the optimal recipe from the multiple recipe ideas generated based on evaluation criteria and instructs the AI ​​robot on specific cooking steps.

[0541] The "means of giving instructions" is a function that sends detailed cooking instructions to the AI ​​robot based on the selected recipe, allowing it to cook appropriately.

[0542] The "delivery means" is a function that transports cooked food to a location designated by the user and manages the delivery progress in real time.

[0543] The "means of collecting feedback" refers to a function that allows users to input ratings and comments on the delivered food, and sends that data to the server, which uses it to generate the next recipe and improve the service.

[0544] A "server" is a central computer that processes data, sends instructions, and manages the entire system.

[0545] A "terminal" is a device that acts as a user interface and collects feedback from the user.

[0546] "Users" are individuals or corporations who actually use the food delivery service and provide feedback.

[0547] An "AI robot" is a machine equipped with artificial intelligence that automatically cooks based on instructions from a server.

[0548] A "delivery robot" is an automated delivery device designed to deliver cooked food to users.

[0549] The present invention relates to a food delivery system including a generating means, a selecting means, a directing means, a delivering means, and a feedback collecting means. How to implement the present invention will be specifically described below.

[0550] System Overview

[0551] The system consists of three main components: a server, a terminal, and a user. The server is primarily responsible for processing data and sending instructions, while the terminal provides the user interface and feedback collection. The user actually uses the service and provides feedback.

[0552] Means of generation

[0553] The first thing the server does is generate a new recipe for each day. To do this, the server uses the following data:

[0554] Past recipe data

[0555] Popular food data

[0556] User feedback data

[0557] By analyzing this data, the generative AI creates multiple new recipe ideas. During this process, the server automatically generates ingredient combinations and cooking methods to suggest innovative and unique dishes. For example, the following prompts can be used:

[0558] Generate a new recipe based on the following data:

[0559] Past recipe data: Avocado Cheese Sandwich, Tomato Soup, Grilled Steak

[0560] Popular ingredients: avocado, chicken, cheese

[0561] User Feedback Data:

[0562] Avocado and Cheese Sandwich: 4.5

[0563] Tomato soup: 4.0

[0564] Grilled Steak: 5.0

[0565] Means of selection

[0566] The server evaluates the generated recipes to select the recipe to serve that day. The server uses the following criteria to select the recipe:

[0567] Ingredient availability

[0568] seasonality

[0569] Past user feedback

[0570] The server scores each recipe based on these criteria, selects the highest-scoring recipe, and then provides detailed cooking instructions to the AI ​​robot based on the selected recipe.

[0571] Means of instruction

[0572] Based on the selected recipe, the server instructs the AI ​​robot on the cooking steps. Specifically, the server generates detailed cooking instructions and sends them to the AI ​​robot, which then cooks the food according to them.

[0573] Means of delivery

[0574] Once cooking is complete, the server issues delivery instructions to the delivery robot. Specifically, the server sends the delivery location and address information to the delivery robot, and the delivery robot then transports and delivers the food via the optimal route. Users can check the delivery progress in real time through the application.

[0575] A means of gathering feedback

[0576] After delivery, the user can enter their rating and comments using a smartphone application. This feedback is sent from the device to the server, which stores the data and uses it as reference data when generating the next recipe.

[0577] Specific examples

[0578] For example, the server analyzes past data to determine that "avocado cheese sandwiches" are popular, and generates a new recipe: "avocado and grilled chicken tacos." This recipe idea receives the highest score, so it is decided to serve it that day. The server sends specific cooking instructions to the AI ​​robot, which then cooks the food according to the recipe. After cooking, the server gives delivery instructions to the delivery robot, and the food is delivered to the location specified by the user. After delivery, the user enters feedback through the application, saying, "The avocado and grilled chicken tacos were very delicious." The server saves this feedback and uses it to generate future recipes.

[0579] As a result, this system can provide new dishes every day, realize an efficient and high-quality food delivery service, and always provide high-quality service.

[0580] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0581] Step 1:

[0582] Data collection and analysis

[0583] The server collects past recipe data, popular ingredient data, and user feedback data. Using this data as input, the generative AI model begins analysis to automatically generate new recipes. Specifically, it analyzes ingredient combinations and cooking methods to generate recipe suggestions that take into account novelty and user preferences.

[0584] input:

[0585] Past recipe data

[0586] Popular food data

[0587] User feedback data

[0588] output:

[0589] Newly generated recipe ideas

[0590] Step 2:

[0591] Recipe Selection

[0592] The server scores the generated recipe ideas based on evaluation criteria and selects the recipe to be served that day. Each recipe is scored based on ingredient availability, seasonality, and past user feedback. The recipe with the highest score is then selected.

[0593] input:

[0594] Newly generated recipe ideas

[0595] Ingredient inventory data

[0596] Seasonal Data

[0597] User feedback data

[0598] output:

[0599] Selected Recipes

[0600] Step 3:

[0601] Cooking instructions

[0602] The server sends detailed cooking instructions to the AI ​​robot based on the selected recipe. Specifically, it instructs the AI ​​robot on which ingredients to use, in what order, and what cooking method to use. Based on these instructions, the AI ​​robot begins cooking.

[0603] input:

[0604] Selected Recipes

[0605] Detailed cooking instructions

[0606] output:

[0607] Send cooking instructions

[0608] Step 4:

[0609] Cooking and delivery preparation

[0610] The AI ​​robot prepares the food according to the cooking instructions received from the server. At the same time, the server sends delivery preparation instructions to the delivery robot, which receives information about the food pick-up location and the user's designated address.

[0611] input:

[0612] Cooking instructions

[0613] Delivery Information

[0614] output:

[0615] Start cooking

[0616] Send delivery preparation instructions

[0617] Step 5:

[0618] Delivery and progress tracking

[0619] Once the food is ready, the server sends instructions to the delivery robot to pick it up. The delivery robot then takes the optimal route and delivers the food to the location specified by the user. Users can check the delivery progress in real time through a smartphone application.

[0620] input:

[0621] The finished dish

[0622] Delivery instructions

[0623] output:

[0624] Food delivery

[0625] Delivery progress information

[0626] Step 6:

[0627] Gathering feedback

[0628] After receiving the food, the user can enter their rating and comments using a smartphone application. The feedback is sent from the device to the server, which stores this data and uses it as reference data when generating the next recipe.

[0629] input:

[0630] User Feedback

[0631] output:

[0632] Feedback Data Storage

[0633] In this way, the server, terminals, and users work together to realize an efficient and high-quality food delivery service. By utilizing generative AI models, users can enjoy new dishes every day, and the service can be expected to continuously improve.

[0634] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0635] The present invention is specifically embodied by a system including a generating means, a selecting means, an instructing means, a serving means, a feedback collecting means, and an emotion engine that recognizes the emotion of a user. An embodiment of the system of the present invention will be described below with specific examples.

[0636] System Overview

[0637] The system consists of three main components: a server, a terminal, and a user, as well as an emotion engine. The server is primarily responsible for data processing and instruction transmission, while the terminal provides the user interface and feedback collection, and the emotion engine analyzes user emotions. Users actually use the service and provide feedback and emotion data.

[0638] Means of generation

[0639] This is the generation method the server uses to generate new recipes each day. The server uses the following data:

[0640] Past recipe data

[0641] Popular food data

[0642] User Feedback Data

[0643] Emotion data from emotion engine

[0644] By analyzing this data, the generative AI creates multiple new recipe ideas. During this process, the server automatically generates ingredient combinations and cooking methods, proposing innovative and unique dishes.

[0645] Means of selection

[0646] The server evaluates the generated recipes to select the recipe to serve that day. The server uses the following criteria to select the recipe:

[0647] Ingredient availability

[0648] seasonality

[0649] Past feedback including user emotional data

[0650] The server scores each recipe based on these criteria and selects the recipe with the highest score.

[0651] Means of instruction

[0652] Based on the selected recipe, the server instructs the AI ​​robot on the cooking steps. Specifically, the server generates detailed cooking instructions and sends them to the AI ​​robot, which then cooks the food according to them.

[0653] Means of serving food

[0654] Once cooking is complete, the server issues delivery instructions to the delivery robot. Specifically, the server sends information about the food's location and the designated table to the delivery robot, and the delivery robot then transports and delivers the food via the optimal route.

[0655] A means of gathering feedback

[0656] After the meal, the device asks the user for feedback via a tablet placed on the table. The user enters their meal rating and comments, and the device sends the data to the server. The server stores this feedback in a database and uses it as reference data for the next recipe generation.

[0657] Emotion Engine

[0658] The emotion engine is particularly important. During and after the meal, the emotion engine analyzes the user's facial expressions, voice, gestures, etc. using the device's built-in camera and voice recognition system. It then compiles detailed data on how the user felt about the food and stores it as feedback. This emotion data is taken into consideration when generating the next recipe.

[0659] Specific examples

[0660] For example, the server analyzes past data to determine that "avocado cheese sandwiches" are popular, and generates a new recipe: "avocado and grilled chicken tacos." This recipe idea receives the highest score, so it is decided to serve it that day. The server sends specific cooking instructions to the AI ​​robot, which then cooks the food according to the recipe. After cooking, the server gives serving instructions to the food delivery robot, and the food is brought to the user's table. During the meal, the emotion engine analyzes the user's facial expressions and voice, and the user later inputs feedback, such as "The avocado and grilled chicken tacos were very delicious." The server saves this feedback and emotion data and uses it to generate future recipes.

[0661] As a result, this system can provide new dishes every day, solve the problem of labor shortages, and always provide high-quality service and a cooking experience based on the user's emotions.

[0662] The processing flow will be explained below.

[0663] Step 1:

[0664] The server starts the generation AI at the start of business every day. The server retrieves past recipe data, popular ingredient data, user feedback data, and emotion data from the emotion engine from its internal database.

[0665] Step 2:

[0666] The server inputs the acquired data into the generation AI, which analyzes the data and generates new recipes. The generation AI generates multiple new recipe ideas based on "randomly selected combinations of ingredients" and "combinations of cooking methods."

[0667] Step 3:

[0668] The server saves the generated recipe plan and the list of ingredients and cooking utensils required in the database.

[0669] Step 4:

[0670] The server evaluates the stored recipe ideas and assigns a score to each recipe based on past feedback, including ingredient availability, seasonality, and user sentiment data.

[0671] Step 5:

[0672] Based on the scoring results, the server selects the recipes to serve that day in order of highest score.

[0673] Step 6:

[0674] The server generates specific cooking instructions (instructions) based on the selected recipe.

[0675] Step 7:

[0676] The server sends the generated cooking instructions to the AI ​​robot, which then checks the instructions, prepares the necessary ingredients, and cooks the food.

[0677] Step 8:

[0678] Once cooking is complete, the AI ​​robot places the food on a serving tray and contacts the serving robot.

[0679] Step 9:

[0680] The server issues instructions to the delivery robot, instructing it to deliver the finished dish to the designated table. The delivery robot uses a map of the restaurant to transport the dish along the optimal route and deliver it to the table.

[0681] Step 10:

[0682] During and after the meal, the device uses a camera and microphone installed on the table to analyze the user's facial expressions, voice, gestures, etc., and the emotion engine saves the analysis results as feedback.

[0683] Step 11:

[0684] After eating, the device asks the user for feedback, and the user operates the tablet to input their meal rating and comments.

[0685] Step 12:

[0686] The device sends the collected feedback data and the emotion data analyzed by the emotion engine to the server, which stores this data in a database and uses it as reference data for the next recipe generation.

[0687] This allows the entire system to work together, offering new dishes every day while collecting and analyzing user feedback based on emotions, allowing for continuous improvement in the quality of service.

[0688] Example 2

[0689] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0690] Conventional recipe suggestion systems and cooking services have difficulty providing optimal recipes based on users' tastes and preferences, and have also been unable to provide services that take users' emotions into consideration.In addition, labor shortages have made it difficult to operate efficiently in cooking and serving food.

[0691] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for generating a new recipe using a generative AI model, a means for selecting a recipe to be provided from the generated recipes based on evaluation criteria, a means for sending cooking instructions to a cooking device based on the selected recipe, a means for sending serving instructions to a food serving device after cooking is completed, a means for collecting evaluations from the user after eating, and a means for collecting emotion data by analyzing the user's facial expressions and voice. This enables the provision of optimal recipes that take into account the user's preferences and emotions, and efficient cooking and food serving operations.

[0692] A "generative AI model" is an artificial intelligence algorithm that analyzes past data and automatically generates new recipes.

[0693] "Evaluation criteria" are the criteria used to select which recipes to offer from the generated recipe ideas. Examples include ingredient availability, seasonality, and past feedback including user emotional data.

[0694] A "cooking device" is an automated mechanical device that cooks food according to cooking instructions received from the server.

[0695] A "serving device" is an automated machine that transports food after cooking is complete and serves it to a designated location based on instructions from the server.

[0696] "User feedback data" is information provided by the user as ratings and comments after eating, and is used as reference for creating the next recipe.

[0697] "Emotion data" is information about emotions obtained by analyzing the user's facial expressions, voice, gestures, etc.

[0698] A "server" is a central computer system that processes data, sends instructions, generates and selects recipes, processes feedback, etc.

[0699] This system generates new recipes using a generative AI model, selects recipes based on evaluation criteria, and sends instructions to cooking devices and serving devices to provide meals based on the user's preferences and emotions. This system is composed of a server, a terminal, a user, and an emotion engine.

[0700] The server processes and calculates data using the following hardware and software:

[0701] The hardware and software used includes:

[0702] Hardware: High-performance computer servers, database servers, and network equipment

[0703] Software: Generative AI models, database management systems, sentiment analysis engines

[0704] Recipe Generation

[0705] The server generates new recipes using a generative AI model. Specifically, it collects and analyzes past recipe data, popular ingredient data, user feedback data, and sentiment data to create multiple new recipe suggestions. An example prompt is as follows:

[0706] "Generate new recipes based on popular recipes from the past week and user feedback"

[0707] Recipe Selection

[0708] The server selects the best recipe from the multiple recipe ideas generated based on evaluation criteria, including ingredient availability, seasonality, and past feedback including user sentiment data. The server assigns a score to each recipe based on these criteria and selects the recipe with the highest score.

[0709] cooking instructions

[0710] The server sends cooking instructions to the cooking device based on the selected recipe. Specifically, it sends the generated detailed cooking instructions to the AI ​​robot, which then cooks the food according to the instructions.

[0711] Serving instructions

[0712] Once cooking is complete, the server sends instructions to the serving device. Specifically, the server sends information about the food placement location and the designated table to the serving robot, and the serving robot then transports and serves the food along the optimal route.

[0713] Feedback collection

[0714] After the meal, the device asks the user for feedback. The user enters their meal rating and comments on a tablet placed on the table, and the device sends the data to the server. The server stores this feedback in a database and uses it as reference data for the next recipe generation.

[0715] Emotion analysis

[0716] Emotion analysis is particularly important. During and after a meal, the emotion engine analyzes the user's facial expressions, voice, and gestures using the device's built-in camera and voice recognition system. The analyzed emotion data is converted into detailed data and saved as feedback. This emotion data is taken into consideration when generating the next recipe.

[0717] Specific examples

[0718] For example, the server analyzes past data to determine that "avocado cheese sandwiches" are popular, and generates a new recipe: "avocado and grilled chicken tacos." This recipe idea receives the highest score, so it is decided to serve it that day. The server sends specific cooking instructions to the AI ​​robot, which then cooks the food according to the recipe. After cooking, the server gives serving instructions to the food delivery robot, and the food is brought to the user's table. During the meal, the emotion engine analyzes the user's facial expressions and voice, and the user later inputs feedback, such as "The avocado and grilled chicken tacos were very delicious." The server saves this feedback and emotion data and uses it to generate future recipes.

[0719] Through the above processing, the system can propose and serve new dishes that take into account the user's preferences and emotions, enabling efficient cooking and serving.

[0720] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0721] Step 1: Data collection

[0722] The server collects past recipe data, popular ingredient data, user feedback data, and sentiment data from a database. This data serves as input data for generating new recipes using a generative AI model. The server accesses the database using SQL queries to extract the necessary information. Specifically, it executes the query "Get recipe data from the past week" and retrieves the results from the database. The output is a set of collected data.

[0723] Step 2: Recipe generation

[0724] The server inputs the collected data into the generative AI model to generate new recipe suggestions. Specifically, the server inputs a prompt to the generative AI model: "Generate a new recipe based on the popular recipes from the past week and user feedback." The generative AI model generates multiple new recipe suggestions based on this prompt. The input is the collected data set and the prompt, and the output is the generated multiple new recipe suggestions.

[0725] Step 3: Recipe Selection

[0726] The server evaluates the generated recipe ideas to select the most appropriate one. Evaluation criteria include ingredient availability, seasonality, and past feedback including user sentiment data. The server uses these criteria to assign a score to each recipe and selects the recipe with the highest score. For example, if the server selects "Avocado and Grilled Chicken Tacos," it indicates that the recipe received a high score. The input is the generated recipe ideas and evaluation criteria, and the output is the selected recipe.

[0727] Step 4: Cooking Instructions

[0728] The server sends cooking instructions to the cooking device based on the selected recipe. The server then sends the generated detailed cooking instructions to the AI ​​robot, which then follows the instructions to cook. Specifically, the server sends specific instructions to the AI ​​robot, such as "Slice the avocado and prepare the grilled chicken." The input is the selected recipe, and the output is the cooking instructions sent to the cooking device.

[0729] Step 5: Serving instructions

[0730] Once cooking is complete, the server sends serving instructions to the food delivery device. The server sends information about the food's location and the specified table to the food delivery robot, which then transports and delivers the food along the optimal route. For example, the server sends the instruction "Deliver avocado and grilled chicken tacos to table number 5" to the food delivery robot. The input is the completed cooking information and the target table information, and the output is the serving instructions sent to the food delivery device.

[0731] Step 6: Gather feedback

[0732] After eating, the device provides an interface to ask the user for feedback. The user inputs their meal rating and comments using a tablet placed on the table, and the device sends the data to the server. The server stores this feedback in a database and uses it as a reference when generating the next recipe. Specifically, the user inputs a rating such as "The tacos were delicious," and this is sent to the server. The input is the feedback provided by the user, and the output is the feedback data stored in the database.

[0733] Step 7: Sentiment Analysis

[0734] The device analyzes the user's emotions during and after the meal. The device's camera and voice recognition system record the user's facial expressions and voice, and the emotion engine analyzes the data. The analysis results are sent to the server and saved as feedback. For example, if a user smiles and says "delicious," this is converted into data as a positive emotion. The input is the user's facial expression and voice data acquired from the device, and the output is emotion data saved on the server.

[0735] (Application example 2)

[0736] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0737] Modern food delivery services often fail to fully utilize user preferences, past order history, and real-time sentiment data, resulting in low user satisfaction. Furthermore, the lack of automation in cooking and serving food leads to labor shortages and reduced efficiency. This results in inconsistent user experience. The purpose of this invention is to solve these issues and provide a high-quality food delivery service.

[0738] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a generating means, a selecting means, an instructing means, a serving means, a feedback collecting means, an emotion engine that recognizes the user's emotions, and a means for proposing new dishes by taking into account the user's past order data, popular ingredient data, and emotion data. This makes it possible to provide personalized dishes based on the user's preferences and emotion data, and furthermore, by automating cooking and serving, it is possible to achieve improved efficiency and consistent quality.

[0739] The "generating means" is a device or program that has the function of analyzing past data and automatically generating new recipes.

[0740] The "selecting means" is a device or program that has the function of selecting a recipe to provide from the generated recipe plans based on evaluation criteria.

[0741] The "means for instructing" is a device or program that has the function of instructing related equipment or robots on cooking procedures based on the selected recipe.

[0742] The "serving means" refers to a device or program that has the function of transporting and serving the cooked food to a designated location or table.

[0743] The "means for collecting feedback" is a device or program that has the function of collecting and storing feedback data from users.

[0744] An "emotion engine" is a device or program that has the function of analyzing a user's facial expressions, voice, gestures, etc. and recognizing emotions.

[0745] "User's past order data" refers to historical information such as dishes that the user has ordered in the past and their ratings.

[0746] "Popular food data" refers to data that includes information about food that is highly popular during a specific period or in a specific region.

[0747] "Emotion data" refers to data that indicates information about a user's emotions analyzed using an emotion engine.

[0748] The "means for suggesting new dishes" is a device or program that has the function of suggesting new dishes personalized to the user based on the user's past order data, popular ingredient data, and emotional data.

[0749] MODE FOR CARRYING OUT THE INVENTION

[0750] System Overview

[0751] The system consists of three main components: a server, a terminal, and a user, as well as an emotion engine. The server is primarily responsible for data processing and instruction transmission, while the terminal provides the user interface and feedback collection, and the emotion engine analyzes user emotions. Users actually use the service and provide feedback and emotion data.

[0752] Server Processing

[0753] 1. Data Collection:

[0754] The server collects and stores the user's past order data, popular ingredients data, and emotional data, including cooking history, ordering ratings, and the user's facial expressions and voice data.

[0755] 2. Means of generation:

[0756] The server analyzes the collected data and automatically generates new recipes using a generative AI model, taking into account past order data and popular ingredients.

[0757] 3. Choose your method:

[0758] The server evaluates the generated recipe ideas based on inventory, seasonality, and past feedback data, assigning a score to each recipe idea, and the recipe with the highest score is selected.

[0759] 4. Means of instruction:

[0760] Based on the selected recipe, the server instructs the cooking robot on specific cooking steps, which causes the cooking robot to automatically start cooking.

[0761] 5. Means of serving:

[0762] After cooking is complete, the server instructs the serving robot to transport and serve the food to the designated table.

[0763] 6. Feedback Collection:

[0764] The server collects feedback from users through their terminals, allowing users to input their ratings and comments on the food they have been served.

[0765] Emotion engine processing

[0766] The emotion engine uses the device's built-in camera and microphone to analyze the user's facial expressions and voice data and generate emotion data. For example, it evaluates the user's level of satisfaction from their facial expressions while they are eating and sends this data to the server.

[0767] Terminal handling

[0768] The terminal is a device such as a tablet placed on a table and used by the user as an interface. The terminal not only collects feedback but also acquires emotional data from the user.

[0769] Specific examples

[0770] The server analyzes past data to determine that "Spicy Chicken Curry" is popular, and generates a new recipe called "Spicy Chicken Curry Wrap." This recipe idea received the highest score, so it is decided to serve it that day. The server sends specific cooking instructions to the cooking robot, and after cooking, a serving robot brings the food to the user. While eating, the device's camera analyzes the user's facial expressions, and an emotion engine evaluates their level of satisfaction. The user then inputs feedback, such as "The spicy chicken curry wrap was very delicious." This data is used to generate the next recipe.

[0771] Example prompts for generative AI models

[0772] "Suggest new recipes based on the user's past order data, popular ingredients, and sentiment data. For example, if the user has previously ordered 'Spicy Chicken Curry,' use that data to generate a new 'Spicy Chicken Curry Wrap.'"

[0773] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0774] Step 1:

[0775] The server collects users' past order data, popular ingredient data, and emotional data. This includes cooking history, ordering ratings, and the user's facial and voice data. The server reads this data from the database and prepares it for analysis. It uses past order data, popular ingredient data, and emotional data as inputs and generates an integrated dataset that can be used for analysis as output.

[0776] Step 2:

[0777] The server uses the generated means to analyze the collected data and automatically generate new recipes using a generative AI model. This process also takes into account the user's past preferences and emotional data. The integrated dataset is used as input, and multiple new recipe suggestions are generated as output. Specifically, the server sends a prompt to the generative AI model and receives the returned recipe suggestions.

[0778] Step 3:

[0779] The server evaluates the generated recipe ideas using a method selected by the server. Evaluation criteria include inventory status, seasonality, and past feedback data. The generated recipe ideas and evaluation criteria data are used as input, and the recipe with the highest score is selected as output. Specifically, the server calculates a score based on the evaluation criteria for each recipe idea, and selects the recipe with the highest score.

[0780] Step 4:

[0781] Using the means instructed by the server, the cooking robot is instructed on specific cooking steps based on the selected recipe. The selected recipe is used as input, and commands including the cooking steps are generated and sent as output. Specifically, the cooking steps are extracted from the recipe data and instructions are sent to the cooking robot.

[0782] Step 5:

[0783] The server uses the means of serving to instruct the serving robot to transport and serve the cooked food to the specified table. It uses the cooking completion notification and serving information as input, and generates and sends serving instructions as output. Specifically, it receives the cooking completion notification from the cooking robot and sends the food location and table information to the serving robot.

[0784] Step 6:

[0785] The device collects feedback from users. After collecting the feedback, the server stores the data. The system uses the ratings and comments entered by users on the tablet device as input, generates feedback data as output, and stores it in a database. Specifically, the device collects the feedback information entered by users on the tablet device and sends it to the server.

[0786] Step 7:

[0787] The device uses an emotion engine to analyze the user's facial expression and voice data and generate emotion data. The device uses the user's facial expression and voice data acquired from a camera or microphone as input, and generates and saves emotion data as output. Specifically, the device captures the user's facial expression and voice with a camera or microphone during and after a meal, and the emotion engine analyzes this to generate emotion data, which is then sent to the server.

[0788] Step 8:

[0789] The server saves the collected feedback and emotion data and uses it for the next recipe generation. The feedback and emotion data are used as input, and reference data for the next recipe generation is generated and saved as output. Specifically, the server stores the collected data in a database and converts it into a usable format for the next analysis.

[0790] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0791] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0792] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0793] [Third embodiment]

[0794] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0795] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0796] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0797] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0798] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0799] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0800] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0801] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0802] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0803] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0804] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0805] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0806] The present invention is specifically embodied in a system including a generating means, a selecting means, an instructing means, a serving means, and a feedback collecting means. How the system of the present invention is implemented will be described below with specific examples.

[0807] System Overview

[0808] The system consists of three main components: a server, a terminal, and a user. The server is primarily responsible for processing data and sending instructions, while the terminal provides the user interface and feedback collection. The user actually uses the service and provides feedback.

[0809] Means of generation

[0810] The first thing the server does is generate a new recipe for each day. To do this, the server uses the following data:

[0811] Past recipe data

[0812] Popular food data

[0813] User feedback data

[0814] By analyzing this data, the generative AI creates multiple new recipe ideas. During this process, the server automatically generates ingredient combinations and cooking methods, proposing innovative and unique dishes.

[0815] Means of selection

[0816] The server evaluates the generated recipes to select the recipe to serve that day. The server uses the following criteria to select the recipe:

[0817] Ingredient availability

[0818] seasonality

[0819] Past user feedback

[0820] The server scores each recipe based on these criteria and selects the recipe with the highest score.

[0821] Means of instruction

[0822] Based on the selected recipe, the server instructs the AI ​​robot on the cooking steps. Specifically, the server generates detailed cooking instructions and sends them to the AI ​​robot, which then cooks the food according to them.

[0823] Means of serving food

[0824] Once cooking is complete, the server issues delivery instructions to the delivery robot. Specifically, the server sends information about the food's location and the designated table to the delivery robot, and the delivery robot then transports and delivers the food via the optimal route.

[0825] A means of gathering feedback

[0826] After the meal, the device asks the user for feedback via a tablet placed on the table. The user enters their meal rating and comments, and the device sends the data to the server. The server stores this feedback in a database and uses it as reference data for the next recipe generation.

[0827] Specific examples

[0828] For example, the server analyzes past data to determine that "avocado cheese sandwiches" are popular, and generates a new recipe: "avocado and grilled chicken tacos." This recipe idea receives the highest score, so it is decided to serve it that day. The server sends specific cooking instructions to the AI ​​robot, which then cooks the food according to the recipe. After cooking, the server gives serving instructions to the food delivery robot, and the food is brought to the user's table. After eating, the user enters feedback via their device, saying, "The avocado and grilled chicken tacos were very delicious." The server saves this feedback and uses it to generate future recipes.

[0829] As a result, this system can provide new dishes every day, solve the problem of labor shortages, and always provide high-quality service.

[0830] The processing flow will be explained below.

[0831] Step 1:

[0832] The server starts the generation AI at the start of business each day, retrieving past recipe data, popular ingredients data, and user feedback data from its internal database.

[0833] Step 2:

[0834] The server inputs the acquired data into the generation AI, which analyzes the data and generates new recipes. The generation AI generates multiple new recipe ideas based on "randomly selected combinations of ingredients" and "combinations of cooking methods."

[0835] Step 3:

[0836] The server saves the generated recipe plan and the list of ingredients and cooking utensils required in the database.

[0837] Step 4:

[0838] The server evaluates multiple saved recipe ideas and assigns a score to each recipe, taking into account ingredient availability, seasonality, and past user feedback.

[0839] Step 5:

[0840] Based on the scoring results, the server selects the recipes to serve that day in order of highest score.

[0841] Step 6:

[0842] The server generates specific cooking instructions (instructions) based on the selected recipe.

[0843] Step 7:

[0844] The server sends the generated cooking instructions to the AI ​​robot, which then checks the instructions, prepares the necessary ingredients, and cooks the food.

[0845] Step 8:

[0846] Once cooking is complete, the AI ​​robot places the food on a serving tray and contacts the serving robot.

[0847] Step 9:

[0848] The server issues instructions to the delivery robot, which then sends instructions to deliver the finished dish to the designated table. The delivery robot uses a map of the restaurant to transport the dish along the optimal route and deliver it to the table.

[0849] Step 10:

[0850] After the meal, the device asks the user for feedback via a tablet installed on each table. The user operates the tablet to input their meal rating and comments.

[0851] Step 11:

[0852] The device sends the collected feedback data to the server, which stores the received feedback in a database and uses it as reference data for the next recipe generation.

[0853] Example 1

[0854] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0855] Conventional systems have been inefficient in the entire process from proposing dishes to cooking, serving, and collecting feedback, resulting in labor shortages and time-consuming tasks due to the high level of manual work. Furthermore, the lack of a mechanism for reflecting user preferences and past feedback has led to inconsistent food quality. The present invention aims to solve these problems and provide a system for providing efficient, high-quality food.

[0856] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0857] In this invention, the server

[0858] a means of collecting data;

[0859] A means for generating new proposals using a generative AI model; and

[0860] means for selecting from among the generated proposals based on evaluation criteria;

[0861] means for transmitting instructions based on the selected suggestions;

[0862] means for transporting the goods in accordance with the instructions;

[0863] a means of collecting feedback;

[0864] This will automate a series of processes and reflect user preferences and feedback, enabling efficient and high-quality food delivery.

[0865] "Means for collecting data" refers to means for capturing historical information, popular information, and user opinions from a database and making them available for the next stage of processing.

[0866] "Means for generating new proposals using generative AI models" refers to means for automatically creating new ideas and recipes using generative AI models based on collected data.

[0867] The "means for selecting from among the generated proposals based on evaluation criteria" refers to a means for evaluating the generated proposals based on inventory status, seasonality, and past opinions, and selecting the most suitable one.

[0868] The "means for transmitting instructions based on the selected suggestion" is a means for transmitting specific instructions to an appropriate device for automating cooking or other tasks in accordance with the selected suggestion.

[0869] "Means for transporting goods in accordance with the instructions" means the equipment or devices for properly transporting goods to the designated location in accordance with the instructions.

[0870] The "means for collecting feedback" is a means for collecting opinions and evaluations from users and storing them in the system so that they can be used when generating the next proposal.

[0871] This invention relates to a system that automates a series of processes: collecting data, generating new proposals using a generative AI model, making selections and instructions based on evaluation criteria, transporting goods according to the instructions, and collecting feedback. This system consists of three main elements: a server, a terminal, and a user.

[0872] Server Roles

[0873] The server is mainly responsible for processing data and sending instructions. Each of these methods will be explained in detail below.

[0874] How data is collected

[0875] The server collects past recipe data, popular ingredient data, and user feedback data from a database, which are then used in the process of utilizing the generative AI model.

[0876] A means of generating new proposals using generative AI models

[0877] The server creates prompts for the generative AI model based on the collected data and sends them to the model to generate multiple new recipe ideas. Examples of prompts include:

[0878] "Generate new recipes based on past popular ingredients and user feedback."

[0879] When the generative AI model receives this prompt, it analyzes the input data and generates new recipe ideas.

[0880] A means of selecting from the generated proposals based on evaluation criteria

[0881] The server evaluates the generated recipe ideas, using criteria such as ingredient availability, seasonality, and past user feedback. The recipe with the highest score is selected as the result of the evaluation.

[0882] A means of sending instructions based on the selected suggestion

[0883] The server creates detailed cooking instructions based on the selected recipe and sends them to the AI ​​robot, which then begins cooking according to the instructions.

[0884] A means of transporting goods based on that instruction

[0885] Once cooking is complete, the server sends serving instructions to the food delivery robot, including information on where to place the food and the designated table. The food delivery robot receives instructions from the server and transports and serves the food to the user's table.

[0886] Device Role

[0887] The terminal mainly handles the user interface and feedback collection.

[0888] A means of gathering feedback

[0889] After the meal, the device asks the user for feedback via a tablet placed on the table. The user enters their rating and comments on the food, and the device sends the data to the server. The server stores this feedback in a database and uses it as reference data when generating the next recipe.

[0890] User Roles

[0891] Users actually use the system and provide feedback on the food served.

[0892] As a concrete example, consider the case where the server analyzes from past data that "avocado cheese sandwiches" are popular, and then uses a new generative AI model to generate "avocado and grilled chicken tacos." This recipe idea received the highest score, so it is selected as the dish to be served that day. The server sends cooking instructions to the AI ​​robot, which follows those instructions to cook the dish. After cooking is complete, the server gives serving instructions to the food delivery robot, and the dish is brought to the user's table. After eating, the user enters feedback via their device, saying, "The avocado and grilled chicken tacos were very delicious." The server saves this feedback and uses it to generate the next recipe.

[0893] In this way, the system of the present invention not only realizes efficient and high-quality food provision, but also has the function of reflecting user preferences and feedback.

[0894] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0895] Program processing steps

[0896] Step 1:

[0897] The server collects past recipe data, popular ingredient data, and user feedback data from the database. The input for this data collection is past data from various databases and external data sources. The collected data is used in the next step.

[0898] Step 2:

[0899] The server creates a prompt for the generative AI model based on the collected data. The input here is the data collected in step 1, and the output is a text prompt to be sent to the generative AI model. A specific prompt generated is "Please generate a new recipe based on past popular ingredients and user feedback."

[0900] Step 3:

[0901] The server sends a prompt to the generative AI model to generate multiple new recipe ideas. The input is the prompt created in step 2, and the output is multiple new recipe ideas. The generative AI model processes and calculates data based on these recipe ideas to provide new recipe ideas.

[0902] Step 4:

[0903] The server evaluates the generated recipe ideas. Evaluation criteria include ingredient availability, seasonality, and past user feedback. The input is the recipe ideas generated in step 3 and the evaluation criteria data, and the output is an evaluation score. Specifically, each recipe is multiplied by the availability data and seasonality information, and the feedback data is weighted to calculate the score.

[0904] Step 5:

[0905] The server selects the recipe with the highest score. The input is the evaluation score calculated in step 4, and the output is the selected recipe. Here, an algorithm is used to automatically select the recipe with the highest score.

[0906] Step 6:

[0907] The server creates detailed cooking instructions based on the selected recipe and sends them to the AI ​​robot. The input is the selected recipe, and the output is data on the specific cooking instructions. The server breaks down the steps of the selected recipe, converts them into a format that the AI ​​robot can understand, and sends them.

[0908] Step 7:

[0909] The AI ​​robot receives the cooking instructions and starts cooking. The input is the detailed cooking instructions sent in step 6, and the output is the cooked food. The AI ​​robot follows the cooking instructions to process the ingredients, cook, and serve.

[0910] Step 8:

[0911] Once cooking is complete, the server sends serving instructions to the delivery robot. The input is the cooked food and serving instructions data, and the output is serving instructions to the delivery robot. The server combines the recipe and table information to calculate the optimal route and sends it to the delivery robot.

[0912] Step 9:

[0913] The delivery robot receives instructions from the server and transports and serves food to the user's table. The input is the delivery instruction data from the server, and the output is the food being served to the correct table. The delivery robot follows the instructions and accurately delivers the food to the user's table.

[0914] Step 10:

[0915] After the meal, the device asks the user for feedback via a tablet installed on the table. The input is the user's dining experience, and the output is feedback data. The device allows users to easily input ratings and comments via the tablet.

[0916] Step 11:

[0917] The user inputs ratings and comments on the meal. The input is the user's feedback, and the output is the rating data stored on the device.

[0918] Step 12:

[0919] The terminal sends the collected feedback to the server. The input is the user's evaluation data, and the output is the feedback sent to the server. The server stores this data in a database and uses it the next time it generates a recipe.

[0920] Through this series of processes, the system enables efficient and high-quality food delivery.

[0921] (Application example 1)

[0922] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0923] Current food delivery services often lack a wide variety of menu items, making it difficult for users to enjoy new dishes every day. Furthermore, the process from cooking to delivery is not streamlined, making it difficult to maintain a high level of service. Furthermore, there is no mechanism for incorporating user feedback into future service improvements.

[0924] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0925] In this invention, the server includes a generating means, a selecting means, an instructing means, a delivering means, and a feedback collecting means. This makes it possible to analyze past data to automatically generate new recipes every day and notify users of a different recipe each day. Furthermore, an efficient and high-quality food delivery service can be realized by having an AI robot provide cooking instructions and manage delivery. Furthermore, since feedback from users can be collected and reflected in future services, continuous improvement of the service can be expected.

[0926] The "means of generation" is a function that analyzes past data to automatically generate new recipes and notifies users of them on a daily basis.

[0927] The "means of selection" is a function that selects the optimal recipe from the multiple recipe ideas generated based on evaluation criteria and instructs the AI ​​robot on specific cooking steps.

[0928] The "means of giving instructions" is a function that sends detailed cooking instructions to the AI ​​robot based on the selected recipe, allowing it to cook appropriately.

[0929] The "delivery means" is a function that transports cooked food to a location designated by the user and manages the delivery progress in real time.

[0930] The "means of collecting feedback" refers to a function that allows users to input ratings and comments on the delivered food, and sends that data to the server, which uses it to generate the next recipe and improve the service.

[0931] A "server" is a central computer that processes data, sends instructions, and manages the entire system.

[0932] A "terminal" is a device that acts as a user interface and collects feedback from the user.

[0933] "Users" are individuals or corporations who actually use the food delivery service and provide feedback.

[0934] An "AI robot" is a machine equipped with artificial intelligence that automatically cooks based on instructions from a server.

[0935] A "delivery robot" is an automated delivery device designed to deliver cooked food to users.

[0936] The present invention relates to a food delivery system including a generating means, a selecting means, a directing means, a delivering means, and a feedback collecting means. How to implement the present invention will be specifically described below.

[0937] System Overview

[0938] The system consists of three main components: a server, a terminal, and a user. The server is primarily responsible for processing data and sending instructions, while the terminal provides the user interface and feedback collection. The user actually uses the service and provides feedback.

[0939] Means of generation

[0940] The first thing the server does is generate a new recipe for each day. To do this, the server uses the following data:

[0941] Past recipe data

[0942] Popular food data

[0943] User feedback data

[0944] By analyzing this data, the generative AI creates multiple new recipe ideas. During this process, the server automatically generates ingredient combinations and cooking methods to suggest innovative and unique dishes. For example, the following prompts can be used:

[0945] Generate a new recipe based on the following data:

[0946] Past recipe data: Avocado Cheese Sandwich, Tomato Soup, Grilled Steak

[0947] Popular ingredients: avocado, chicken, cheese

[0948] User Feedback Data:

[0949] Avocado and Cheese Sandwich: 4.5

[0950] Tomato soup: 4.0

[0951] Grilled Steak: 5.0

[0952] Means of selection

[0953] The server evaluates the generated recipes to select the recipe to serve that day. The server uses the following criteria to select the recipe:

[0954] Ingredient availability

[0955] seasonality

[0956] Past user feedback

[0957] The server scores each recipe based on these criteria, selects the highest-scoring recipe, and then provides detailed cooking instructions to the AI ​​robot based on the selected recipe.

[0958] Means of instruction

[0959] Based on the selected recipe, the server instructs the AI ​​robot on the cooking steps. Specifically, the server generates detailed cooking instructions and sends them to the AI ​​robot, which then cooks the food according to them.

[0960] Means of delivery

[0961] Once cooking is complete, the server issues delivery instructions to the delivery robot. Specifically, the server sends the delivery location and address information to the delivery robot, and the delivery robot then transports and delivers the food via the optimal route. Users can check the delivery progress in real time through the application.

[0962] A means of gathering feedback

[0963] After delivery, the user can enter their rating and comments using a smartphone application. This feedback is sent from the device to the server, which stores the data and uses it as reference data when generating the next recipe.

[0964] Specific examples

[0965] For example, the server analyzes past data to determine that "avocado cheese sandwiches" are popular, and generates a new recipe: "avocado and grilled chicken tacos." This recipe idea receives the highest score, so it is decided to serve it that day. The server sends specific cooking instructions to the AI ​​robot, which then cooks the food according to the recipe. After cooking, the server gives delivery instructions to the delivery robot, and the food is delivered to the location specified by the user. After delivery, the user enters feedback through the application, saying, "The avocado and grilled chicken tacos were very delicious." The server saves this feedback and uses it to generate future recipes.

[0966] As a result, this system can provide new dishes every day, realize an efficient and high-quality food delivery service, and always provide high-quality service.

[0967] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0968] Step 1:

[0969] Data collection and analysis

[0970] The server collects past recipe data, popular ingredient data, and user feedback data. Using this data as input, the generative AI model begins analysis to automatically generate new recipes. Specifically, it analyzes ingredient combinations and cooking methods to generate recipe suggestions that take into account novelty and user preferences.

[0971] input:

[0972] Past recipe data

[0973] Popular food data

[0974] User feedback data

[0975] output:

[0976] Newly generated recipe ideas

[0977] Step 2:

[0978] Recipe Selection

[0979] The server scores the generated recipe ideas based on evaluation criteria and selects the recipe to be served that day. Each recipe is scored based on ingredient availability, seasonality, and past user feedback. The recipe with the highest score is then selected.

[0980] input:

[0981] Newly generated recipe ideas

[0982] Ingredient inventory data

[0983] Seasonal Data

[0984] User feedback data

[0985] output:

[0986] Selected Recipes

[0987] Step 3:

[0988] Cooking instructions

[0989] The server sends detailed cooking instructions to the AI ​​robot based on the selected recipe. Specifically, it instructs the AI ​​robot on which ingredients to use, in what order, and what cooking method to use. Based on these instructions, the AI ​​robot begins cooking.

[0990] input:

[0991] Selected Recipes

[0992] Detailed cooking instructions

[0993] output:

[0994] Send cooking instructions

[0995] Step 4:

[0996] Cooking and delivery preparation

[0997] The AI ​​robot prepares the food according to the cooking instructions received from the server. At the same time, the server sends delivery preparation instructions to the delivery robot, which receives information about the food pick-up location and the user's designated address.

[0998] input:

[0999] Cooking instructions

[1000] Delivery Information

[1001] output:

[1002] Start cooking

[1003] Send delivery preparation instructions

[1004] Step 5:

[1005] Delivery and progress tracking

[1006] Once the food is ready, the server sends instructions to the delivery robot to pick it up. The delivery robot then takes the optimal route and delivers the food to the location specified by the user. Users can check the delivery progress in real time through a smartphone application.

[1007] input:

[1008] The finished dish

[1009] Delivery instructions

[1010] output:

[1011] Food delivery

[1012] Delivery progress information

[1013] Step 6:

[1014] Gathering feedback

[1015] After receiving the food, the user can enter their rating and comments using a smartphone application. The feedback is sent from the device to the server, which stores this data and uses it as reference data when generating the next recipe.

[1016] input:

[1017] User Feedback

[1018] output:

[1019] Feedback Data Storage

[1020] In this way, the server, terminals, and users work together to realize an efficient and high-quality food delivery service. By utilizing generative AI models, users can enjoy new dishes every day, and the service can be expected to continuously improve.

[1021] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1022] The present invention is specifically embodied by a system including a generating means, a selecting means, an instructing means, a serving means, a feedback collecting means, and an emotion engine that recognizes the emotion of a user. An embodiment of the system of the present invention will be described below with specific examples.

[1023] System Overview

[1024] The system consists of three main components: a server, a terminal, and a user, as well as an emotion engine. The server is primarily responsible for data processing and instruction transmission, while the terminal provides the user interface and feedback collection, and the emotion engine analyzes user emotions. Users actually use the service and provide feedback and emotion data.

[1025] Means of generation

[1026] This is the generation method the server uses to generate new recipes each day. The server uses the following data:

[1027] Past recipe data

[1028] Popular food data

[1029] User Feedback Data

[1030] Emotion data from emotion engine

[1031] By analyzing this data, the generative AI creates multiple new recipe ideas. During this process, the server automatically generates ingredient combinations and cooking methods, proposing innovative and unique dishes.

[1032] Means of selection

[1033] The server evaluates the generated recipes to select the recipe to serve that day. The server uses the following criteria to select the recipe:

[1034] Ingredient availability

[1035] seasonality

[1036] Past feedback including user emotional data

[1037] The server scores each recipe based on these criteria and selects the recipe with the highest score.

[1038] Means of instruction

[1039] Based on the selected recipe, the server instructs the AI ​​robot on the cooking steps. Specifically, the server generates detailed cooking instructions and sends them to the AI ​​robot, which then cooks the food according to them.

[1040] Means of serving food

[1041] Once cooking is complete, the server issues delivery instructions to the delivery robot. Specifically, the server sends information about the food's location and the designated table to the delivery robot, and the delivery robot then transports and delivers the food via the optimal route.

[1042] A means of gathering feedback

[1043] After the meal, the device asks the user for feedback via a tablet placed on the table. The user enters their meal rating and comments, and the device sends the data to the server. The server stores this feedback in a database and uses it as reference data for the next recipe generation.

[1044] Emotion Engine

[1045] The emotion engine is particularly important. During and after the meal, the emotion engine analyzes the user's facial expressions, voice, gestures, etc. using the device's built-in camera and voice recognition system. It then compiles detailed data on how the user felt about the food and stores it as feedback. This emotion data is taken into consideration when generating the next recipe.

[1046] Specific examples

[1047] For example, the server analyzes past data to determine that "avocado cheese sandwiches" are popular, and generates a new recipe: "avocado and grilled chicken tacos." This recipe idea receives the highest score, so it is decided to serve it that day. The server sends specific cooking instructions to the AI ​​robot, which then cooks the food according to the recipe. After cooking, the server gives serving instructions to the food delivery robot, and the food is brought to the user's table. During the meal, the emotion engine analyzes the user's facial expressions and voice, and the user later inputs feedback, such as "The avocado and grilled chicken tacos were very delicious." The server saves this feedback and emotion data and uses it to generate future recipes.

[1048] As a result, this system can provide new dishes every day, solve the problem of labor shortages, and always provide high-quality service and a cooking experience based on the user's emotions.

[1049] The processing flow will be explained below.

[1050] Step 1:

[1051] The server starts the generation AI at the start of business every day. The server retrieves past recipe data, popular ingredient data, user feedback data, and emotion data from the emotion engine from its internal database.

[1052] Step 2:

[1053] The server inputs the acquired data into the generation AI, which analyzes the data and generates new recipes. The generation AI generates multiple new recipe ideas based on "randomly selected combinations of ingredients" and "combinations of cooking methods."

[1054] Step 3:

[1055] The server saves the generated recipe plan and the list of ingredients and cooking utensils required in the database.

[1056] Step 4:

[1057] The server evaluates the stored recipe ideas and assigns a score to each recipe based on past feedback, including ingredient availability, seasonality, and user sentiment data.

[1058] Step 5:

[1059] Based on the scoring results, the server selects the recipes to serve that day in order of highest score.

[1060] Step 6:

[1061] The server generates specific cooking instructions (instructions) based on the selected recipe.

[1062] Step 7:

[1063] The server sends the generated cooking instructions to the AI ​​robot, which then checks the instructions, prepares the necessary ingredients, and cooks the food.

[1064] Step 8:

[1065] Once cooking is complete, the AI ​​robot places the food on a serving tray and contacts the serving robot.

[1066] Step 9:

[1067] The server issues instructions to the delivery robot, instructing it to deliver the finished dish to the designated table. The delivery robot uses a map of the restaurant to transport the dish along the optimal route and deliver it to the table.

[1068] Step 10:

[1069] During and after the meal, the device uses a camera and microphone installed on the table to analyze the user's facial expressions, voice, gestures, etc., and the emotion engine saves the analysis results as feedback.

[1070] Step 11:

[1071] After eating, the device asks the user for feedback, and the user operates the tablet to input their meal rating and comments.

[1072] Step 12:

[1073] The device sends the collected feedback data and the emotion data analyzed by the emotion engine to the server, which stores this data in a database and uses it as reference data for the next recipe generation.

[1074] This allows the entire system to work together, offering new dishes every day while collecting and analyzing user feedback based on emotions, allowing for continuous improvement in the quality of service.

[1075] Example 2

[1076] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1077] Conventional recipe suggestion systems and cooking services have difficulty providing optimal recipes based on users' tastes and preferences, and have also been unable to provide services that take users' emotions into consideration.In addition, labor shortages have made it difficult to operate efficiently in cooking and serving food.

[1078] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for generating a new recipe using a generative AI model, a means for selecting a recipe to be provided from the generated recipes based on evaluation criteria, a means for sending cooking instructions to a cooking device based on the selected recipe, a means for sending serving instructions to a food serving device after cooking is completed, a means for collecting evaluations from the user after eating, and a means for collecting emotion data by analyzing the user's facial expressions and voice. This enables the provision of optimal recipes that take into account the user's preferences and emotions, and efficient cooking and food serving operations.

[1079] A "generative AI model" is an artificial intelligence algorithm that analyzes past data and automatically generates new recipes.

[1080] "Evaluation criteria" are the criteria used to select which recipes to offer from the generated recipe ideas. Examples include ingredient availability, seasonality, and past feedback including user emotional data.

[1081] A "cooking device" is an automated mechanical device that cooks food according to cooking instructions received from the server.

[1082] A "serving device" is an automated machine that transports food after cooking is complete and serves it to a designated location based on instructions from the server.

[1083] "User feedback data" is information provided by the user as ratings and comments after eating, and is used as reference for creating the next recipe.

[1084] "Emotion data" is information about emotions obtained by analyzing the user's facial expressions, voice, gestures, etc.

[1085] A "server" is a central computer system that processes data, sends instructions, generates and selects recipes, processes feedback, etc.

[1086] This system generates new recipes using a generative AI model, selects recipes based on evaluation criteria, and sends instructions to cooking devices and serving devices to provide meals based on the user's preferences and emotions. This system is composed of a server, a terminal, a user, and an emotion engine.

[1087] The server processes and calculates data using the following hardware and software:

[1088] The hardware and software used includes:

[1089] Hardware: High-performance computer servers, database servers, and network equipment

[1090] Software: Generative AI models, database management systems, sentiment analysis engines

[1091] Recipe Generation

[1092] The server generates new recipes using a generative AI model. Specifically, it collects and analyzes past recipe data, popular ingredient data, user feedback data, and sentiment data to create multiple new recipe suggestions. An example prompt is as follows:

[1093] "Generate new recipes based on popular recipes from the past week and user feedback"

[1094] Recipe Selection

[1095] The server selects the best recipe from the multiple recipe ideas generated based on evaluation criteria, including ingredient availability, seasonality, and past feedback including user sentiment data. The server assigns a score to each recipe based on these criteria and selects the recipe with the highest score.

[1096] cooking instructions

[1097] The server sends cooking instructions to the cooking device based on the selected recipe. Specifically, it sends the generated detailed cooking instructions to the AI ​​robot, which then cooks the food according to the instructions.

[1098] Serving instructions

[1099] Once cooking is complete, the server sends instructions to the serving device. Specifically, the server sends information about the food placement location and the designated table to the serving robot, and the serving robot then transports and serves the food along the optimal route.

[1100] Feedback collection

[1101] After the meal, the device asks the user for feedback. The user enters their meal rating and comments on a tablet placed on the table, and the device sends the data to the server. The server stores this feedback in a database and uses it as reference data for the next recipe generation.

[1102] Emotion analysis

[1103] Emotion analysis is particularly important. During and after a meal, the emotion engine analyzes the user's facial expressions, voice, and gestures using the device's built-in camera and voice recognition system. The analyzed emotion data is converted into detailed data and saved as feedback. This emotion data is taken into consideration when generating the next recipe.

[1104] Specific examples

[1105] For example, the server analyzes past data to determine that "avocado cheese sandwiches" are popular, and generates a new recipe: "avocado and grilled chicken tacos." This recipe idea receives the highest score, so it is decided to serve it that day. The server sends specific cooking instructions to the AI ​​robot, which then cooks the food according to the recipe. After cooking, the server gives serving instructions to the food delivery robot, and the food is brought to the user's table. During the meal, the emotion engine analyzes the user's facial expressions and voice, and the user later inputs feedback, such as "The avocado and grilled chicken tacos were very delicious." The server saves this feedback and emotion data and uses it to generate future recipes.

[1106] Through the above processing, the system can propose and serve new dishes that take into account the user's preferences and emotions, enabling efficient cooking and serving.

[1107] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1108] Step 1: Data collection

[1109] The server collects past recipe data, popular ingredient data, user feedback data, and sentiment data from a database. This data serves as input data for generating new recipes using a generative AI model. The server accesses the database using SQL queries to extract the necessary information. Specifically, it executes the query "Get recipe data from the past week" and retrieves the results from the database. The output is a set of collected data.

[1110] Step 2: Recipe generation

[1111] The server inputs the collected data into the generative AI model to generate new recipe suggestions. Specifically, the server inputs a prompt to the generative AI model: "Generate a new recipe based on the popular recipes from the past week and user feedback." The generative AI model generates multiple new recipe suggestions based on this prompt. The input is the collected data set and the prompt, and the output is the generated multiple new recipe suggestions.

[1112] Step 3: Recipe Selection

[1113] The server evaluates the generated recipe ideas to select the most appropriate one. Evaluation criteria include ingredient availability, seasonality, and past feedback including user sentiment data. The server uses these criteria to assign a score to each recipe and selects the recipe with the highest score. For example, if the server selects "Avocado and Grilled Chicken Tacos," it indicates that the recipe received a high score. The input is the generated recipe ideas and evaluation criteria, and the output is the selected recipe.

[1114] Step 4: Cooking Instructions

[1115] The server sends cooking instructions to the cooking device based on the selected recipe. The server then sends the generated detailed cooking instructions to the AI ​​robot, which then follows the instructions to cook. Specifically, the server sends specific instructions to the AI ​​robot, such as "Slice the avocado and prepare the grilled chicken." The input is the selected recipe, and the output is the cooking instructions sent to the cooking device.

[1116] Step 5: Serving instructions

[1117] Once cooking is complete, the server sends serving instructions to the food delivery device. The server sends information about the food's location and the specified table to the food delivery robot, which then transports and delivers the food along the optimal route. For example, the server sends the instruction "Deliver avocado and grilled chicken tacos to table number 5" to the food delivery robot. The input is the completed cooking information and the target table information, and the output is the serving instructions sent to the food delivery device.

[1118] Step 6: Gather feedback

[1119] After eating, the device provides an interface to ask the user for feedback. The user inputs their meal rating and comments using a tablet placed on the table, and the device sends the data to the server. The server stores this feedback in a database and uses it as a reference when generating the next recipe. Specifically, the user inputs a rating such as "The tacos were delicious," and this is sent to the server. The input is the feedback provided by the user, and the output is the feedback data stored in the database.

[1120] Step 7: Sentiment Analysis

[1121] The device analyzes the user's emotions during and after the meal. The device's camera and voice recognition system record the user's facial expressions and voice, and the emotion engine analyzes the data. The analysis results are sent to the server and saved as feedback. For example, if a user smiles and says "delicious," this is converted into data as a positive emotion. The input is the user's facial expression and voice data acquired from the device, and the output is emotion data saved on the server.

[1122] (Application example 2)

[1123] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1124] Modern food delivery services often fail to fully utilize user preferences, past order history, and real-time sentiment data, resulting in low user satisfaction. Furthermore, the lack of automation in cooking and serving food leads to labor shortages and reduced efficiency. This results in inconsistent user experience. The purpose of this invention is to solve these issues and provide a high-quality food delivery service.

[1125] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a generating means, a selecting means, an instructing means, a serving means, a feedback collecting means, an emotion engine that recognizes the user's emotions, and a means for proposing new dishes by taking into account the user's past order data, popular ingredient data, and emotion data. This makes it possible to provide personalized dishes based on the user's preferences and emotion data, and furthermore, by automating cooking and serving, it is possible to achieve improved efficiency and consistent quality.

[1126] The "generating means" is a device or program that has the function of analyzing past data and automatically generating new recipes.

[1127] The "selecting means" is a device or program that has the function of selecting a recipe to provide from the generated recipe plans based on evaluation criteria.

[1128] The "means for instructing" is a device or program that has the function of instructing related equipment or robots on cooking procedures based on the selected recipe.

[1129] The "serving means" refers to a device or program that has the function of transporting and serving the cooked food to a designated location or table.

[1130] The "means for collecting feedback" is a device or program that has the function of collecting and storing feedback data from users.

[1131] An "emotion engine" is a device or program that has the function of analyzing a user's facial expressions, voice, gestures, etc. and recognizing emotions.

[1132] "User's past order data" refers to historical information such as dishes that the user has ordered in the past and their ratings.

[1133] "Popular food data" refers to data that includes information about food that is highly popular during a specific period or in a specific region.

[1134] "Emotion data" refers to data that indicates information about a user's emotions analyzed using an emotion engine.

[1135] The "means for suggesting new dishes" is a device or program that has the function of suggesting new dishes personalized to the user based on the user's past order data, popular ingredient data, and emotional data.

[1136] MODE FOR CARRYING OUT THE INVENTION

[1137] System Overview

[1138] The system consists of three main components: a server, a terminal, and a user, as well as an emotion engine. The server is primarily responsible for data processing and instruction transmission, while the terminal provides the user interface and feedback collection, and the emotion engine analyzes user emotions. Users actually use the service and provide feedback and emotion data.

[1139] Server Processing

[1140] 1. Data Collection:

[1141] The server collects and stores the user's past order data, popular ingredients data, and emotional data, including cooking history, ordering ratings, and the user's facial expressions and voice data.

[1142] 2. Means of generation:

[1143] The server analyzes the collected data and automatically generates new recipes using a generative AI model, taking into account past order data and popular ingredients.

[1144] 3. Choose your method:

[1145] The server evaluates the generated recipe ideas based on inventory, seasonality, and past feedback data, assigning a score to each recipe idea, and the recipe with the highest score is selected.

[1146] 4. Means of instruction:

[1147] Based on the selected recipe, the server instructs the cooking robot on specific cooking steps, which causes the cooking robot to automatically start cooking.

[1148] 5. Means of serving:

[1149] After cooking is complete, the server instructs the serving robot to transport and serve the food to the designated table.

[1150] 6. Feedback Collection:

[1151] The server collects feedback from users through their terminals, allowing users to input their ratings and comments on the food they have been served.

[1152] Emotion engine processing

[1153] The emotion engine uses the device's built-in camera and microphone to analyze the user's facial expressions and voice data and generate emotion data. For example, it evaluates the user's level of satisfaction from their facial expressions while they are eating and sends this data to the server.

[1154] Terminal handling

[1155] The terminal is a device such as a tablet placed on a table and used by the user as an interface. The terminal not only collects feedback but also acquires emotional data from the user.

[1156] Specific examples

[1157] The server analyzes past data to determine that "Spicy Chicken Curry" is popular, and generates a new recipe called "Spicy Chicken Curry Wrap." This recipe idea received the highest score, so it is decided to serve it that day. The server sends specific cooking instructions to the cooking robot, and after cooking, a serving robot brings the food to the user. While eating, the device's camera analyzes the user's facial expressions, and an emotion engine evaluates their level of satisfaction. The user then inputs feedback, such as "The spicy chicken curry wrap was very delicious." This data is used to generate the next recipe.

[1158] Example prompts for generative AI models

[1159] "Suggest new recipes based on the user's past order data, popular ingredients, and sentiment data. For example, if the user has previously ordered 'Spicy Chicken Curry,' use that data to generate a new 'Spicy Chicken Curry Wrap.'"

[1160] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1161] Step 1:

[1162] The server collects users' past order data, popular ingredient data, and emotional data. This includes cooking history, ordering ratings, and the user's facial and voice data. The server reads this data from the database and prepares it for analysis. It uses past order data, popular ingredient data, and emotional data as inputs and generates an integrated dataset that can be used for analysis as output.

[1163] Step 2:

[1164] The server uses the generated means to analyze the collected data and automatically generate new recipes using a generative AI model. This process also takes into account the user's past preferences and emotional data. The integrated dataset is used as input, and multiple new recipe suggestions are generated as output. Specifically, the server sends a prompt to the generative AI model and receives the returned recipe suggestions.

[1165] Step 3:

[1166] The server evaluates the generated recipe ideas using a method selected by the server. Evaluation criteria include inventory status, seasonality, and past feedback data. The generated recipe ideas and evaluation criteria data are used as input, and the recipe with the highest score is selected as output. Specifically, the server calculates a score based on the evaluation criteria for each recipe idea, and selects the recipe with the highest score.

[1167] Step 4:

[1168] Using the means instructed by the server, the cooking robot is instructed on specific cooking steps based on the selected recipe. The selected recipe is used as input, and commands including the cooking steps are generated and sent as output. Specifically, the cooking steps are extracted from the recipe data and instructions are sent to the cooking robot.

[1169] Step 5:

[1170] The server uses the means of serving to instruct the serving robot to transport and serve the cooked food to the specified table. It uses the cooking completion notification and serving information as input, and generates and sends serving instructions as output. Specifically, it receives the cooking completion notification from the cooking robot and sends the food location and table information to the serving robot.

[1171] Step 6:

[1172] The device collects feedback from users. After collecting the feedback, the server stores the data. The system uses the ratings and comments entered by users on the tablet device as input, generates feedback data as output, and stores it in a database. Specifically, the device collects the feedback information entered by users on the tablet device and sends it to the server.

[1173] Step 7:

[1174] The device uses an emotion engine to analyze the user's facial expression and voice data and generate emotion data. The device uses the user's facial expression and voice data acquired from a camera or microphone as input, and generates and saves emotion data as output. Specifically, the device captures the user's facial expression and voice with a camera or microphone during and after a meal, and the emotion engine analyzes this to generate emotion data, which is then sent to the server.

[1175] Step 8:

[1176] The server saves the collected feedback and emotion data and uses it for the next recipe generation. The feedback and emotion data are used as input, and reference data for the next recipe generation is generated and saved as output. Specifically, the server stores the collected data in a database and converts it into a usable format for the next analysis.

[1177] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1178] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1179] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1180] [Fourth embodiment]

[1181] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1182] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1183] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1184] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1185] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1186] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1187] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1188] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1189] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1190] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1191] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1192] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1193] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1194] The present invention is specifically embodied in a system including a generating means, a selecting means, an instructing means, a serving means, and a feedback collecting means. How the system of the present invention is implemented will be described below with specific examples.

[1195] System Overview

[1196] The system consists of three main components: a server, a terminal, and a user. The server is primarily responsible for processing data and sending instructions, while the terminal provides the user interface and feedback collection. The user actually uses the service and provides feedback.

[1197] Means of generation

[1198] The first thing the server does is generate a new recipe for each day. To do this, the server uses the following data:

[1199] Past recipe data

[1200] Popular food data

[1201] User feedback data

[1202] By analyzing this data, the generative AI creates multiple new recipe ideas. During this process, the server automatically generates ingredient combinations and cooking methods, proposing innovative and unique dishes.

[1203] Means of selection

[1204] The server evaluates the generated recipes to select the recipe to serve that day. The server uses the following criteria to select the recipe:

[1205] Ingredient availability

[1206] seasonality

[1207] Past user feedback

[1208] The server scores each recipe based on these criteria and selects the recipe with the highest score.

[1209] Means of instruction

[1210] Based on the selected recipe, the server instructs the AI ​​robot on the cooking steps. Specifically, the server generates detailed cooking instructions and sends them to the AI ​​robot, which then cooks the food according to them.

[1211] Means of serving food

[1212] Once cooking is complete, the server issues delivery instructions to the delivery robot. Specifically, the server sends information about the food's location and the designated table to the delivery robot, and the delivery robot then transports and delivers the food via the optimal route.

[1213] A means of gathering feedback

[1214] After the meal, the device asks the user for feedback via a tablet placed on the table. The user enters their meal rating and comments, and the device sends the data to the server. The server stores this feedback in a database and uses it as reference data for the next recipe generation.

[1215] Specific examples

[1216] For example, the server analyzes past data to determine that "avocado cheese sandwiches" are popular, and generates a new recipe: "avocado and grilled chicken tacos." This recipe idea receives the highest score, so it is decided to serve it that day. The server sends specific cooking instructions to the AI ​​robot, which then cooks the food according to the recipe. After cooking, the server gives serving instructions to the food delivery robot, and the food is brought to the user's table. After eating, the user enters feedback via their device, saying, "The avocado and grilled chicken tacos were very delicious." The server saves this feedback and uses it to generate future recipes.

[1217] As a result, this system can provide new dishes every day, solve the problem of labor shortages, and always provide high-quality service.

[1218] The processing flow will be explained below.

[1219] Step 1:

[1220] The server starts the generation AI at the start of business each day, retrieving past recipe data, popular ingredients data, and user feedback data from its internal database.

[1221] Step 2:

[1222] The server inputs the acquired data into the generation AI, which analyzes the data and generates new recipes. The generation AI generates multiple new recipe ideas based on "randomly selected combinations of ingredients" and "combinations of cooking methods."

[1223] Step 3:

[1224] The server saves the generated recipe plan and the list of ingredients and cooking utensils required in the database.

[1225] Step 4:

[1226] The server evaluates multiple saved recipe ideas and assigns a score to each recipe, taking into account ingredient availability, seasonality, and past user feedback.

[1227] Step 5:

[1228] Based on the scoring results, the server selects the recipes to serve that day in order of highest score.

[1229] Step 6:

[1230] The server generates specific cooking instructions (instructions) based on the selected recipe.

[1231] Step 7:

[1232] The server sends the generated cooking instructions to the AI ​​robot, which then checks the instructions, prepares the necessary ingredients, and cooks the food.

[1233] Step 8:

[1234] Once cooking is complete, the AI ​​robot places the food on a serving tray and contacts the serving robot.

[1235] Step 9:

[1236] The server issues instructions to the delivery robot, which then sends instructions to deliver the finished dish to the designated table. The delivery robot uses a map of the restaurant to transport the dish along the optimal route and deliver it to the table.

[1237] Step 10:

[1238] After the meal, the device asks the user for feedback via a tablet installed on each table. The user operates the tablet to input their meal rating and comments.

[1239] Step 11:

[1240] The device sends the collected feedback data to the server, which stores the received feedback in a database and uses it as reference data for the next recipe generation.

[1241] Example 1

[1242] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1243] Conventional systems have been inefficient in the entire process from proposing dishes to cooking, serving, and collecting feedback, resulting in labor shortages and time-consuming tasks due to the high level of manual work. Furthermore, the lack of a mechanism for reflecting user preferences and past feedback has led to inconsistent food quality. The present invention aims to solve these problems and provide a system for providing efficient, high-quality food.

[1244] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1245] In this invention, the server

[1246] a means of collecting data;

[1247] A means for generating new proposals using a generative AI model; and

[1248] means for selecting from among the generated proposals based on evaluation criteria;

[1249] means for transmitting instructions based on the selected suggestions;

[1250] means for transporting the goods in accordance with the instructions;

[1251] a means of collecting feedback;

[1252] This will automate a series of processes and reflect user preferences and feedback, enabling efficient and high-quality food delivery.

[1253] "Means for collecting data" refers to means for capturing historical information, popular information, and user opinions from a database and making them available for the next stage of processing.

[1254] "Means for generating new proposals using generative AI models" refers to means for automatically creating new ideas and recipes using generative AI models based on collected data.

[1255] The "means for selecting from among the generated proposals based on evaluation criteria" refers to a means for evaluating the generated proposals based on inventory status, seasonality, and past opinions, and selecting the most suitable one.

[1256] The "means for transmitting instructions based on the selected suggestion" is a means for transmitting specific instructions to an appropriate device for automating cooking or other tasks in accordance with the selected suggestion.

[1257] "Means for transporting goods in accordance with the instructions" means the equipment or devices for properly transporting goods to the designated location in accordance with the instructions.

[1258] The "means for collecting feedback" is a means for collecting opinions and evaluations from users and storing them in the system so that they can be used when generating the next proposal.

[1259] This invention relates to a system that automates a series of processes: collecting data, generating new proposals using a generative AI model, making selections and instructions based on evaluation criteria, transporting goods according to the instructions, and collecting feedback. This system consists of three main elements: a server, a terminal, and a user.

[1260] Server Roles

[1261] The server is mainly responsible for processing data and sending instructions. Each of these methods will be explained in detail below.

[1262] How data is collected

[1263] The server collects past recipe data, popular ingredient data, and user feedback data from a database, which are then used in the process of utilizing the generative AI model.

[1264] A means of generating new proposals using generative AI models

[1265] The server creates prompts for the generative AI model based on the collected data and sends them to the model to generate multiple new recipe ideas. Examples of prompts include:

[1266] "Generate new recipes based on past popular ingredients and user feedback."

[1267] When the generative AI model receives this prompt, it analyzes the input data and generates new recipe ideas.

[1268] A means of selecting from the generated proposals based on evaluation criteria

[1269] The server evaluates the generated recipe ideas, using criteria such as ingredient availability, seasonality, and past user feedback. The recipe with the highest score is selected as the result of the evaluation.

[1270] A means of sending instructions based on the selected suggestion

[1271] The server creates detailed cooking instructions based on the selected recipe and sends them to the AI ​​robot, which then begins cooking according to the instructions.

[1272] A means of transporting goods based on that instruction

[1273] Once cooking is complete, the server sends serving instructions to the food delivery robot, including information on where to place the food and the designated table. The food delivery robot receives instructions from the server and transports and serves the food to the user's table.

[1274] Device Role

[1275] The terminal mainly handles the user interface and feedback collection.

[1276] A means of gathering feedback

[1277] After the meal, the device asks the user for feedback via a tablet placed on the table. The user enters their rating and comments on the food, and the device sends the data to the server. The server stores this feedback in a database and uses it as reference data when generating the next recipe.

[1278] User Roles

[1279] Users actually use the system and provide feedback on the food served.

[1280] As a concrete example, consider the case where the server analyzes from past data that "avocado cheese sandwiches" are popular, and then uses a new generative AI model to generate "avocado and grilled chicken tacos." This recipe idea received the highest score, so it is selected as the dish to be served that day. The server sends cooking instructions to the AI ​​robot, which follows those instructions to cook the dish. After cooking is complete, the server gives serving instructions to the food delivery robot, and the dish is brought to the user's table. After eating, the user enters feedback via their device, saying, "The avocado and grilled chicken tacos were very delicious." The server saves this feedback and uses it to generate the next recipe.

[1281] In this way, the system of the present invention not only realizes efficient and high-quality food provision, but also has the function of reflecting user preferences and feedback.

[1282] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1283] Program processing steps

[1284] Step 1:

[1285] The server collects past recipe data, popular ingredient data, and user feedback data from the database. The input for this data collection is past data from various databases and external data sources. The collected data is used in the next step.

[1286] Step 2:

[1287] The server creates a prompt for the generative AI model based on the collected data. The input here is the data collected in step 1, and the output is a text prompt to be sent to the generative AI model. A specific prompt generated is "Please generate a new recipe based on past popular ingredients and user feedback."

[1288] Step 3:

[1289] The server sends a prompt to the generative AI model to generate multiple new recipe ideas. The input is the prompt created in step 2, and the output is multiple new recipe ideas. The generative AI model processes and calculates data based on these recipe ideas to provide new recipe ideas.

[1290] Step 4:

[1291] The server evaluates the generated recipe ideas. Evaluation criteria include ingredient availability, seasonality, and past user feedback. The input is the recipe ideas generated in step 3 and the evaluation criteria data, and the output is an evaluation score. Specifically, each recipe is multiplied by the availability data and seasonality information, and the feedback data is weighted to calculate the score.

[1292] Step 5:

[1293] The server selects the recipe with the highest score. The input is the evaluation score calculated in step 4, and the output is the selected recipe. Here, an algorithm is used to automatically select the recipe with the highest score.

[1294] Step 6:

[1295] The server creates detailed cooking instructions based on the selected recipe and sends them to the AI ​​robot. The input is the selected recipe, and the output is data on the specific cooking instructions. The server breaks down the steps of the selected recipe, converts them into a format that the AI ​​robot can understand, and sends them.

[1296] Step 7:

[1297] The AI ​​robot receives the cooking instructions and starts cooking. The input is the detailed cooking instructions sent in step 6, and the output is the cooked food. The AI ​​robot follows the cooking instructions to process the ingredients, cook, and serve.

[1298] Step 8:

[1299] Once cooking is complete, the server sends serving instructions to the delivery robot. The input is the cooked food and serving instructions data, and the output is serving instructions to the delivery robot. The server combines the recipe and table information to calculate the optimal route and sends it to the delivery robot.

[1300] Step 9:

[1301] The delivery robot receives instructions from the server and transports and serves food to the user's table. The input is the delivery instruction data from the server, and the output is the food being served to the correct table. The delivery robot follows the instructions and accurately delivers the food to the user's table.

[1302] Step 10:

[1303] After the meal, the device asks the user for feedback via a tablet installed on the table. The input is the user's dining experience, and the output is feedback data. The device allows users to easily input ratings and comments via the tablet.

[1304] Step 11:

[1305] The user inputs ratings and comments on the meal. The input is the user's feedback, and the output is the rating data stored on the device.

[1306] Step 12:

[1307] The terminal sends the collected feedback to the server. The input is the user's evaluation data, and the output is the feedback sent to the server. The server stores this data in a database and uses it the next time it generates a recipe.

[1308] Through this series of processes, the system enables efficient and high-quality food delivery.

[1309] (Application example 1)

[1310] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1311] Current food delivery services often lack a wide variety of menu items, making it difficult for users to enjoy new dishes every day. Furthermore, the process from cooking to delivery is not streamlined, making it difficult to maintain a high level of service. Furthermore, there is no mechanism for incorporating user feedback into future service improvements.

[1312] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1313] In this invention, the server includes a generating means, a selecting means, an instructing means, a delivering means, and a feedback collecting means. This makes it possible to analyze past data to automatically generate new recipes every day and notify users of a different recipe each day. Furthermore, an efficient and high-quality food delivery service can be realized by having an AI robot provide cooking instructions and manage delivery. Furthermore, since feedback from users can be collected and reflected in future services, continuous improvement of the service can be expected.

[1314] The "means of generation" is a function that analyzes past data to automatically generate new recipes and notifies users of them on a daily basis.

[1315] The "means of selection" is a function that selects the optimal recipe from the multiple recipe ideas generated based on evaluation criteria and instructs the AI ​​robot on specific cooking steps.

[1316] The "means of giving instructions" is a function that sends detailed cooking instructions to the AI ​​robot based on the selected recipe, allowing it to cook appropriately.

[1317] The "delivery means" is a function that transports cooked food to a location designated by the user and manages the delivery progress in real time.

[1318] The "means of collecting feedback" refers to a function that allows users to input ratings and comments on the delivered food, and sends that data to the server, which uses it to generate the next recipe and improve the service.

[1319] A "server" is a central computer that processes data, sends instructions, and manages the entire system.

[1320] A "terminal" is a device that acts as a user interface and collects feedback from the user.

[1321] "Users" are individuals or corporations who actually use the food delivery service and provide feedback.

[1322] An "AI robot" is a machine equipped with artificial intelligence that automatically cooks based on instructions from a server.

[1323] A "delivery robot" is an automated delivery device designed to deliver cooked food to users.

[1324] The present invention relates to a food delivery system including a generating means, a selecting means, a directing means, a delivering means, and a feedback collecting means. How to implement the present invention will be specifically described below.

[1325] System Overview

[1326] The system consists of three main components: a server, a terminal, and a user. The server is primarily responsible for processing data and sending instructions, while the terminal provides the user interface and feedback collection. The user actually uses the service and provides feedback.

[1327] Means of generation

[1328] The first thing the server does is generate a new recipe for each day. To do this, the server uses the following data:

[1329] Past recipe data

[1330] Popular food data

[1331] User feedback data

[1332] By analyzing this data, the generative AI creates multiple new recipe ideas. During this process, the server automatically generates ingredient combinations and cooking methods to suggest innovative and unique dishes. For example, the following prompts can be used:

[1333] Generate a new recipe based on the following data:

[1334] Past recipe data: Avocado Cheese Sandwich, Tomato Soup, Grilled Steak

[1335] Popular ingredients: avocado, chicken, cheese

[1336] User Feedback Data:

[1337] Avocado and Cheese Sandwich: 4.5

[1338] Tomato soup: 4.0

[1339] Grilled Steak: 5.0

[1340] Means of selection

[1341] The server evaluates the generated recipes to select the recipe to serve that day. The server uses the following criteria to select the recipe:

[1342] Ingredient availability

[1343] seasonality

[1344] Past user feedback

[1345] The server scores each recipe based on these criteria, selects the highest-scoring recipe, and then provides detailed cooking instructions to the AI ​​robot based on the selected recipe.

[1346] Means of instruction

[1347] Based on the selected recipe, the server instructs the AI ​​robot on the cooking steps. Specifically, the server generates detailed cooking instructions and sends them to the AI ​​robot, which then cooks the food according to them.

[1348] Means of delivery

[1349] Once cooking is complete, the server issues delivery instructions to the delivery robot. Specifically, the server sends the delivery location and address information to the delivery robot, and the delivery robot then transports and delivers the food via the optimal route. Users can check the delivery progress in real time through the application.

[1350] A means of gathering feedback

[1351] After delivery, the user can enter their rating and comments using a smartphone application. This feedback is sent from the device to the server, which stores the data and uses it as reference data when generating the next recipe.

[1352] Specific examples

[1353] For example, the server analyzes past data to determine that "avocado cheese sandwiches" are popular, and generates a new recipe: "avocado and grilled chicken tacos." This recipe idea receives the highest score, so it is decided to serve it that day. The server sends specific cooking instructions to the AI ​​robot, which then cooks the food according to the recipe. After cooking, the server gives delivery instructions to the delivery robot, and the food is delivered to the location specified by the user. After delivery, the user enters feedback through the application, saying, "The avocado and grilled chicken tacos were very delicious." The server saves this feedback and uses it to generate future recipes.

[1354] As a result, this system can provide new dishes every day, realize an efficient and high-quality food delivery service, and always provide high-quality service.

[1355] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1356] Step 1:

[1357] Data collection and analysis

[1358] The server collects past recipe data, popular ingredient data, and user feedback data. Using this data as input, the generative AI model begins analysis to automatically generate new recipes. Specifically, it analyzes ingredient combinations and cooking methods to generate recipe suggestions that take into account novelty and user preferences.

[1359] input:

[1360] Past recipe data

[1361] Popular food data

[1362] User feedback data

[1363] output:

[1364] Newly generated recipe ideas

[1365] Step 2:

[1366] Recipe Selection

[1367] The server scores the generated recipe ideas based on evaluation criteria and selects the recipe to be served that day. Each recipe is scored based on ingredient availability, seasonality, and past user feedback. The recipe with the highest score is then selected.

[1368] input:

[1369] Newly generated recipe ideas

[1370] Ingredient inventory data

[1371] Seasonal Data

[1372] User feedback data

[1373] output:

[1374] Selected Recipes

[1375] Step 3:

[1376] Cooking instructions

[1377] The server sends detailed cooking instructions to the AI ​​robot based on the selected recipe. Specifically, it instructs the AI ​​robot on which ingredients to use, in what order, and what cooking method to use. Based on these instructions, the AI ​​robot begins cooking.

[1378] input:

[1379] Selected Recipes

[1380] Detailed cooking instructions

[1381] output:

[1382] Send cooking instructions

[1383] Step 4:

[1384] Cooking and delivery preparation

[1385] The AI ​​robot prepares the food according to the cooking instructions received from the server. At the same time, the server sends delivery preparation instructions to the delivery robot, which receives information about the food pick-up location and the user's designated address.

[1386] input:

[1387] Cooking instructions

[1388] Delivery Information

[1389] output:

[1390] Start cooking

[1391] Send delivery preparation instructions

[1392] Step 5:

[1393] Delivery and progress tracking

[1394] Once the food is ready, the server sends instructions to the delivery robot to pick it up. The delivery robot then takes the optimal route and delivers the food to the location specified by the user. Users can check the delivery progress in real time through a smartphone application.

[1395] input:

[1396] The finished dish

[1397] Delivery instructions

[1398] output:

[1399] Food delivery

[1400] Delivery progress information

[1401] Step 6:

[1402] Gathering feedback

[1403] After receiving the food, the user can enter their rating and comments using a smartphone application. The feedback is sent from the device to the server, which stores this data and uses it as reference data when generating the next recipe.

[1404] input:

[1405] User Feedback

[1406] output:

[1407] Feedback Data Storage

[1408] In this way, the server, terminals, and users work together to realize an efficient and high-quality food delivery service. By utilizing generative AI models, users can enjoy new dishes every day, and the service can be expected to continuously improve.

[1409] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1410] The present invention is specifically embodied by a system including a generating means, a selecting means, an instructing means, a serving means, a feedback collecting means, and an emotion engine that recognizes the emotion of a user. An embodiment of the system of the present invention will be described below with specific examples.

[1411] System Overview

[1412] The system consists of three main components: a server, a terminal, and a user, as well as an emotion engine. The server is primarily responsible for data processing and instruction transmission, while the terminal provides the user interface and feedback collection, and the emotion engine analyzes user emotions. Users actually use the service and provide feedback and emotion data.

[1413] Means of generation

[1414] This is the generation method the server uses to generate new recipes each day. The server uses the following data:

[1415] Past recipe data

[1416] Popular food data

[1417] User Feedback Data

[1418] Emotion data from emotion engine

[1419] By analyzing this data, the generative AI creates multiple new recipe ideas. During this process, the server automatically generates ingredient combinations and cooking methods, proposing innovative and unique dishes.

[1420] Means of selection

[1421] The server evaluates the generated recipes to select the recipe to serve that day. The server uses the following criteria to select the recipe:

[1422] Ingredient availability

[1423] seasonality

[1424] Past feedback including user emotional data

[1425] The server scores each recipe based on these criteria and selects the recipe with the highest score.

[1426] Means of instruction

[1427] Based on the selected recipe, the server instructs the AI ​​robot on the cooking steps. Specifically, the server generates detailed cooking instructions and sends them to the AI ​​robot, which then cooks the food according to them.

[1428] Means of serving food

[1429] Once cooking is complete, the server issues delivery instructions to the delivery robot. Specifically, the server sends information about the food's location and the designated table to the delivery robot, and the delivery robot then transports and delivers the food via the optimal route.

[1430] A means of gathering feedback

[1431] After the meal, the device asks the user for feedback via a tablet placed on the table. The user enters their meal rating and comments, and the device sends the data to the server. The server stores this feedback in a database and uses it as reference data for the next recipe generation.

[1432] Emotion Engine

[1433] The emotion engine is particularly important. During and after the meal, the emotion engine analyzes the user's facial expressions, voice, gestures, etc. using the device's built-in camera and voice recognition system. It then compiles detailed data on how the user felt about the food and stores it as feedback. This emotion data is taken into consideration when generating the next recipe.

[1434] Specific examples

[1435] For example, the server analyzes past data to determine that "avocado cheese sandwiches" are popular, and generates a new recipe: "avocado and grilled chicken tacos." This recipe idea receives the highest score, so it is decided to serve it that day. The server sends specific cooking instructions to the AI ​​robot, which then cooks the food according to the recipe. After cooking, the server gives serving instructions to the food delivery robot, and the food is brought to the user's table. During the meal, the emotion engine analyzes the user's facial expressions and voice, and the user later inputs feedback, such as "The avocado and grilled chicken tacos were very delicious." The server saves this feedback and emotion data and uses it to generate future recipes.

[1436] As a result, this system can provide new dishes every day, solve the problem of labor shortages, and always provide high-quality service and a cooking experience based on the user's emotions.

[1437] The processing flow will be explained below.

[1438] Step 1:

[1439] The server starts the generation AI at the start of business every day. The server retrieves past recipe data, popular ingredient data, user feedback data, and emotion data from the emotion engine from its internal database.

[1440] Step 2:

[1441] The server inputs the acquired data into the generation AI, which analyzes the data and generates new recipes. The generation AI generates multiple new recipe ideas based on "randomly selected combinations of ingredients" and "combinations of cooking methods."

[1442] Step 3:

[1443] The server saves the generated recipe plan and the list of ingredients and cooking utensils required in the database.

[1444] Step 4:

[1445] The server evaluates the stored recipe ideas and assigns a score to each recipe based on past feedback, including ingredient availability, seasonality, and user sentiment data.

[1446] Step 5:

[1447] Based on the scoring results, the server selects the recipes to serve that day in order of highest score.

[1448] Step 6:

[1449] The server generates specific cooking instructions (instructions) based on the selected recipe.

[1450] Step 7:

[1451] The server sends the generated cooking instructions to the AI ​​robot, which then checks the instructions, prepares the necessary ingredients, and cooks the food.

[1452] Step 8:

[1453] Once cooking is complete, the AI ​​robot places the food on a serving tray and contacts the serving robot.

[1454] Step 9:

[1455] The server issues instructions to the delivery robot, instructing it to deliver the finished dish to the designated table. The delivery robot uses a map of the restaurant to transport the dish along the optimal route and deliver it to the table.

[1456] Step 10:

[1457] During and after the meal, the device uses a camera and microphone installed on the table to analyze the user's facial expressions, voice, gestures, etc., and the emotion engine saves the analysis results as feedback.

[1458] Step 11:

[1459] After eating, the device asks the user for feedback, and the user operates the tablet to input their meal rating and comments.

[1460] Step 12:

[1461] The device sends the collected feedback data and the emotion data analyzed by the emotion engine to the server, which stores this data in a database and uses it as reference data for the next recipe generation.

[1462] This allows the entire system to work together, offering new dishes every day while collecting and analyzing user feedback based on emotions, allowing for continuous improvement in the quality of service.

[1463] Example 2

[1464] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1465] Conventional recipe suggestion systems and cooking services have difficulty providing optimal recipes based on users' tastes and preferences, and have also been unable to provide services that take users' emotions into consideration.In addition, labor shortages have made it difficult to operate efficiently in cooking and serving food.

[1466] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for generating a new recipe using a generative AI model, a means for selecting a recipe to be provided from the generated recipes based on evaluation criteria, a means for sending cooking instructions to a cooking device based on the selected recipe, a means for sending serving instructions to a food serving device after cooking is completed, a means for collecting evaluations from the user after eating, and a means for collecting emotion data by analyzing the user's facial expressions and voice. This enables the provision of optimal recipes that take into account the user's preferences and emotions, and efficient cooking and food serving operations.

[1467] A "generative AI model" is an artificial intelligence algorithm that analyzes past data and automatically generates new recipes.

[1468] "Evaluation criteria" are the criteria used to select which recipes to offer from the generated recipe ideas. Examples include ingredient availability, seasonality, and past feedback including user emotional data.

[1469] A "cooking device" is an automated mechanical device that cooks food according to cooking instructions received from the server.

[1470] A "serving device" is an automated machine that transports food after cooking is complete and serves it to a designated location based on instructions from the server.

[1471] "User feedback data" is information provided by the user as ratings and comments after eating, and is used as reference for creating the next recipe.

[1472] "Emotion data" is information about emotions obtained by analyzing the user's facial expressions, voice, gestures, etc.

[1473] A "server" is a central computer system that processes data, sends instructions, generates and selects recipes, processes feedback, etc.

[1474] This system generates new recipes using a generative AI model, selects recipes based on evaluation criteria, and sends instructions to cooking devices and serving devices to provide meals based on the user's preferences and emotions. This system is composed of a server, a terminal, a user, and an emotion engine.

[1475] The server processes and calculates data using the following hardware and software:

[1476] The hardware and software used includes:

[1477] Hardware: High-performance computer servers, database servers, and network equipment

[1478] Software: Generative AI models, database management systems, sentiment analysis engines

[1479] Recipe Generation

[1480] The server generates new recipes using a generative AI model. Specifically, it collects and analyzes past recipe data, popular ingredient data, user feedback data, and sentiment data to create multiple new recipe suggestions. An example prompt is as follows:

[1481] "Generate new recipes based on popular recipes from the past week and user feedback"

[1482] Recipe Selection

[1483] The server selects the best recipe from the multiple recipe ideas generated based on evaluation criteria, including ingredient availability, seasonality, and past feedback including user sentiment data. The server assigns a score to each recipe based on these criteria and selects the recipe with the highest score.

[1484] cooking instructions

[1485] The server sends cooking instructions to the cooking device based on the selected recipe. Specifically, it sends the generated detailed cooking instructions to the AI ​​robot, which then cooks the food according to the instructions.

[1486] Serving instructions

[1487] Once cooking is complete, the server sends instructions to the serving device. Specifically, the server sends information about the food placement location and the designated table to the serving robot, and the serving robot then transports and serves the food along the optimal route.

[1488] Feedback collection

[1489] After the meal, the device asks the user for feedback. The user enters their meal rating and comments on a tablet placed on the table, and the device sends the data to the server. The server stores this feedback in a database and uses it as reference data for the next recipe generation.

[1490] Emotion analysis

[1491] Emotion analysis is particularly important. During and after a meal, the emotion engine analyzes the user's facial expressions, voice, and gestures using the device's built-in camera and voice recognition system. The analyzed emotion data is converted into detailed data and saved as feedback. This emotion data is taken into consideration when generating the next recipe.

[1492] Specific examples

[1493] For example, the server analyzes past data to determine that "avocado cheese sandwiches" are popular, and generates a new recipe: "avocado and grilled chicken tacos." This recipe idea receives the highest score, so it is decided to serve it that day. The server sends specific cooking instructions to the AI ​​robot, which then cooks the food according to the recipe. After cooking, the server gives serving instructions to the food delivery robot, and the food is brought to the user's table. During the meal, the emotion engine analyzes the user's facial expressions and voice, and the user later inputs feedback, such as "The avocado and grilled chicken tacos were very delicious." The server saves this feedback and emotion data and uses it to generate future recipes.

[1494] Through the above processing, the system can propose and serve new dishes that take into account the user's preferences and emotions, enabling efficient cooking and serving.

[1495] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1496] Step 1: Data collection

[1497] The server collects past recipe data, popular ingredient data, user feedback data, and sentiment data from a database. This data serves as input data for generating new recipes using a generative AI model. The server accesses the database using SQL queries to extract the necessary information. Specifically, it executes the query "Get recipe data from the past week" and retrieves the results from the database. The output is a set of collected data.

[1498] Step 2: Recipe generation

[1499] The server inputs the collected data into the generative AI model to generate new recipe suggestions. Specifically, the server inputs a prompt to the generative AI model: "Generate a new recipe based on the popular recipes from the past week and user feedback." The generative AI model generates multiple new recipe suggestions based on this prompt. The input is the collected data set and the prompt, and the output is the generated multiple new recipe suggestions.

[1500] Step 3: Recipe Selection

[1501] The server evaluates the generated recipe ideas to select the most appropriate one. Evaluation criteria include ingredient availability, seasonality, and past feedback including user sentiment data. The server uses these criteria to assign a score to each recipe and selects the recipe with the highest score. For example, if the server selects "Avocado and Grilled Chicken Tacos," it indicates that the recipe received a high score. The input is the generated recipe ideas and evaluation criteria, and the output is the selected recipe.

[1502] Step 4: Cooking Instructions

[1503] The server sends cooking instructions to the cooking device based on the selected recipe. The server then sends the generated detailed cooking instructions to the AI ​​robot, which then follows the instructions to cook. Specifically, the server sends specific instructions to the AI ​​robot, such as "Slice the avocado and prepare the grilled chicken." The input is the selected recipe, and the output is the cooking instructions sent to the cooking device.

[1504] Step 5: Serving instructions

[1505] Once cooking is complete, the server sends serving instructions to the food delivery device. The server sends information about the food's location and the specified table to the food delivery robot, which then transports and delivers the food along the optimal route. For example, the server sends the instruction "Deliver avocado and grilled chicken tacos to table number 5" to the food delivery robot. The input is the completed cooking information and the target table information, and the output is the serving instructions sent to the food delivery device.

[1506] Step 6: Gather feedback

[1507] After eating, the device provides an interface to ask the user for feedback. The user inputs their meal rating and comments using a tablet placed on the table, and the device sends the data to the server. The server stores this feedback in a database and uses it as a reference when generating the next recipe. Specifically, the user inputs a rating such as "The tacos were delicious," and this is sent to the server. The input is the feedback provided by the user, and the output is the feedback data stored in the database.

[1508] Step 7: Sentiment Analysis

[1509] The device analyzes the user's emotions during and after the meal. The device's camera and voice recognition system record the user's facial expressions and voice, and the emotion engine analyzes the data. The analysis results are sent to the server and saved as feedback. For example, if a user smiles and says "delicious," this is converted into data as a positive emotion. The input is the user's facial expression and voice data acquired from the device, and the output is emotion data saved on the server.

[1510] (Application example 2)

[1511] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1512] Modern food delivery services often fail to fully utilize user preferences, past order history, and real-time sentiment data, resulting in low user satisfaction. Furthermore, the lack of automation in cooking and serving food leads to labor shortages and reduced efficiency. This results in inconsistent user experience. The purpose of this invention is to solve these issues and provide a high-quality food delivery service.

[1513] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a generating means, a selecting means, an instructing means, a serving means, a feedback collecting means, an emotion engine that recognizes the user's emotions, and a means for proposing new dishes by taking into account the user's past order data, popular ingredient data, and emotion data. This makes it possible to provide personalized dishes based on the user's preferences and emotion data, and furthermore, by automating cooking and serving, it is possible to achieve improved efficiency and consistent quality.

[1514] The "generating means" is a device or program that has the function of analyzing past data and automatically generating new recipes.

[1515] The "selecting means" is a device or program that has the function of selecting a recipe to provide from the generated recipe plans based on evaluation criteria.

[1516] The "means for instructing" is a device or program that has the function of instructing related equipment or robots on cooking procedures based on the selected recipe.

[1517] The "serving means" refers to a device or program that has the function of transporting and serving the cooked food to a designated location or table.

[1518] The "means for collecting feedback" is a device or program that has the function of collecting and storing feedback data from users.

[1519] An "emotion engine" is a device or program that has the function of analyzing a user's facial expressions, voice, gestures, etc. and recognizing emotions.

[1520] "User's past order data" refers to historical information such as dishes that the user has ordered in the past and their ratings.

[1521] "Popular food data" refers to data that includes information about food that is highly popular during a specific period or in a specific region.

[1522] "Emotion data" refers to data that indicates information about a user's emotions analyzed using an emotion engine.

[1523] The "means for suggesting new dishes" is a device or program that has the function of suggesting new dishes personalized to the user based on the user's past order data, popular ingredient data, and emotional data.

[1524] MODE FOR CARRYING OUT THE INVENTION

[1525] System Overview

[1526] The system consists of three main components: a server, a terminal, and a user, as well as an emotion engine. The server is primarily responsible for data processing and instruction transmission, while the terminal provides the user interface and feedback collection, and the emotion engine analyzes user emotions. Users actually use the service and provide feedback and emotion data.

[1527] Server Processing

[1528] 1. Data Collection:

[1529] The server collects and stores the user's past order data, popular ingredients data, and emotional data, including cooking history, ordering ratings, and the user's facial expressions and voice data.

[1530] 2. Means of generation:

[1531] The server analyzes the collected data and automatically generates new recipes using a generative AI model, taking into account past order data and popular ingredients.

[1532] 3. Choose your method:

[1533] The server evaluates the generated recipe ideas based on inventory, seasonality, and past feedback data, assigning a score to each recipe idea, and the recipe with the highest score is selected.

[1534] 4. Means of instruction:

[1535] Based on the selected recipe, the server instructs the cooking robot on specific cooking steps, which causes the cooking robot to automatically start cooking.

[1536] 5. Means of serving:

[1537] After cooking is complete, the server instructs the serving robot to transport and serve the food to the designated table.

[1538] 6. Feedback Collection:

[1539] The server collects feedback from users through their terminals, allowing users to input their ratings and comments on the food they have been served.

[1540] Emotion engine processing

[1541] The emotion engine uses the device's built-in camera and microphone to analyze the user's facial expressions and voice data and generate emotion data. For example, it evaluates the user's level of satisfaction from their facial expressions while they are eating and sends this data to the server.

[1542] Terminal handling

[1543] The terminal is a device such as a tablet placed on a table and used by the user as an interface. The terminal not only collects feedback but also acquires emotional data from the user.

[1544] Specific examples

[1545] The server analyzes past data to determine that "Spicy Chicken Curry" is popular, and generates a new recipe called "Spicy Chicken Curry Wrap." This recipe idea received the highest score, so it is decided to serve it that day. The server sends specific cooking instructions to the cooking robot, and after cooking, a serving robot brings the food to the user. While eating, the device's camera analyzes the user's facial expressions, and an emotion engine evaluates their level of satisfaction. The user then inputs feedback, such as "The spicy chicken curry wrap was very delicious." This data is used to generate the next recipe.

[1546] Example prompts for generative AI models

[1547] "Suggest new recipes based on the user's past order data, popular ingredients, and sentiment data. For example, if the user has previously ordered 'Spicy Chicken Curry,' use that data to generate a new 'Spicy Chicken Curry Wrap.'"

[1548] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1549] Step 1:

[1550] The server collects users' past order data, popular ingredient data, and emotional data. This includes cooking history, ordering ratings, and the user's facial and voice data. The server reads this data from the database and prepares it for analysis. It uses past order data, popular ingredient data, and emotional data as inputs and generates an integrated dataset that can be used for analysis as output.

[1551] Step 2:

[1552] The server uses the generated means to analyze the collected data and automatically generate new recipes using a generative AI model. This process also takes into account the user's past preferences and emotional data. The integrated dataset is used as input, and multiple new recipe suggestions are generated as output. Specifically, the server sends a prompt to the generative AI model and receives the returned recipe suggestions.

[1553] Step 3:

[1554] The server evaluates the generated recipe ideas using a method selected by the server. Evaluation criteria include inventory status, seasonality, and past feedback data. The generated recipe ideas and evaluation criteria data are used as input, and the recipe with the highest score is selected as output. Specifically, the server calculates a score based on the evaluation criteria for each recipe idea, and selects the recipe with the highest score.

[1555] Step 4:

[1556] Using the means instructed by the server, the cooking robot is instructed on specific cooking steps based on the selected recipe. The selected recipe is used as input, and commands including the cooking steps are generated and sent as output. Specifically, the cooking steps are extracted from the recipe data and instructions are sent to the cooking robot.

[1557] Step 5:

[1558] The server uses the means of serving to instruct the serving robot to transport and serve the cooked food to the specified table. It uses the cooking completion notification and serving information as input, and generates and sends serving instructions as output. Specifically, it receives the cooking completion notification from the cooking robot and sends the food location and table information to the serving robot.

[1559] Step 6:

[1560] The device collects feedback from users. After collecting the feedback, the server stores the data. The system uses the ratings and comments entered by users on the tablet device as input, generates feedback data as output, and stores it in a database. Specifically, the device collects the feedback information entered by users on the tablet device and sends it to the server.

[1561] Step 7:

[1562] The device uses an emotion engine to analyze the user's facial expression and voice data and generate emotion data. The device uses the user's facial expression and voice data acquired from a camera or microphone as input, and generates and saves emotion data as output. Specifically, the device captures the user's facial expression and voice with a camera or microphone during and after a meal, and the emotion engine analyzes this to generate emotion data, which is then sent to the server.

[1563] Step 8:

[1564] The server saves the collected feedback and emotion data and uses it for the next recipe generation. The feedback and emotion data are used as input, and reference data for the next recipe generation is generated and saved as output. Specifically, the server stores the collected data in a database and converts it into a usable format for the next analysis.

[1565] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1566] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1567] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1568] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1569] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1570] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1571] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1572] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1573] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1574] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1575] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1576] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1577] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1578] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1579] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1580] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1581] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1582] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1583] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1584] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1585] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1586] The following is further disclosed regarding the above embodiment.

[1587] (Claim 1)

[1588] a generating means;

[1589] A means of selection;

[1590] a means for indicating;

[1591] A means of serving food;

[1592] a means of collecting feedback;

[1593] A system including:

[1594] (Claim 2)

[1595] 2. The system according to claim 1, wherein said generating means analyzes past data and automatically generates a new recipe.

[1596] (Claim 3)

[1597] 2. The system according to claim 1, wherein the selecting means selects a recipe to be provided from the generated recipe proposals based on an evaluation criterion.

[1598]

[1599] "Example 1"

[1600] (Claim 1)

[1601] a means of collecting data;

[1602] A means for generating new proposals using a generative AI model; and

[1603] means for selecting from among the generated proposals based on evaluation criteria;

[1604] means for transmitting instructions based on the selected suggestions;

[1605] means for transporting the goods in accordance with the instructions;

[1606] a means of collecting feedback;

[1607] A system including:

[1608] (Claim 2)

[1609] 2. The system according to claim 1, wherein said generating means automatically generates new suggestions by analyzing past data, popularity data, and user opinions.

[1610] (Claim 3)

[1611] The system according to claim 1, wherein the selecting means evaluates the generated proposals based on stock availability, seasonality, and past opinions, and selects the proposal to be provided.

[1612] "Application Example 1"

[1613] (Claim 1)

[1614] a generating means;

[1615] A means of selection;

[1616] a means for indicating;

[1617] A means of delivery;

[1618] a means of collecting feedback;

[1619] A system including:

[1620] (Claim 2)

[1621] 2. The system according to claim 1, wherein said generating means analyzes past data, automatically generates new recipes, and notifies the user of the new recipes on a daily basis.

[1622] (Claim 3)

[1623] The system according to claim 1, wherein the selecting means selects a recipe to provide from the generated recipe proposals based on evaluation criteria and instructs the AI ​​robot on cooking procedures.

[1624] "Example 2: Combining Emotion Engines"

[1625] (Claim 1)

[1626] a means for generating new recipes using a generative AI model;

[1627] A means for selecting a recipe to be provided from the generated recipes based on evaluation criteria;

[1628] means for transmitting cooking instructions to a cooking device based on the selected recipe;

[1629] means for transmitting a serving instruction to the serving device after cooking is completed;

[1630] means for collecting ratings from users after a meal;

[1631] A means for collecting emotional data by analyzing the user's facial expressions and voice;

[1632] A system including:

[1633] (Claim 2)

[1634] The system of claim 1, wherein the generating means analyzes past recipe data, popular ingredient data, user feedback data, and sentiment data, and generates new recipes using a generative AI model.

[1635] (Claim 3)

[1636] The system according to claim 1, characterized in that the selecting means selects a recipe from the generated plurality of recipe ideas based on past feedback including ingredient availability, seasonality, and user emotional data.

[1637] "Application example 2 when combining emotion engines"

[1638] (Claim 1)

[1639] a generating means;

[1640] A means of selection;

[1641] a means for indicating;

[1642] A means of serving food;

[1643] a means of collecting feedback;

[1644] an emotion engine that recognizes the user's emotions;

[1645] A means for suggesting new dishes by taking into consideration the user's past order data, popular ingredient data, and emotion data;

[1646] A system including:

[1647] (Claim 2)

[1648] 2. The system according to claim 1, wherein said generating means analyzes past data and automatically generates a new recipe.

[1649] (Claim 3)

[1650] 2. The system according to claim 1, wherein the selecting means selects a recipe to be provided from the generated recipe proposals based on an evaluation criterion. [Explanation of symbols]

[1651] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a generating means; A means of selection; a means for indicating; A means of serving food; a means of collecting feedback; A system including:

2. 2. The system according to claim 1, wherein said generating means analyzes past data and automatically generates a new recipe.

3. 2. The system according to claim 1, wherein said selecting means selects a recipe to be provided from among the generated recipe proposals based on an evaluation criterion.

Images