System

Abstract

A system is provided.SOLUTION: A system comprising: means for providing an interface for a user to input preferences and conditions; means for using a generative AI model to output a generated recipe based on the user's input; means for operating a food printer to print a physical dish based on the recipe generated by the generative AI model; means for delivering the physical dish to the user; and means for collecting feedback provided by the user to improve the generative AI model.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional food delivery services have difficulty providing a wide variety of dishes in regions where there are few restaurants serving specific specialty dishes, resulting in regional disparities. Additionally, there is a problem in that users do not continue using the service because the dishes provided do not match their preferences or requirements. The present invention aims to solve these problems by providing a wide variety of specialized menus regardless of region, thereby encouraging users to continue using the service. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for providing an interface for a user to input preferences and conditions, a generative AI model that outputs a recipe generated based on the user's input, a food printer that prints a physical dish based on the recipe generated by the generative AI model, a means for delivering the physical dish to the user, and a means for collecting feedback provided by the user and improving the generative AI model. This makes it possible to continue providing dishes optimized for the user's preferences and conditions regardless of location. The system also includes a means for temporarily saving the preferences and conditions input by the user and a means for calling the generative AI model to generate a recipe.

[0006] "User" means an individual or organization that uses the system.

[0007] "Preferences" is information that indicates the characteristics of ingredients and dishes that the user likes.

[0008] "Conditions" are information that refer to specific requirements such as allergies or calorie restrictions that a user has.

[0009] "Interface" refers to the screen or format through which a user inputs information into a system.

[0010] A "generative AI model" is an artificial intelligence program that automatically generates recipes based on user input.

[0011] A "recipe" is a list of steps and ingredients for making a dish.

[0012] A "food printer" is a device that produces physical dishes based on a generated recipe.

[0013] "Delivery" refers to the act of delivering the printed recipe to a location specified by the user.

[0014] "Feedback" refers to the evaluation and opinions of the dishes provided by the user.

[0015] The term "system" refers to an entire configuration that integrates multiple means and functions included in the scope of this claim.

[0016] "Means" refers to a method or device provided for a system to achieve a specific function. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The present invention is a system that allows users to order food based on their specific preferences and conditions, creates a recipe for the food through a generative AI model, and delivers the physically printed food to the user. The present invention is specifically implemented as follows.

[0039] First, the user uses a dedicated application (web app or mobile app) to input their preferences and conditions (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.) This information is temporarily stored on the device and later sent to the server.

[0040] The server receives the information sent by the user and calls up a generative AI model based on that information. This generative AI model is trained using multiple recipe data sets and generates new recipes optimized for the user's preferences.

[0041] The server then sends the generated recipe to the food printer, which then generates a physical dish based on the recipe. Specifically, the food printer automatically mixes the specified ingredients and follows the cooking instructions to complete the dish.

[0042] After the food is ready, the server receives a notification from the food printer and issues a delivery instruction to a local delivery center. Multiple drivers are waiting at the delivery center, and an available driver will deliver the food to the user's location.

[0043] After the delivery is complete, the user uses the app again to provide feedback on the food. The feedback can cover a variety of topics, including the food's taste, appearance, and overall satisfaction. This feedback is sent to the server and used to improve the generative AI model. Specifically, the feedback data is used to retrain the generative AI model and reflect it in future recipe generation.

[0044] As a concrete example, suppose a user requests a "high-protein, low-calorie smoothie to drink after sports." The user inputs these requirements into the application and submits it. The server receives the request and generates an optimal smoothie recipe based on a generative AI model. The generated recipe is sent to a food printer, which creates a smoothie using the necessary ingredients (e.g., protein powder, low-fat yogurt, blueberries, etc.). The created smoothie is promptly delivered to the user. After enjoying the smoothie, the user can provide feedback on the taste and effects, which will be used to help with future orders.

[0045] As described above, the system of the present invention provides an environment where users can easily enjoy meals optimized to their preferences and conditions, regardless of where they live. This reduces regional disparities in food delivery services and improves user satisfaction and frequency of use.

[0046] The processing flow will be explained below.

[0047] Step 1:

[0048] The user opens the application. The user uses an interface to input their preferences and conditions (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.). The information entered by the user is temporarily stored on the device.

[0049] Step 2:

[0050] The device sends the user's preferences and requirements to the server, including the user's personal information and details of the desired dish.

[0051] Step 3:

[0052] The server analyzes the data received from the user and calls a generative AI model. The generative AI model generates a recipe that takes into account the user's preferences and conditions. This recipe is based on a model trained on multiple recipe data.

[0053] Step 4:

[0054] The server sends the generated recipe, which includes the ingredients, cooking steps, and quantities, to the food printer.

[0055] Step 5:

[0056] The food printer prints physical meals based on the recipe it receives, automatically mixing ingredients like protein powder, low-fat yogurt, and blueberries, and cooking them according to the instructions.

[0057] Step 6:

[0058] Once the food printer has printed the meal, it notifies the server, which then sends the information to a local distribution center.

[0059] Step 7:

[0060] Multiple drivers are waiting at the delivery center. The server issues printed delivery instructions for the food to an available driver. The driver then picks up the food and delivers it to the address specified by the user.

[0061] Step 8:

[0062] The user receives the food and provides feedback on it through the application, including the taste, appearance, and overall satisfaction with the food.

[0063] Step 9:

[0064] The terminal sends feedback from the user to the server, which collects and analyzes this feedback.

[0065] Step 10:

[0066] The server retrains the generative AI model based on the collected feedback, a process that ensures that future recipes are more tailored to the user's preferences.

[0067] Through the above steps, the system of the present invention can provide meals optimized to the preferences and conditions of the user regardless of the area where the user lives, thereby improving user satisfaction and frequency of use.

[0068] Example 1

[0069] 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."

[0070] Conventional food delivery systems have made it difficult for users to easily order food based on their specific preferences and conditions, and then automatically generate and deliver it. They also lacked a mechanism for improving recipes based on user feedback. As a result, it was difficult to improve user satisfaction and meet individual needs.

[0071] 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.

[0072] In this invention, the server includes means for providing an interface for users to input preferences and conditions, means for using a generative AI model that outputs recipes generated based on the user's input, means for operating a food printer that generates physical food based on the recipes generated by the generative AI model, means for collecting feedback provided by the user and improving the generative AI model, means for temporarily saving the preferences and conditions input by the user, means for calling the generative AI model to generate recipes, and means for generating prompt sentences for inputting user information into the generative AI model. This not only enables users, wherever they live, to easily order and enjoy food optimized for their preferences and conditions, but also enables the service to be continuously improved based on the provided feedback.

[0073] "User" refers to any person or entity that uses the System to order food based on specific preferences and requirements.

[0074] "Interface" refers to software, such as a web or mobile application, that provides a means for users to input their specific preferences or requirements.

[0075] "Generative AI model" refers to the artificial intelligence algorithm used to generate optimal recipes based on user input.

[0076] A "food printer" refers to a device that automatically produces physical food products based on recipes generated by a generative AI model.

[0077] "Feedback" refers to ratings and opinions provided by users regarding food quality and service.

[0078] "Server" refers to a computer system that receives and stores information from users and performs various processes such as calling up generative AI models.

[0079] A "prompt sentence" refers to the instructions or questions conveyed to a generative AI model based on user input information.

[0080] "Storage means" refers to a storage device or database for temporarily storing preferences and conditions entered by the user.

[0081] The present invention is a system that allows users to order food based on their specific preferences and requirements, creates a recipe for the food through a generative AI model, and delivers the physically printed food to the user. This system is implemented using the following specific hardware and software:

[0082] First, users input their preferences and conditions using a dedicated interface (web application or mobile application). This interface allows users to easily enter detailed information such as favorite ingredients, disliked ingredients, allergy information, and calorie restrictions.

[0083] For example, if a user requests a "high-protein, low-calorie smoothie to drink after sports," the following prompt text might be entered:

[0084] "Make a high-protein, low-calorie smoothie to drink after exercise. It must meet the following criteria: Favorite ingredients: blueberries, bananas, low-fat yogurt. Disliked ingredients: spirulina. Allergy information: nut allergy. Calorie limit: 200 calories or less."

[0085] The terminal (user's device) temporarily stores the input information and then transmits it to the server, which receives and analyzes the user's input information sent from the terminal.

[0086] The server then calls a generative AI model, which uses the user's input as a prompt, and the model (which may include natural language processing libraries or machine learning algorithms) generates recipes optimized for the user's preferences based on a vast amount of recipe data.

[0087] The generated recipe is sent from the server to the food printer in a standard format such as JSON, which then analyzes the recipe data and automatically mixes the necessary ingredients. Physical food is then produced according to the specific cooking instructions.

[0088] When the food is ready, the food printer sends a completion notification to the server. The server receives this notification and issues a delivery instruction to a local distribution center. The distribution center then issues a delivery instruction to an available driver based on the received notification and delivers the food to the user.

[0089] After enjoying the delivered food, the user again uses the interface to provide feedback, which can include various aspects such as the food's taste, appearance, and overall satisfaction. This feedback data is sent to the server and used to retrain the generative AI model.

[0090] In this way, the present invention provides an environment where users can easily order and enjoy food optimized for their preferences and conditions, regardless of where they live. This system can mitigate regional disparities in food delivery and improve user satisfaction and frequency of use.

[0091] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0092] Step 1:

[0093] The user launches a dedicated interface (web application or mobile application) and inputs their preferences and conditions. Input items include favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc. An example of a specific prompt is, "Make a high-protein, low-calorie smoothie to drink after exercise. Please meet the following conditions: Favorite ingredients: blueberries, bananas, low-fat yogurt. Disliked ingredients: spirulina. Allergy information: nut allergy. Calorie restrictions: 200 calories or less." This information is sent to the server by the user's operation.

[0094] Input: User preferences and conditions

[0095] Output: User information sent to the server

[0096] Step 2:

[0097] The device temporarily stores the information entered by the user and then transmits it to the server via a connection, specifically by using an HTTP POST request to transfer the data to the server, and then waits for a response to confirm that the information was sent correctly.

[0098] Input: Preferences and conditions data entered by the user

[0099] Output: User information sent to the server

[0100] Step 3:

[0101] The server receives user information sent from the device, analyzes this information, and generates a prompt that matches the user's request. This prompt is then passed to the generative AI model.

[0102] Input: User information sent from the device

[0103] Output: The prompt passed to the generative AI model

[0104] Step 4:

[0105] The server calls the generative AI model and inputs a prompt based on the user's information. The generative AI model generates the optimal recipe based on a huge amount of recipe data. Specifically, it uses natural language processing libraries and machine learning algorithms.

[0106] Input: prompt statement

[0107] Output: A new recipe from a generative AI model

[0108] Step 5:

[0109] The server sends the generated recipe data to the food printer, which receives the data, analyzes the recipe, and automatically mixes the necessary ingredients and creates the dish according to the specified cooking procedure.

[0110] Input: Recipe data from a generative AI model

[0111] Output: Physical food produced by a food printer

[0112] Step 6:

[0113] The food printer sends a message to the server notifying it that the food is ready. The server receives this notification and issues a delivery instruction to a local delivery center. The delivery center then assigns an available driver to pick up the food and deliver it to the user.

[0114] Input: Completion notification from food printer

[0115] Output: Delivery instructions to the distribution center

[0116] Step 7:

[0117] The user receives the delivered food and provides feedback on the food through the application, including taste, appearance, and overall satisfaction. The feedback is then sent to the server.

[0118] Input: User feedback

[0119] Output: Feedback data sent to the server

[0120] Step 8:

[0121] The server collects feedback data received from users and uses this data to retrain the generative AI model, which is then reflected in future recipe generation, resulting in continuous improvement of the service.

[0122] Input: User feedback data

[0123] Output: Improved recipes from a retrained generative AI model

[0124] (Application example 1)

[0125] 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."

[0126] Conventional food delivery systems have difficulty providing individually customized meals based on the user's preferences and conditions, leading to issues such as lower user satisfaction and reduced frequency of use due to regional disparities. Furthermore, there are also issues with the effort and efficiency involved in preparing and delivering meals, making it impossible to provide an environment that users can easily use.

[0127] 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.

[0128] In this invention, the server includes: means for providing an interface for a user to input preferences and conditions; means for using a generative AI model to output a recipe generated based on the user's input; means for operating a food printer to print a physical dish based on the recipe generated by the generative AI model; means for delivering the physical dish to the user; means for collecting feedback provided by the user and improving the generative AI model; and means including an application for generating recipes based on the preferences and conditions input by the user and managing delivery. This enables users to easily order and receive dishes optimized for their individual preferences and conditions, mitigating regional disparities in food delivery and improving user satisfaction and frequency of use.

[0129] A "user" is an entity that orders food based on specific preferences or requirements.

[0130] An "interface" is a means by which a user inputs preferences and requirements.

[0131] A "generative AI model" is an artificial intelligence technology that generates optimal recipes based on user input information.

[0132] A "food printer" is a device that automatically cooks and prints physical dishes according to a generated recipe.

[0133] "Delivery means" refers to the means or system for delivering the created meal to the user.

[0134] "Feedback" is user-provided evaluation information about a dish, and is data used to improve the generative AI model.

[0135] An "application" is software that allows a user to input food preferences and requirements and place an order.

[0136] This invention is a system that allows users to order food based on their specific preferences and requirements, creates a recipe for it through a generative AI model, and delivers the physically printed food to the user using a food printer.

[0137] System configuration and operation

[0138] 1. User Input Interface

[0139] Users use a dedicated application (smartphone application or web application) to input their cooking preferences and conditions (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.) This information is temporarily stored on the user's device and then sent to the server.

[0140] 2. Recipe generation using generative AI models

[0141] The server receives the information sent by the user and calls a generative AI model based on that information. This generative AI model is trained using multiple recipe data sets and generates new recipes optimized for the user's preferences. This process uses natural language processing and deep learning technologies and is executed on the server.

[0142] 3. Food printing to create dishes

[0143] The generated recipe is sent from the server to the food printer, which then automatically mixes the specified ingredients based on the recipe and completes the dish according to the instructions. The food printer has advanced cooking technology and can handle a variety of ingredients.

[0144] 4. Food delivery

[0145] Once the food is ready, the server issues a delivery order. Delivery is made from a local distribution center with multiple drivers waiting. An available driver will deliver the food to the user. The delivery process is tracked in real time, and users can check the current delivery status through the application.

[0146] 5. Gathering feedback and improving the generative AI model

[0147] After receiving the dish, the user uses the application to provide feedback on the dish, including the taste, appearance, and overall satisfaction level, which is sent to the server. This feedback data is used to retrain the generative AI model and is reflected in future recipe generation.

[0148] Hardware and Software Use

[0149] Hardware: smartphones, servers, food printers, delivery vehicles

[0150] Software: Django (web framework), generative AI model (natural language processing technology), REST API (calling the generative AI model)

[0151] Specific examples

[0152] If the user requests a "low carb, gluten-free dinner," the application will generate the following prompt:

[0153] I'd like a low carb, gluten free dinner please.

[0154] This prompt is sent to a generative AI model, and the generated recipe is printed as a meal using a food printer and delivered. The generated recipe is a low-carb, gluten-free menu based on protein-rich chicken breast and vegetables. After receiving the meal, the user provides feedback through the application, such as "The taste was very good, but I wish there was a little more," and this feedback is reflected in the next recipe generation.

[0155] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0156] Step 1:

[0157] The user uses the device to input preferences and conditions (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.) into the application. The device temporarily stores this information and sends it to the server. The input data is in text format and includes specific information about the user's preferences.

[0158] Step 2:

[0159] The server generates a prompt for the generative AI model based on the user's preferences and conditions sent from the device and sends it. The prompt is text that is automatically generated based on the user's request. The generative AI model receives this prompt and generates the optimal recipe. Data processing involves converting the user's preferences and conditions into a format suitable for the generative AI model.

[0160] Step 3:

[0161] The generated recipe is sent back to the server, which interprets the recipe content and sends recipe instructions to the food printer. The recipe data includes the required ingredients, cooking steps, cooking time, etc. The server converts this information into a format compatible with the food printer.

[0162] Step 4:

[0163] The food printer automatically mixes the specified ingredients based on the recipe instructions received from the server and creates the dish according to the cooking steps, measuring the amount of food ingredients and operating automated cooking equipment for each cooking step.

[0164] Step 5:

[0165] Once the food is ready, the food printer sends a notification to the server. When the server receives the notification, it issues a delivery instruction to the delivery center and assigns an available driver. During this process, it references the delivery center's database to select the most suitable driver.

[0166] Step 6:

[0167] The delivery driver will receive the requested food and deliver it to the user. The delivery progress is reported to the server in real time, and the user can check the delivery status through the application.

[0168] Step 7:

[0169] After receiving the food, the user provides feedback using the application. The feedback includes evaluation data on the taste, appearance, quantity, satisfaction level, etc. of the food. The device then sends this to the server.

[0170] Step 8:

[0171] The server accumulates the received feedback data and uses it to retrain the generative AI model, improving its accuracy and reflecting it in future recipe generation.

[0172] The above are the specific processing steps of the system that realizes the application example.

[0173] 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.

[0174] The present invention is a system that uses a generative AI model to create dishes based on a user's preferences and conditions, and further combines it with an emotion engine that recognizes the user's emotions. This makes it possible to provide dishes that are more accurately tailored to the user's preferences and emotions. The present invention is specifically implemented as follows.

[0175] First, a user opens an application (web app or mobile app) and uses an interface to input preferences and conditions (likes, dislikes, allergies, calorie restrictions, etc.) Dedicated input fields, checkboxes, and selection menus are provided for this input task.

[0176] The information entered by the user is temporarily stored on the device and then sent to a server, including details about the user's personal information and cooking preferences.

[0177] The server analyzes the user's preferences and conditions data and calls up a generative AI model. This generative AI model has been trained from multiple recipe data and automatically generates the optimal recipe based on the user's input conditions.

[0178] After the recipe is generated, the server calls the emotion engine to analyze the user's emotions. The emotion engine analyzes the user's facial expressions, voice, text data, etc. to recognize the user's emotional state. This emotion data is also reflected in the recipe generation process described above.

[0179] The server then sends the generated recipe to the food printer, which automatically mixes the specified ingredients and creates a physical dish according to the cooking instructions. For example, if a user requests a "soup to eat when you want to relax," the generative AI model will select ingredients and cooking methods that will enhance the relaxing effect based on the user's emotions recognized by the emotion engine.

[0180] Once the printed meal is ready, the server sends the information to a local distribution center, where multiple drivers are waiting, and an available driver will deliver the meal to the address specified by the user.

[0181] After the delivery is complete, the user again uses the application to provide feedback on the food, which may include the food's taste, appearance, overall satisfaction, and emotional response to the entire experience. This feedback is sent to and collected by the server.

[0182] The server retrains the generative AI model based on user feedback and data from the emotion engine, so that the next time it generates a recipe, it will provide dishes that better match the user's preferences and emotions.

[0183] As a concrete example, if a user requests a "light meal that helps relieve stress," the emotion engine will recognize that the user is under stress from their facial expressions and voice. Based on this information, the generative AI model will select ingredients and cooking methods that are effective in relieving stress and generate the optimal recipe. The food printer will create a meal based on the recipe and deliver it to the user. Feedback will add previously unrecognized stress factors and taste preferences, and these will be reflected in future services.

[0184] As described above, the present invention is a system that provides more personalized food delivery by combining emotion recognition using an emotion engine with user preferences and conditions, which can significantly improve user satisfaction and frequency of use.

[0185] The processing flow will be explained below.

[0186] Step 1:

[0187] The user opens the application and enters their preferences and requirements (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.) through the interface. Input operations are performed using text boxes, check boxes, drop-down menus, etc.

[0188] Step 2:

[0189] The device temporarily stores the preferences and conditions entered by the user and then transmits them to the server, including all the information entered.

[0190] Step 3:

[0191] The server processes the received user data and invokes the generative AI model, which uses pre-trained data to create optimal recipes based on the user's preferences and conditions.

[0192] Step 4:

[0193] The server passes the generated recipe information to the emotion engine, which acquires and analyzes emotion data based on the user's facial expressions, voice, or text to recognize the user's emotional state.

[0194] Step 5:

[0195] The server uses the emotional data obtained from the emotion engine to optimize the recipe, specifically selecting ingredients and cooking methods that best suit the user's emotional state and fine-tuning the recipe.

[0196] Step 6:

[0197] The server sends the optimized recipe to the food printer, including details such as the specific ingredient list, cooking instructions, and quantities required.

[0198] Step 7:

[0199] The food printer prints physical dishes based on the received recipe, for example, automatically mixing the specified ingredients and following the cooking instructions to complete the dish.

[0200] Step 8:

[0201] Once the food printer has completed the cooking process, it notifies the server, which then sends the information to a local distribution center.

[0202] Step 9:

[0203] Multiple drivers are waiting at the delivery center. The server sends printed delivery instructions to the appropriate driver, who then delivers the food to the address specified by the user.

[0204] Step 10:

[0205] After receiving their food, users use the application again to provide feedback on the food, including its taste, appearance, overall satisfaction, and emotional response to the entire experience.

[0206] Step 11:

[0207] The device sends the user's feedback to the server, which includes detailed evaluation information and emotion data.

[0208] Step 12:

[0209] The server retrains the generative AI model based on the collected feedback and emotional data, allowing it to provide dishes that better suit the user's preferences and emotions in future recipe generation.

[0210] Through these steps, the system of the present invention can provide more personalized food by incorporating emotion recognition in addition to user preferences and conditions, thereby improving user satisfaction and frequency of use.

[0211] Example 2

[0212] 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."

[0213] Conventional systems were unable to consider the user's emotional state when providing food based on the user's preferences and conditions. As a result, they were unable to provide food that matched the user's momentary mood or emotions, potentially reducing user satisfaction. Furthermore, mechanisms for effectively utilizing user feedback to improve generative AI models were limited, meaning that subsequent food offerings may not necessarily match the user's preferences or emotions. To address these issues, a more personalized food offering mechanism that reflects the user's emotional data is needed.

[0214] 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 means for providing an interface for a user to input preferences and conditions, means for using a generative AI model to output a recipe generated based on the user's input, and means for invoking an emotion engine to reflect the user's emotional data in the recipe generated by the generative AI model. This enables the provision of more personalized dishes that reflect not only the user's preferences and conditions but also their emotional state. Furthermore, by combining means for collecting feedback provided by users and improving the generative AI model, it is expected that the accuracy of the generative AI model and user satisfaction will be improved.

[0215] A "user" is an individual who uses the system to make a food request.

[0216] An "interface" is an input device or software screen provided for a user to input preferences and requirements.

[0217] A "generative AI model" is an artificial intelligence model that automatically generates optimal recipes based on input data.

[0218] A "food printer" is a device that creates physical dishes using specified ingredients based on a recipe generated by a generative AI model.

[0219] An "emotion engine" is a program or system that analyzes a user's facial expressions, voice, and text data to recognize their emotional state.

[0220] "Feedback" refers to ratings and comments about the taste and appearance of the food provided by the user, overall satisfaction, and emotional response.

[0221] A "server" is a computer system that receives and analyzes input data from users, and then calls generative AI models and emotion engines for processing.

[0222] "Delivery means" refers to a means for physically delivering the prepared meal to the address specified by the user.

[0223] "Temporary storage" refers to the short-term storage of data on preferences and conditions entered by the user.

[0224] "Data analysis" is the process of analyzing user input data, converting it into an appropriate format, and extracting the required information.

[0225] MODE FOR CARRYING OUT THE INVENTION

[0226] The present invention is a system that provides optimal dishes based on a user's preferences and conditions. The system aims to improve user satisfaction by analyzing the user's emotions and providing more personalized dishes. Specific embodiments for implementing the present invention are described below.

[0227] System Overview

[0228] First, a user opens an application (web app or mobile app) on their smartphone or computer. This application provides an interface for the user to input their preferences and conditions. The interface provides input fields, checkboxes, and drop-down menus for favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.

[0229] The information entered by the user is temporarily stored in the device's local storage or the browser's session storage. This input data is then sent to a server, where a computer system is located to analyze and process the data. This processing can be performed using cloud technologies such as AWS Lambda or Google Cloud Functions.

[0230] The server analyzes the received user data and calls up a generative AI model, which has been trained in advance using multiple recipe data sets and automatically generates optimal recipes based on the user's input conditions.

[0231] The server then invokes an emotion engine, which uses facial expressions, voice, and text data to analyze the user's emotional state. The emotion engine could be, for example, Microsoft Azure's Emotion API. The emotion data is also reflected in the generated recipe. For example, if a user wants to relax, the server can select ingredients and cooking methods that match that emotional state.

[0232] The generated optimal recipe information is sent from the server to the food printer, which automatically mixes the specified ingredients and creates a physical dish using 3D food printing technology. The information is then sent in real time to a local distribution center, where it is delivered to the user's specified address via a delivery method.

[0233] After the food is delivered to the user, the user uses the application to provide feedback on the food, which can range from taste and appearance to overall satisfaction and emotional response. The feedback is sent to the server, and the collected data is used to retrain the generative AI model, allowing it to provide a more personalized and optimal dish for future meals.

[0234] Specific examples

[0235] Consider a case where a user opens the app and requests a "stress-relieving snack." The emotion engine recognizes that the user is under stress from their facial expressions and voice. Based on this information, the generative AI model selects ingredients and cooking methods that are effective in relieving stress, generating a recipe such as herbal tea or nut bars. This is then printed using a food printer and delivered to the user. The user provides feedback on the food that arrives, and this information is reflected in future service plans.

[0236] Prompt Sentence Examples

[0237] An example of a prompt is as follows:

[0238] User: Opens the app and enters preferences and requirements.

[0239] Device: Temporarily save user information.

[0240] Server: Analyzes the data and invokes the generative AI model.

[0241] Generative AI model: Automatically generates optimal recipes.

[0242] Server: Calls the emotion engine and recognizes the user's emotional state.

[0243] Server: Sends the generated recipe to the food printer.

[0244] Food printer: Create your food.

[0245] Delivery point: delivers food to the user's address.

[0246] Users: Provide feedback.

[0247] Server: Retrain the generative AI model based on feedback and emotion data.

[0248] In this way, the embodiment of the present invention combines emotion recognition by the emotion engine with user preferences and conditions to provide more personalized food, which is expected to significantly improve user satisfaction and frequency of use.

[0249] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0250] Step 1:

[0251] The user opens the application and inputs their preferences and requirements. The application provides an interface for inputting their favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc. The user's input information is collected via text fields and check boxes. The input data is treated as information on preferences and requirements.

[0252] Input: User preferences and conditions

[0253] Output: User input data (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.)

[0254] Step 2:

[0255] The device temporarily stores the user's input data. The input data is stored in local storage or the browser's session storage and prepared for transmission to the server. The stored data may also be backed up to ensure reliability.

[0256] Input: User-entered data

[0257] Output: Temporarily saved data

[0258] Step 3:

[0259] The device sends the temporarily stored data to the server. Data such as the user's preferences and conditions are sent to the server via an HTTP request. Encryption technology such as SSL is used to ensure secure communication.

[0260] Input:Temporarily saved data

[0261] Output: Data sent to the server

[0262] Step 4:

[0263] The server analyzes the data received from the user. During the analysis process, the data items are appropriately classified and the necessary information is extracted. For example, the data can be divided into a list of favorite ingredients and a list of allergy information. Scripts written in Python or Java are often used for data analysis.

[0264] Input: Data sent to the server

[0265] Output: Categorized and organized data items

[0266] Step 5:

[0267] The server calls the generative AI model and generates a recipe based on the user's criteria. The generative AI model selects the optimal recipe from a large amount of recipe data it has learned in the past. To call the model, a request is sent via an API. Machine learning technology is used in the generation process.

[0268] Input: Categorised and organised data items

[0269] Output: The generated optimal recipe

[0270] Step 6:

[0271] The server calls the emotion engine to analyze the user's emotional state. The emotion engine inputs the user's facial expressions, voice, and text data to recognize the emotional state. For example, it uses data obtained from a camera and microphone to determine whether the user is stressed or relaxed.

[0272] Input: User's facial expressions, voice, and text data

[0273] Output: Analyzed user emotion data

[0274] Step 7:

[0275] The server then further adjusts the generated recipe based on the emotional data. The generative AI model evaluates the emotional data and selects ingredients and cooking methods that suit the user's emotional state. For example, it adds relaxing herbs or warm soup.

[0276] Input: Generated optimal recipe and sentiment data

[0277] Output: The final recipe reflecting the sentiment data

[0278] Step 8:

[0279] The server sends the final recipe to the food printer. The final recipe information is sent to the food printer as a data set including the ingredients list and cooking instructions. The food printer receives this data and automatically mixes the ingredients and cooks the food.

[0280] Input: Final recipe reflecting sentiment data

[0281] Output: Recipe data sent to the food printer

[0282] Step 9:

[0283] The food printer creates the meal based on the final recipe, using 3D food printing technology to build the ingredients layer by layer, with temperature and timing controlled according to the cooking instructions.

[0284] Input: Recipe data sent to the food printer

[0285] Output: A physically created dish

[0286] Step 10:

[0287] The server sends information about the completed meal to the delivery center, which then prepares the meal for delivery and issues delivery instructions to the driver. Information is updated in real time and managed to ensure efficient delivery.

[0288] Input: Information about the finished dish

[0289] Output: Information notification to delivery center

[0290] Step 11:

[0291] The driver delivers the food to the address specified by the user. The delivery system selects the optimal route based on the user's address information and provides navigation information to the driver. After delivery is complete, the user receives a delivery completion notification.

[0292] Input: Delivery instructions from the distribution center

[0293] Output: The meal delivered to the user

[0294] Step 12:

[0295] The user uses the application to provide feedback on the dish, including the dish's taste, appearance, overall satisfaction, and emotional response. Feedback data is entered in the form of text and choices.

[0296] Input: User ratings and opinions

[0297] Output: Feedback data

[0298] Step 13:

[0299] The server collects and analyzes the feedback provided by users. The feedback is used to evaluate the quality of the food and user satisfaction. The analysis results are used to generate future recipes.

[0300] Input: Feedback data

[0301] Output: Analysis results and evaluation data

[0302] Step 14:

[0303] The server retrains the generative AI model based on the feedback and emotion data. The retraining process improves the accuracy and user adaptability of the generative AI model, which in turn improves the accuracy of recipe generation from the next time onwards.

[0304] Input: Analysis results and feedback data

[0305] Output: Retrained generative AI model

[0306] (Application example 2)

[0307] 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."

[0308] Conventional food delivery services were able to provide food based on the user's preferences and conditions, but they did not provide services that took into account the user's emotional state. As a result, they were unable to suggest or provide the optimal dish based on the user's emotional state, making it difficult to improve user satisfaction. In addition, feedback on the delivered dish was not sufficiently reflected in the next dish suggestions, making it difficult to improve the quality of the service.

[0309] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for providing an interface for the user to input preferences and conditions, means for using a generative AI model that outputs a recipe generated based on the user's input, means for using an emotion engine that recognizes the user's emotional state, means for reflecting emotion data obtained from the emotion engine in the generative AI model, means for operating a cooking machine that prints a physical dish based on the recipe generated by the generative AI model, delivery means for delivering the physical dish to the user, and means for collecting feedback provided by the user and improving the generative AI model. This makes it possible to provide food that takes into account the user's emotional state in addition to their preferences and conditions, thereby improving user satisfaction and the quality of food delivery services.

[0310] "User" refers to an individual who uses the system to order food and input their preferences and requirements.

[0311] "Interface" refers to the screens and tools that users use to input information into a system.

[0312] A "generative AI model" refers to an artificial intelligence model that automatically generates optimal recipes based on the user's preferences and conditions.

[0313] An "emotion engine" refers to software or algorithms that recognize a user's emotional state from facial expressions, voice, text data, etc.

[0314] "Emotion data" refers to information about a user's emotional state obtained by an emotion engine.

[0315] "Cooking machine" refers to a device that prints or cooks physical dishes based on recipes generated by generative AI models.

[0316] "Delivery method" refers to the mechanism or method for delivering the created meal to the address specified by the user.

[0317] "Feedback" refers to the action of a user inputting their opinion or evaluation regarding the food or service provided.

[0318] "Server" refers to the computer system that receives and analyzes user input data and runs the generative AI model and emotion engine.

[0319] A specific embodiment of a system for realizing an application example of the present invention will be described below. The present invention is a system for providing optimal dishes based on a user's preferences and emotional state, and includes a server, an emotion engine, a generative AI model, a cooking machine, and a delivery means.

[0320] Overall system configuration

[0321] 1. User Device

[0322] Interface: Provides an application that allows users to input their preferences and conditions. A typical example is a smartphone app. Users input their favorite ingredients, disliked ingredients, allergy information, calorie restrictions, emotional state, etc.

[0323] 2. Server

[0324] Data Receipt and Storage: Information entered by the user is received and temporarily stored.

[0325] Generative AI model: Runs an artificial intelligence model that generates optimal recipes based on user preferences and conditions.

[0326] Emotion engine: Recognizes emotions from user input data (facial expressions, voice, text) and obtains emotional data.

[0327] Data integration: The acquired emotional data is fed into the generative AI model to generate recipes based on the emotional state.

[0328] 3. Cooking machine

[0329] Food Printer: Operates an automated cooking machine that creates physical food based on recipes sent from the server, allowing for precise mixing and cooking of ingredients.

[0330] 4. Delivery method

[0331] Delivery people and drones: The finished meal is delivered to the address specified by the user, either by automated drones or human delivery people.

[0332] 5. Feedback System

[0333] Rating collection: Provides an interface for users to enter feedback on the food and service provided.

[0334] Data analysis and learning: Retrain the generative AI model based on collected feedback to improve the quality of future recipe generation.

[0335] Specific examples

[0336] The user opens the smartphone app and enters the following information:

[0337] User name: Sato

[0338] Favorite ingredients: chicken, tomatoes

[0339] Disliked ingredient: Fish sauce

[0340] Allergens: nuts

[0341] Calorie restriction: 600 kcal or less

[0342] Current Emotion: High Stress

[0343] Based on this, the prompt would look like this:

[0344] User Sato is currently feeling stressed. Please suggest a dish that uses chicken and tomatoes, is nut-free, and is under 600 kcal. It should not contain fish sauce.

[0345] The server receives this data and generates an optimal recipe using the generative AI model and emotion engine. It then sends the recipe to the cooking machine, which creates the physical dish. The finished dish is delivered to the user via a delivery vehicle, and the user again provides feedback using the app. This feedback is collected by the server and used to retrain the generative AI model.

[0346] The key hardware and software used throughout the process include smartphones, servers, generative AI models, emotion engines, food printers, delivery drones and delivery people.

[0347] This allows for the provision of high-quality food that takes into account not only the user's preferences and conditions, but also their emotional state.

[0348] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0349] Step 1:

[0350] The user enters preferences and requirements.

[0351] Input: The user enters their favorite ingredients, disliked ingredients, allergy information, calorie restrictions, and current emotional state into the smartphone app.

[0352] How it works: An application on a user's device provides specialized input fields, checkboxes, and selection menus.

[0353] Output: User-entered preferences and conditions data.

[0354] Step 2:

[0355] Send and temporarily save input data.

[0356] Input: Data entered by the user through the application.

[0357] Operation: The user terminal temporarily stores this data and sends it to the server.

[0358] Output: User preferences and requirements data transferred to the server.

[0359] Step 3:

[0360] Recipe generation using generative AI models.

[0361] Input: User preferences and requirements data stored on the server.

[0362] How it works: The server invokes a generative AI model to generate the optimal recipe based on the user's preferences and conditions.

[0363] Output: The generated recipe data.

[0364] Step 4:

[0365] Acquiring emotion data.

[0366] Input: Data about the emotional state submitted by the user.

[0367] How it works: The server uses an emotion engine to analyze the user's emotional state, which may involve facial recognition, speech analysis, or text analysis.

[0368] Output: Emotion data from the emotion engine.

[0369] Step 5:

[0370] Reflecting emotional data.

[0371] Input: Generated recipe data and sentiment data.

[0372] How it works: The server applies the emotional data to the generative AI model and re-optimizes the recipe.

[0373] Output: Recipe data optimized for emotional states.

[0374] Step 6:

[0375] Cooking food using a cooking machine.

[0376] Input: Optimized recipe data.

[0377] Operation: The server sends the optimized recipe data to the cooking machine (food printer), which then automatically mixes the specified ingredients and prepares the dish according to the recipe.

[0378] Output: The finished physical dish.

[0379] Step 7:

[0380] Arrange delivery.

[0381] Input: The finished dish and the user's address information.

[0382] How it works: The server sends the completed meal and address information to a delivery vehicle (delivery person or drone) to arrange for delivery.

[0383] Output: The meal delivered to the user's address.

[0384] Step 8:

[0385] Get feedback.

[0386] Input: User's ratings and opinions about the food and service provided.

[0387] How it works: The user enters feedback through a smartphone app, which then sends this feedback to the server.

[0388] Output: User feedback data stored on the server.

[0389] Step 9:

[0390] Retraining generative AI models.

[0391] Input: Feedback data and emotion data.

[0392] How it works: The server retrains the generative AI model based on the collected feedback and emotion data, improving the accuracy of future recipe generation.

[0393] Output: An improved generative AI model.

[0394] The above is the specific processing flow of this system.

[0395] 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.

[0396] 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.

[0397] 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.

[0398] [Second embodiment]

[0399] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0400] 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.

[0401] 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).

[0402] 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.

[0403] 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.

[0404] 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).

[0405] 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. 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.

[0406] 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.

[0407] 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.

[0408] 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.

[0409] 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.

[0410] 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."

[0411] The present invention is a system that allows users to order food based on their specific preferences and conditions, creates a recipe for the food through a generative AI model, and delivers the physically printed food to the user. The present invention is specifically implemented as follows.

[0412] First, the user uses a dedicated application (web app or mobile app) to input their preferences and conditions (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.) This information is temporarily stored on the device and later sent to the server.

[0413] The server receives the information sent by the user and calls up a generative AI model based on that information. This generative AI model is trained using multiple recipe data sets and generates new recipes optimized for the user's preferences.

[0414] The server then sends the generated recipe to the food printer, which then generates a physical dish based on the recipe. Specifically, the food printer automatically mixes the specified ingredients and follows the cooking instructions to complete the dish.

[0415] After the food is ready, the server receives a notification from the food printer and issues a delivery instruction to a local delivery center. Multiple drivers are waiting at the delivery center, and an available driver will deliver the food to the user's location.

[0416] After the delivery is complete, the user uses the app again to provide feedback on the food. The feedback can cover a variety of topics, including the food's taste, appearance, and overall satisfaction. This feedback is sent to the server and used to improve the generative AI model. Specifically, the feedback data is used to retrain the generative AI model and reflect it in future recipe generation.

[0417] As a concrete example, suppose a user requests a "high-protein, low-calorie smoothie to drink after sports." The user inputs these requirements into the application and submits it. The server receives the request and generates an optimal smoothie recipe based on a generative AI model. The generated recipe is sent to a food printer, which creates a smoothie using the necessary ingredients (e.g., protein powder, low-fat yogurt, blueberries, etc.). The created smoothie is promptly delivered to the user. After enjoying the smoothie, the user can provide feedback on the taste and effects, which will be used to help with future orders.

[0418] As described above, the system of the present invention provides an environment where users can easily enjoy meals optimized to their preferences and conditions, regardless of where they live. This reduces regional disparities in food delivery services and improves user satisfaction and frequency of use.

[0419] The processing flow will be explained below.

[0420] Step 1:

[0421] The user opens the application. The user uses an interface to input their preferences and conditions (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.). The information entered by the user is temporarily stored on the device.

[0422] Step 2:

[0423] The device sends the user's preferences and requirements to the server, including the user's personal information and details of the desired dish.

[0424] Step 3:

[0425] The server analyzes the data received from the user and calls a generative AI model. The generative AI model generates a recipe that takes into account the user's preferences and conditions. This recipe is based on a model trained on multiple recipe data.

[0426] Step 4:

[0427] The server sends the generated recipe, which includes the ingredients, cooking steps, and quantities, to the food printer.

[0428] Step 5:

[0429] The food printer prints physical meals based on the recipe it receives, automatically mixing ingredients like protein powder, low-fat yogurt, and blueberries, and cooking them according to the instructions.

[0430] Step 6:

[0431] Once the food printer has printed the meal, it notifies the server, which then sends the information to a local distribution center.

[0432] Step 7:

[0433] Multiple drivers are waiting at the delivery center. The server issues printed delivery instructions for the food to an available driver. The driver then picks up the food and delivers it to the address specified by the user.

[0434] Step 8:

[0435] The user receives the food and provides feedback on it through the application, including the taste, appearance, and overall satisfaction with the food.

[0436] Step 9:

[0437] The terminal sends feedback from the user to the server, which collects and analyzes this feedback.

[0438] Step 10:

[0439] The server retrains the generative AI model based on the collected feedback, a process that ensures that future recipes are more tailored to the user's preferences.

[0440] Through the above steps, the system of the present invention can provide meals optimized to the preferences and conditions of the user regardless of the area where the user lives, thereby improving user satisfaction and frequency of use.

[0441] Example 1

[0442] 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."

[0443] Conventional food delivery systems have made it difficult for users to easily order food based on their specific preferences and conditions, and then automatically generate and deliver it. They also lacked a mechanism for improving recipes based on user feedback. As a result, it was difficult to improve user satisfaction and meet individual needs.

[0444] 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.

[0445] In this invention, the server includes means for providing an interface for users to input preferences and conditions, means for using a generative AI model that outputs recipes generated based on the user's input, means for operating a food printer that generates physical food based on the recipes generated by the generative AI model, means for collecting feedback provided by the user and improving the generative AI model, means for temporarily saving the preferences and conditions input by the user, means for calling the generative AI model to generate recipes, and means for generating prompt sentences for inputting user information into the generative AI model. This not only enables users, wherever they live, to easily order and enjoy food optimized for their preferences and conditions, but also enables the service to be continuously improved based on the provided feedback.

[0446] "User" refers to any person or entity that uses the System to order food based on specific preferences and requirements.

[0447] "Interface" refers to software, such as a web or mobile application, that provides a means for users to input their specific preferences or requirements.

[0448] "Generative AI model" refers to the artificial intelligence algorithm used to generate optimal recipes based on user input.

[0449] A "food printer" refers to a device that automatically produces physical food products based on recipes generated by a generative AI model.

[0450] "Feedback" refers to ratings and opinions provided by users regarding food quality and service.

[0451] "Server" refers to a computer system that receives and stores information from users and performs various processes such as calling up generative AI models.

[0452] A "prompt sentence" refers to the instructions or questions conveyed to a generative AI model based on user input information.

[0453] "Storage means" refers to a storage device or database for temporarily storing preferences and conditions entered by the user.

[0454] The present invention is a system that allows users to order food based on their specific preferences and requirements, creates a recipe for the food through a generative AI model, and delivers the physically printed food to the user. This system is implemented using the following specific hardware and software:

[0455] First, users input their preferences and conditions using a dedicated interface (web application or mobile application). This interface allows users to easily enter detailed information such as favorite ingredients, disliked ingredients, allergy information, and calorie restrictions.

[0456] For example, if a user requests a "high-protein, low-calorie smoothie to drink after sports," the following prompt text might be entered:

[0457] "Make a high-protein, low-calorie smoothie to drink after exercise. It must meet the following criteria: Favorite ingredients: blueberries, bananas, low-fat yogurt. Disliked ingredients: spirulina. Allergy information: nut allergy. Calorie limit: 200 calories or less."

[0458] The terminal (user's device) temporarily stores the input information and then transmits it to the server, which receives and analyzes the user's input information sent from the terminal.

[0459] The server then calls a generative AI model, which uses the user's input as a prompt, and the model (which may include natural language processing libraries or machine learning algorithms) generates recipes optimized for the user's preferences based on a vast amount of recipe data.

[0460] The generated recipe is sent from the server to the food printer in a standard format such as JSON, which then analyzes the recipe data and automatically mixes the necessary ingredients. Physical food is then produced according to the specific cooking instructions.

[0461] When the food is ready, the food printer sends a completion notification to the server. The server receives this notification and issues a delivery instruction to a local distribution center. The distribution center then issues a delivery instruction to an available driver based on the received notification and delivers the food to the user.

[0462] After enjoying the delivered food, the user again uses the interface to provide feedback, which can include various aspects such as the food's taste, appearance, and overall satisfaction. This feedback data is sent to the server and used to retrain the generative AI model.

[0463] In this way, the present invention provides an environment where users can easily order and enjoy food optimized for their preferences and conditions, regardless of where they live. This system can mitigate regional disparities in food delivery and improve user satisfaction and frequency of use.

[0464] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0465] Step 1:

[0466] The user launches a dedicated interface (web application or mobile application) and inputs their preferences and conditions. Input items include favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc. An example of a specific prompt is, "Make a high-protein, low-calorie smoothie to drink after exercise. Please meet the following conditions: Favorite ingredients: blueberries, bananas, low-fat yogurt. Disliked ingredients: spirulina. Allergy information: nut allergy. Calorie restrictions: 200 calories or less." This information is sent to the server by the user's operation.

[0467] Input: User preferences and conditions

[0468] Output: User information sent to the server

[0469] Step 2:

[0470] The device temporarily stores the information entered by the user and then transmits it to the server via a connection, specifically by using an HTTP POST request to transfer the data to the server, and then waits for a response to confirm that the information was sent correctly.

[0471] Input: Preferences and conditions data entered by the user

[0472] Output: User information sent to the server

[0473] Step 3:

[0474] The server receives user information sent from the device, analyzes this information, and generates a prompt that matches the user's request. This prompt is then passed to the generative AI model.

[0475] Input: User information sent from the device

[0476] Output: The prompt passed to the generative AI model

[0477] Step 4:

[0478] The server calls the generative AI model and inputs a prompt based on the user's information. The generative AI model generates the optimal recipe based on a huge amount of recipe data. Specifically, it uses natural language processing libraries and machine learning algorithms.

[0479] Input: prompt statement

[0480] Output: A new recipe from a generative AI model

[0481] Step 5:

[0482] The server sends the generated recipe data to the food printer, which receives the data, analyzes the recipe, and automatically mixes the necessary ingredients and creates the dish according to the specified cooking procedure.

[0483] Input: Recipe data from a generative AI model

[0484] Output: Physical food produced by a food printer

[0485] Step 6:

[0486] The food printer sends a message to the server notifying it that the food is ready. The server receives this notification and issues a delivery instruction to a local delivery center. The delivery center then assigns an available driver to pick up the food and deliver it to the user.

[0487] Input: Completion notification from food printer

[0488] Output: Delivery instructions to the distribution center

[0489] Step 7:

[0490] The user receives the delivered food and provides feedback on the food through the application, including taste, appearance, and overall satisfaction. The feedback is then sent to the server.

[0491] Input: User feedback

[0492] Output: Feedback data sent to the server

[0493] Step 8:

[0494] The server collects feedback data received from users and uses this data to retrain the generative AI model, which is then reflected in future recipe generation, resulting in continuous improvement of the service.

[0495] Input: User feedback data

[0496] Output: Improved recipes from a retrained generative AI model

[0497] (Application example 1)

[0498] 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."

[0499] Conventional food delivery systems have difficulty providing individually customized meals based on the user's preferences and conditions, leading to issues such as lower user satisfaction and reduced frequency of use due to regional disparities. Furthermore, there are also issues with the effort and efficiency involved in preparing and delivering meals, making it impossible to provide an environment that users can easily use.

[0500] 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.

[0501] In this invention, the server includes: means for providing an interface for a user to input preferences and conditions; means for using a generative AI model to output a recipe generated based on the user's input; means for operating a food printer to print a physical dish based on the recipe generated by the generative AI model; means for delivering the physical dish to the user; means for collecting feedback provided by the user and improving the generative AI model; and means including an application for generating recipes based on the preferences and conditions input by the user and managing delivery. This enables users to easily order and receive dishes optimized for their individual preferences and conditions, mitigating regional disparities in food delivery and improving user satisfaction and frequency of use.

[0502] A "user" is an entity that orders food based on specific preferences or requirements.

[0503] An "interface" is a means by which a user inputs preferences and requirements.

[0504] A "generative AI model" is an artificial intelligence technology that generates optimal recipes based on user input information.

[0505] A "food printer" is a device that automatically cooks and prints physical dishes according to a generated recipe.

[0506] "Delivery means" refers to the means or system for delivering the created meal to the user.

[0507] "Feedback" is user-provided evaluation information about a dish, and is data used to improve the generative AI model.

[0508] An "application" is software that allows a user to input food preferences and requirements and place an order.

[0509] This invention is a system that allows users to order food based on their specific preferences and requirements, creates a recipe for it through a generative AI model, and delivers the physically printed food to the user using a food printer.

[0510] System configuration and operation

[0511] 1. User Input Interface

[0512] Users use a dedicated application (smartphone application or web application) to input their cooking preferences and conditions (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.) This information is temporarily stored on the user's device and then sent to the server.

[0513] 2. Recipe generation using generative AI models

[0514] The server receives the information sent by the user and calls a generative AI model based on that information. This generative AI model is trained using multiple recipe data sets and generates new recipes optimized for the user's preferences. This process uses natural language processing and deep learning technologies and is executed on the server.

[0515] 3. Food printing to create dishes

[0516] The generated recipe is sent from the server to the food printer, which then automatically mixes the specified ingredients based on the recipe and completes the dish according to the instructions. The food printer has advanced cooking technology and can handle a variety of ingredients.

[0517] 4. Food delivery

[0518] Once the food is ready, the server issues a delivery order. Delivery is made from a local distribution center with multiple drivers waiting. An available driver will deliver the food to the user. The delivery process is tracked in real time, and users can check the current delivery status through the application.

[0519] 5. Gathering feedback and improving the generative AI model

[0520] After receiving the dish, the user uses the application to provide feedback on the dish, including the taste, appearance, and overall satisfaction level, which is sent to the server. This feedback data is used to retrain the generative AI model and is reflected in future recipe generation.

[0521] Hardware and Software Use

[0522] Hardware: smartphones, servers, food printers, delivery vehicles

[0523] Software: Django (web framework), generative AI model (natural language processing technology), REST API (calling the generative AI model)

[0524] Specific examples

[0525] If the user requests a "low carb, gluten-free dinner," the application will generate the following prompt:

[0526] I'd like a low carb, gluten free dinner please.

[0527] This prompt is sent to a generative AI model, and the generated recipe is printed as a meal using a food printer and delivered. The generated recipe is a low-carb, gluten-free menu based on protein-rich chicken breast and vegetables. After receiving the meal, the user provides feedback through the application, such as "The taste was very good, but I wish there was a little more," and this feedback is reflected in the next recipe generation.

[0528] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0529] Step 1:

[0530] The user uses the device to input preferences and conditions (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.) into the application. The device temporarily stores this information and sends it to the server. The input data is in text format and includes specific information about the user's preferences.

[0531] Step 2:

[0532] The server generates a prompt for the generative AI model based on the user's preferences and conditions sent from the device and sends it. The prompt is text that is automatically generated based on the user's request. The generative AI model receives this prompt and generates the optimal recipe. Data processing involves converting the user's preferences and conditions into a format suitable for the generative AI model.

[0533] Step 3:

[0534] The generated recipe is sent back to the server, which interprets the recipe content and sends recipe instructions to the food printer. The recipe data includes the required ingredients, cooking steps, cooking time, etc. The server converts this information into a format compatible with the food printer.

[0535] Step 4:

[0536] The food printer automatically mixes the specified ingredients based on the recipe instructions received from the server and creates the dish according to the cooking steps, measuring the amount of food ingredients and operating automated cooking equipment for each cooking step.

[0537] Step 5:

[0538] Once the food is ready, the food printer sends a notification to the server. When the server receives the notification, it issues a delivery instruction to the delivery center and assigns an available driver. During this process, it references the delivery center's database to select the most suitable driver.

[0539] Step 6:

[0540] The delivery driver will receive the requested food and deliver it to the user. The delivery progress is reported to the server in real time, and the user can check the delivery status through the application.

[0541] Step 7:

[0542] After receiving the food, the user provides feedback using the application. The feedback includes evaluation data on the taste, appearance, quantity, satisfaction level, etc. of the food. The device then sends this to the server.

[0543] Step 8:

[0544] The server accumulates the received feedback data and uses it to retrain the generative AI model, improving its accuracy and reflecting it in future recipe generation.

[0545] The above are the specific processing steps of the system that realizes the application example.

[0546] 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.

[0547] The present invention is a system that uses a generative AI model to create dishes based on a user's preferences and conditions, and further combines it with an emotion engine that recognizes the user's emotions. This makes it possible to provide dishes that are more accurately tailored to the user's preferences and emotions. The present invention is specifically implemented as follows.

[0548] First, a user opens an application (web app or mobile app) and uses an interface to input preferences and conditions (likes, dislikes, allergies, calorie restrictions, etc.) Dedicated input fields, checkboxes, and selection menus are provided for this input task.

[0549] The information entered by the user is temporarily stored on the device and then sent to a server, including details about the user's personal information and cooking preferences.

[0550] The server analyzes the user's preferences and conditions data and calls up a generative AI model. This generative AI model has been trained from multiple recipe data and automatically generates the optimal recipe based on the user's input conditions.

[0551] After the recipe is generated, the server calls the emotion engine to analyze the user's emotions. The emotion engine analyzes the user's facial expressions, voice, text data, etc. to recognize the user's emotional state. This emotion data is also reflected in the recipe generation process described above.

[0552] The server then sends the generated recipe to the food printer, which automatically mixes the specified ingredients and creates a physical dish according to the cooking instructions. For example, if a user requests a "soup to eat when you want to relax," the generative AI model will select ingredients and cooking methods that will enhance the relaxing effect based on the user's emotions recognized by the emotion engine.

[0553] Once the printed meal is ready, the server sends the information to a local distribution center, where multiple drivers are waiting, and an available driver will deliver the meal to the address specified by the user.

[0554] After the delivery is complete, the user again uses the application to provide feedback on the food, which may include the food's taste, appearance, overall satisfaction, and emotional response to the entire experience. This feedback is sent to and collected by the server.

[0555] The server retrains the generative AI model based on user feedback and data from the emotion engine, so that the next time it generates a recipe, it will provide dishes that better match the user's preferences and emotions.

[0556] As a concrete example, if a user requests a "light meal that helps relieve stress," the emotion engine will recognize that the user is under stress from their facial expressions and voice. Based on this information, the generative AI model will select ingredients and cooking methods that are effective in relieving stress and generate the optimal recipe. The food printer will create a meal based on the recipe and deliver it to the user. Feedback will add previously unrecognized stress factors and taste preferences, and these will be reflected in future services.

[0557] As described above, the present invention is a system that provides more personalized food delivery by combining emotion recognition using an emotion engine with user preferences and conditions, which can significantly improve user satisfaction and frequency of use.

[0558] The processing flow will be explained below.

[0559] Step 1:

[0560] The user opens the application and enters their preferences and requirements (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.) through the interface. Input operations are performed using text boxes, check boxes, drop-down menus, etc.

[0561] Step 2:

[0562] The device temporarily stores the preferences and conditions entered by the user and then transmits them to the server, including all the information entered.

[0563] Step 3:

[0564] The server processes the received user data and invokes the generative AI model, which uses pre-trained data to create optimal recipes based on the user's preferences and conditions.

[0565] Step 4:

[0566] The server passes the generated recipe information to the emotion engine, which acquires and analyzes emotion data based on the user's facial expressions, voice, or text to recognize the user's emotional state.

[0567] Step 5:

[0568] The server uses the emotional data obtained from the emotion engine to optimize the recipe, specifically selecting ingredients and cooking methods that best suit the user's emotional state and fine-tuning the recipe.

[0569] Step 6:

[0570] The server sends the optimized recipe to the food printer, including details such as the specific ingredient list, cooking instructions, and quantities required.

[0571] Step 7:

[0572] The food printer prints physical dishes based on the received recipe, for example, automatically mixing the specified ingredients and following the cooking instructions to complete the dish.

[0573] Step 8:

[0574] Once the food printer has completed the cooking process, it notifies the server, which then sends the information to a local distribution center.

[0575] Step 9:

[0576] Multiple drivers are waiting at the delivery center. The server sends printed delivery instructions to the appropriate driver, who then delivers the food to the address specified by the user.

[0577] Step 10:

[0578] After receiving their food, users use the application again to provide feedback on the food, including its taste, appearance, overall satisfaction, and emotional response to the entire experience.

[0579] Step 11:

[0580] The device sends the user's feedback to the server, which includes detailed evaluation information and emotion data.

[0581] Step 12:

[0582] The server retrains the generative AI model based on the collected feedback and emotional data, allowing it to provide dishes that better suit the user's preferences and emotions in future recipe generation.

[0583] Through these steps, the system of the present invention can provide more personalized food by incorporating emotion recognition in addition to user preferences and conditions, thereby improving user satisfaction and frequency of use.

[0584] Example 2

[0585] 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."

[0586] Conventional systems were unable to consider the user's emotional state when providing food based on the user's preferences and conditions. As a result, they were unable to provide food that matched the user's momentary mood or emotions, potentially reducing user satisfaction. Furthermore, mechanisms for effectively utilizing user feedback to improve generative AI models were limited, meaning that subsequent food offerings may not necessarily match the user's preferences or emotions. To address these issues, a more personalized food offering mechanism that reflects the user's emotional data is needed.

[0587] 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 means for providing an interface for a user to input preferences and conditions, means for using a generative AI model to output a recipe generated based on the user's input, and means for invoking an emotion engine to reflect the user's emotional data in the recipe generated by the generative AI model. This enables the provision of more personalized dishes that reflect not only the user's preferences and conditions but also their emotional state. Furthermore, by combining means for collecting feedback provided by users and improving the generative AI model, it is expected that the accuracy of the generative AI model and user satisfaction will be improved.

[0588] A "user" is an individual who uses the system to make a food request.

[0589] An "interface" is an input device or software screen provided for a user to input preferences and requirements.

[0590] A "generative AI model" is an artificial intelligence model that automatically generates optimal recipes based on input data.

[0591] A "food printer" is a device that creates physical dishes using specified ingredients based on a recipe generated by a generative AI model.

[0592] An "emotion engine" is a program or system that analyzes a user's facial expressions, voice, and text data to recognize their emotional state.

[0593] "Feedback" refers to ratings and comments about the taste and appearance of the food provided by the user, overall satisfaction, and emotional response.

[0594] A "server" is a computer system that receives and analyzes input data from users, and then calls generative AI models and emotion engines for processing.

[0595] "Delivery means" refers to a means for physically delivering the prepared meal to the address specified by the user.

[0596] "Temporary storage" refers to the short-term storage of data on preferences and conditions entered by the user.

[0597] "Data analysis" is the process of analyzing user input data, converting it into an appropriate format, and extracting the required information.

[0598] MODE FOR CARRYING OUT THE INVENTION

[0599] The present invention is a system that provides optimal dishes based on a user's preferences and conditions. The system aims to improve user satisfaction by analyzing the user's emotions and providing more personalized dishes. Specific embodiments for implementing the present invention are described below.

[0600] System Overview

[0601] First, a user opens an application (web app or mobile app) on their smartphone or computer. This application provides an interface for the user to input their preferences and conditions. The interface provides input fields, checkboxes, and drop-down menus for favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.

[0602] The information entered by the user is temporarily stored in the device's local storage or the browser's session storage. This input data is then sent to a server, where a computer system is located to analyze and process the data. This processing can be performed using cloud technologies such as AWS Lambda or Google Cloud Functions.

[0603] The server analyzes the received user data and calls up a generative AI model, which has been trained in advance using multiple recipe data sets and automatically generates optimal recipes based on the user's input conditions.

[0604] The server then invokes an emotion engine, which uses facial expressions, voice, and text data to analyze the user's emotional state. The emotion engine could be, for example, Microsoft Azure's Emotion API. The emotion data is also reflected in the generated recipe. For example, if a user wants to relax, the server can select ingredients and cooking methods that match that emotional state.

[0605] The generated optimal recipe information is sent from the server to the food printer, which automatically mixes the specified ingredients and creates a physical dish using 3D food printing technology. The information is then sent in real time to a local distribution center, where it is delivered to the user's specified address via a delivery method.

[0606] After the food is delivered to the user, the user uses the application to provide feedback on the food, which can range from taste and appearance to overall satisfaction and emotional response. The feedback is sent to the server, and the collected data is used to retrain the generative AI model, allowing it to provide a more personalized and optimal dish for future meals.

[0607] Specific examples

[0608] Consider a case where a user opens the app and requests a "stress-relieving snack." The emotion engine recognizes that the user is under stress from their facial expressions and voice. Based on this information, the generative AI model selects ingredients and cooking methods that are effective in relieving stress, generating a recipe such as herbal tea or nut bars. This is then printed using a food printer and delivered to the user. The user provides feedback on the food that arrives, and this information is reflected in future service plans.

[0609] Prompt Sentence Examples

[0610] An example of a prompt is as follows:

[0611] User: Opens the app and enters preferences and requirements.

[0612] Device: Temporarily save user information.

[0613] Server: Analyzes the data and invokes the generative AI model.

[0614] Generative AI model: Automatically generates optimal recipes.

[0615] Server: Calls the emotion engine and recognizes the user's emotional state.

[0616] Server: Sends the generated recipe to the food printer.

[0617] Food printer: Create your food.

[0618] Delivery point: delivers food to the user's address.

[0619] Users: Provide feedback.

[0620] Server: Retrain the generative AI model based on feedback and emotion data.

[0621] In this way, the embodiment of the present invention combines emotion recognition by the emotion engine with user preferences and conditions to provide more personalized food, which is expected to significantly improve user satisfaction and frequency of use.

[0622] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0623] Step 1:

[0624] The user opens the application and inputs their preferences and requirements. The application provides an interface for inputting their favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc. The user's input information is collected via text fields and check boxes. The input data is treated as information on preferences and requirements.

[0625] Input: User preferences and conditions

[0626] Output: User input data (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.)

[0627] Step 2:

[0628] The device temporarily stores the user's input data. The input data is stored in local storage or the browser's session storage and prepared for transmission to the server. The stored data may also be backed up to ensure reliability.

[0629] Input: User-entered data

[0630] Output: Temporarily saved data

[0631] Step 3:

[0632] The device sends the temporarily stored data to the server. Data such as the user's preferences and conditions are sent to the server via an HTTP request. Encryption technology such as SSL is used to ensure secure communication.

[0633] Input:Temporarily saved data

[0634] Output: Data sent to the server

[0635] Step 4:

[0636] The server analyzes the data received from the user. During the analysis process, the data items are appropriately classified and the necessary information is extracted. For example, the data can be divided into a list of favorite ingredients and a list of allergy information. Scripts written in Python or Java are often used for data analysis.

[0637] Input: Data sent to the server

[0638] Output: Categorized and organized data items

[0639] Step 5:

[0640] The server calls the generative AI model and generates a recipe based on the user's criteria. The generative AI model selects the optimal recipe from a large amount of recipe data it has learned in the past. To call the model, a request is sent via an API. Machine learning technology is used in the generation process.

[0641] Input: Categorised and organised data items

[0642] Output: The generated optimal recipe

[0643] Step 6:

[0644] The server calls the emotion engine to analyze the user's emotional state. The emotion engine inputs the user's facial expressions, voice, and text data to recognize the emotional state. For example, it uses data obtained from a camera and microphone to determine whether the user is stressed or relaxed.

[0645] Input: User's facial expressions, voice, and text data

[0646] Output: Analyzed user emotion data

[0647] Step 7:

[0648] The server then further adjusts the generated recipe based on the emotional data. The generative AI model evaluates the emotional data and selects ingredients and cooking methods that suit the user's emotional state. For example, it adds relaxing herbs or warm soup.

[0649] Input: Generated optimal recipe and sentiment data

[0650] Output: The final recipe reflecting the sentiment data

[0651] Step 8:

[0652] The server sends the final recipe to the food printer. The final recipe information is sent to the food printer as a data set including the ingredients list and cooking instructions. The food printer receives this data and automatically mixes the ingredients and cooks the food.

[0653] Input: Final recipe reflecting sentiment data

[0654] Output: Recipe data sent to the food printer

[0655] Step 9:

[0656] The food printer creates the meal based on the final recipe, using 3D food printing technology to build the ingredients layer by layer, with temperature and timing controlled according to the cooking instructions.

[0657] Input: Recipe data sent to the food printer

[0658] Output: A physically created dish

[0659] Step 10:

[0660] The server sends information about the completed meal to the delivery center, which then prepares the meal for delivery and issues delivery instructions to the driver. Information is updated in real time and managed to ensure efficient delivery.

[0661] Input: Information about the finished dish

[0662] Output: Information notification to delivery center

[0663] Step 11:

[0664] The driver delivers the food to the address specified by the user. The delivery system selects the optimal route based on the user's address information and provides navigation information to the driver. After delivery is complete, the user receives a delivery completion notification.

[0665] Input: Delivery instructions from the distribution center

[0666] Output: The meal delivered to the user

[0667] Step 12:

[0668] The user uses the application to provide feedback on the dish, including the dish's taste, appearance, overall satisfaction, and emotional response. Feedback data is entered in the form of text and choices.

[0669] Input: User ratings and opinions

[0670] Output: Feedback data

[0671] Step 13:

[0672] The server collects and analyzes the feedback provided by users. The feedback is used to evaluate the quality of the food and user satisfaction. The analysis results are used to generate future recipes.

[0673] Input: Feedback data

[0674] Output: Analysis results and evaluation data

[0675] Step 14:

[0676] The server retrains the generative AI model based on the feedback and emotion data. The retraining process improves the accuracy and user adaptability of the generative AI model, which in turn improves the accuracy of recipe generation from the next time onwards.

[0677] Input: Analysis results and feedback data

[0678] Output: Retrained generative AI model

[0679] (Application example 2)

[0680] 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."

[0681] Conventional food delivery services were able to provide food based on the user's preferences and conditions, but they did not provide services that took into account the user's emotional state. As a result, they were unable to suggest or provide the optimal dish based on the user's emotional state, making it difficult to improve user satisfaction. In addition, feedback on the delivered dish was not sufficiently reflected in the next dish suggestions, making it difficult to improve the quality of the service.

[0682] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for providing an interface for the user to input preferences and conditions, means for using a generative AI model that outputs a recipe generated based on the user's input, means for using an emotion engine that recognizes the user's emotional state, means for reflecting emotion data obtained from the emotion engine in the generative AI model, means for operating a cooking machine that prints a physical dish based on the recipe generated by the generative AI model, delivery means for delivering the physical dish to the user, and means for collecting feedback provided by the user and improving the generative AI model. This makes it possible to provide food that takes into account the user's emotional state in addition to their preferences and conditions, thereby improving user satisfaction and the quality of food delivery services.

[0683] "User" refers to an individual who uses the system to order food and input their preferences and requirements.

[0684] "Interface" refers to the screens and tools that users use to input information into a system.

[0685] A "generative AI model" refers to an artificial intelligence model that automatically generates optimal recipes based on the user's preferences and conditions.

[0686] An "emotion engine" refers to software or algorithms that recognize a user's emotional state from facial expressions, voice, text data, etc.

[0687] "Emotion data" refers to information about a user's emotional state obtained by an emotion engine.

[0688] "Cooking machine" refers to a device that prints or cooks physical dishes based on recipes generated by generative AI models.

[0689] "Delivery method" refers to the mechanism or method for delivering the created meal to the address specified by the user.

[0690] "Feedback" refers to the action of a user inputting their opinion or evaluation regarding the food or service provided.

[0691] "Server" refers to the computer system that receives and analyzes user input data and runs the generative AI model and emotion engine.

[0692] A specific embodiment of a system for realizing an application example of the present invention will be described below. The present invention is a system for providing optimal dishes based on a user's preferences and emotional state, and includes a server, an emotion engine, a generative AI model, a cooking machine, and a delivery means.

[0693] Overall system configuration

[0694] 1. User Device

[0695] Interface: Provides an application that allows users to input their preferences and conditions. A typical example is a smartphone app. Users input their favorite ingredients, disliked ingredients, allergy information, calorie restrictions, emotional state, etc.

[0696] 2. Server

[0697] Data Receipt and Storage: Information entered by the user is received and temporarily stored.

[0698] Generative AI model: Runs an artificial intelligence model that generates optimal recipes based on user preferences and conditions.

[0699] Emotion engine: Recognizes emotions from user input data (facial expressions, voice, text) and obtains emotional data.

[0700] Data integration: The acquired emotional data is fed into the generative AI model to generate recipes based on the emotional state.

[0701] 3. Cooking machine

[0702] Food Printer: Operates an automated cooking machine that creates physical food based on recipes sent from the server, allowing for precise mixing and cooking of ingredients.

[0703] 4. Delivery method

[0704] Delivery people and drones: The finished meal is delivered to the address specified by the user, either by automated drones or human delivery people.

[0705] 5. Feedback System

[0706] Rating collection: Provides an interface for users to enter feedback on the food and service provided.

[0707] Data analysis and learning: Retrain the generative AI model based on collected feedback to improve the quality of future recipe generation.

[0708] Specific examples

[0709] The user opens the smartphone app and enters the following information:

[0710] User name: Sato

[0711] Favorite ingredients: chicken, tomatoes

[0712] Disliked ingredient: Fish sauce

[0713] Allergens: nuts

[0714] Calorie restriction: 600 kcal or less

[0715] Current Emotion: High Stress

[0716] Based on this, the prompt would look like this:

[0717] User Sato is currently feeling stressed. Please suggest a dish that uses chicken and tomatoes, is nut-free, and is under 600 kcal. It should not contain fish sauce.

[0718] The server receives this data and generates an optimal recipe using the generative AI model and emotion engine. It then sends the recipe to the cooking machine, which creates the physical dish. The finished dish is delivered to the user via a delivery vehicle, and the user again provides feedback using the app. This feedback is collected by the server and used to retrain the generative AI model.

[0719] The key hardware and software used throughout the process include smartphones, servers, generative AI models, emotion engines, food printers, delivery drones and delivery people.

[0720] This allows for the provision of high-quality food that takes into account not only the user's preferences and conditions, but also their emotional state.

[0721] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0722] Step 1:

[0723] The user enters preferences and requirements.

[0724] Input: The user enters their favorite ingredients, disliked ingredients, allergy information, calorie restrictions, and current emotional state into the smartphone app.

[0725] How it works: An application on a user's device provides specialized input fields, checkboxes, and selection menus.

[0726] Output: User-entered preferences and conditions data.

[0727] Step 2:

[0728] Send and temporarily save input data.

[0729] Input: Data entered by the user through the application.

[0730] Operation: The user terminal temporarily stores this data and sends it to the server.

[0731] Output: User preferences and requirements data transferred to the server.

[0732] Step 3:

[0733] Recipe generation using generative AI models.

[0734] Input: User preferences and requirements data stored on the server.

[0735] How it works: The server invokes a generative AI model to generate the optimal recipe based on the user's preferences and conditions.

[0736] Output: The generated recipe data.

[0737] Step 4:

[0738] Acquiring emotion data.

[0739] Input: Data about the emotional state submitted by the user.

[0740] How it works: The server uses an emotion engine to analyze the user's emotional state, which may involve facial recognition, speech analysis, or text analysis.

[0741] Output: Emotion data from the emotion engine.

[0742] Step 5:

[0743] Reflecting emotional data.

[0744] Input: Generated recipe data and sentiment data.

[0745] How it works: The server applies the emotional data to the generative AI model and re-optimizes the recipe.

[0746] Output: Recipe data optimized for emotional states.

[0747] Step 6:

[0748] Cooking food using a cooking machine.

[0749] Input: Optimized recipe data.

[0750] Operation: The server sends the optimized recipe data to the cooking machine (food printer), which then automatically mixes the specified ingredients and prepares the dish according to the recipe.

[0751] Output: The finished physical dish.

[0752] Step 7:

[0753] Arrange delivery.

[0754] Input: The finished dish and the user's address information.

[0755] How it works: The server sends the completed meal and address information to a delivery vehicle (delivery person or drone) to arrange for delivery.

[0756] Output: The meal delivered to the user's address.

[0757] Step 8:

[0758] Get feedback.

[0759] Input: User's ratings and opinions about the food and service provided.

[0760] How it works: The user enters feedback through a smartphone app, which then sends this feedback to the server.

[0761] Output: User feedback data stored on the server.

[0762] Step 9:

[0763] Retraining generative AI models.

[0764] Input: Feedback data and emotion data.

[0765] How it works: The server retrains the generative AI model based on the collected feedback and emotion data, improving the accuracy of future recipe generation.

[0766] Output: An improved generative AI model.

[0767] The above is the specific processing flow of this system.

[0768] 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.

[0769] 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.

[0770] 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.

[0771] [Third embodiment]

[0772] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0773] 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.

[0774] 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).

[0775] 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.

[0776] 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.

[0777] 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).

[0778] 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. 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.

[0779] 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.

[0780] 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.

[0781] 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.

[0782] 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.

[0783] 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."

[0784] The present invention is a system that allows users to order food based on their specific preferences and conditions, creates a recipe for the food through a generative AI model, and delivers the physically printed food to the user. The present invention is specifically implemented as follows.

[0785] First, the user uses a dedicated application (web app or mobile app) to input their preferences and conditions (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.) This information is temporarily stored on the device and later sent to the server.

[0786] The server receives the information sent by the user and calls up a generative AI model based on that information. This generative AI model is trained using multiple recipe data sets and generates new recipes optimized for the user's preferences.

[0787] The server then sends the generated recipe to the food printer, which then generates a physical dish based on the recipe. Specifically, the food printer automatically mixes the specified ingredients and follows the cooking instructions to complete the dish.

[0788] After the food is ready, the server receives a notification from the food printer and issues a delivery instruction to a local delivery center. Multiple drivers are waiting at the delivery center, and an available driver will deliver the food to the user's location.

[0789] After the delivery is complete, the user uses the app again to provide feedback on the food. The feedback can cover a variety of topics, including the food's taste, appearance, and overall satisfaction. This feedback is sent to the server and used to improve the generative AI model. Specifically, the feedback data is used to retrain the generative AI model and reflect it in future recipe generation.

[0790] As a concrete example, suppose a user requests a "high-protein, low-calorie smoothie to drink after sports." The user inputs these requirements into the application and submits it. The server receives the request and generates an optimal smoothie recipe based on a generative AI model. The generated recipe is sent to a food printer, which creates a smoothie using the necessary ingredients (e.g., protein powder, low-fat yogurt, blueberries, etc.). The created smoothie is promptly delivered to the user. After enjoying the smoothie, the user can provide feedback on the taste and effects, which will be used to help with future orders.

[0791] As described above, the system of the present invention provides an environment where users can easily enjoy meals optimized to their preferences and conditions, regardless of where they live. This reduces regional disparities in food delivery services and improves user satisfaction and frequency of use.

[0792] The processing flow will be explained below.

[0793] Step 1:

[0794] The user opens the application. The user uses an interface to input their preferences and conditions (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.). The information entered by the user is temporarily stored on the device.

[0795] Step 2:

[0796] The device sends the user's preferences and requirements to the server, including the user's personal information and details of the desired dish.

[0797] Step 3:

[0798] The server analyzes the data received from the user and calls a generative AI model. The generative AI model generates a recipe that takes into account the user's preferences and conditions. This recipe is based on a model trained on multiple recipe data.

[0799] Step 4:

[0800] The server sends the generated recipe, which includes the ingredients, cooking steps, and quantities, to the food printer.

[0801] Step 5:

[0802] The food printer prints physical meals based on the recipe it receives, automatically mixing ingredients like protein powder, low-fat yogurt, and blueberries, and cooking them according to the instructions.

[0803] Step 6:

[0804] Once the food printer has printed the meal, it notifies the server, which then sends the information to a local distribution center.

[0805] Step 7:

[0806] Multiple drivers are waiting at the delivery center. The server issues printed delivery instructions for the food to an available driver. The driver then picks up the food and delivers it to the address specified by the user.

[0807] Step 8:

[0808] The user receives the food and provides feedback on it through the application, including the taste, appearance, and overall satisfaction with the food.

[0809] Step 9:

[0810] The terminal sends feedback from the user to the server, which collects and analyzes this feedback.

[0811] Step 10:

[0812] The server retrains the generative AI model based on the collected feedback, a process that ensures that future recipes are more tailored to the user's preferences.

[0813] Through the above steps, the system of the present invention can provide meals optimized to the preferences and conditions of the user regardless of the area where the user lives, thereby improving user satisfaction and frequency of use.

[0814] Example 1

[0815] 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."

[0816] Conventional food delivery systems have made it difficult for users to easily order food based on their specific preferences and conditions, and then automatically generate and deliver it. They also lacked a mechanism for improving recipes based on user feedback. As a result, it was difficult to improve user satisfaction and meet individual needs.

[0817] 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.

[0818] In this invention, the server includes means for providing an interface for users to input preferences and conditions, means for using a generative AI model that outputs recipes generated based on the user's input, means for operating a food printer that generates physical food based on the recipes generated by the generative AI model, means for collecting feedback provided by the user and improving the generative AI model, means for temporarily saving the preferences and conditions input by the user, means for calling the generative AI model to generate recipes, and means for generating prompt sentences for inputting user information into the generative AI model. This not only enables users, wherever they live, to easily order and enjoy food optimized for their preferences and conditions, but also enables the service to be continuously improved based on the provided feedback.

[0819] "User" refers to any person or entity that uses the System to order food based on specific preferences and requirements.

[0820] "Interface" refers to software, such as a web or mobile application, that provides a means for users to input their specific preferences or requirements.

[0821] "Generative AI model" refers to the artificial intelligence algorithm used to generate optimal recipes based on user input.

[0822] A "food printer" refers to a device that automatically produces physical food products based on recipes generated by a generative AI model.

[0823] "Feedback" refers to ratings and opinions provided by users regarding food quality and service.

[0824] "Server" refers to a computer system that receives and stores information from users and performs various processes such as calling up generative AI models.

[0825] A "prompt sentence" refers to the instructions or questions conveyed to a generative AI model based on user input information.

[0826] "Storage means" refers to a storage device or database for temporarily storing preferences and conditions entered by the user.

[0827] The present invention is a system that allows users to order food based on their specific preferences and requirements, creates a recipe for the food through a generative AI model, and delivers the physically printed food to the user. This system is implemented using the following specific hardware and software:

[0828] First, users input their preferences and conditions using a dedicated interface (web application or mobile application). This interface allows users to easily enter detailed information such as favorite ingredients, disliked ingredients, allergy information, and calorie restrictions.

[0829] For example, if a user requests a "high-protein, low-calorie smoothie to drink after sports," the following prompt text might be entered:

[0830] "Make a high-protein, low-calorie smoothie to drink after exercise. It must meet the following criteria: Favorite ingredients: blueberries, bananas, low-fat yogurt. Disliked ingredients: spirulina. Allergy information: nut allergy. Calorie limit: 200 calories or less."

[0831] The terminal (user's device) temporarily stores the input information and then transmits it to the server, which receives and analyzes the user's input information sent from the terminal.

[0832] The server then calls a generative AI model, which uses the user's input as a prompt, and the model (which may include natural language processing libraries or machine learning algorithms) generates recipes optimized for the user's preferences based on a vast amount of recipe data.

[0833] The generated recipe is sent from the server to the food printer in a standard format such as JSON, which then analyzes the recipe data and automatically mixes the necessary ingredients. Physical food is then produced according to the specific cooking instructions.

[0834] When the food is ready, the food printer sends a completion notification to the server. The server receives this notification and issues a delivery instruction to a local distribution center. The distribution center then issues a delivery instruction to an available driver based on the received notification and delivers the food to the user.

[0835] After enjoying the delivered food, the user again uses the interface to provide feedback, which can include various aspects such as the food's taste, appearance, and overall satisfaction. This feedback data is sent to the server and used to retrain the generative AI model.

[0836] In this way, the present invention provides an environment where users can easily order and enjoy food optimized for their preferences and conditions, regardless of where they live. This system can mitigate regional disparities in food delivery and improve user satisfaction and frequency of use.

[0837] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0838] Step 1:

[0839] The user launches a dedicated interface (web application or mobile application) and inputs their preferences and conditions. Input items include favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc. An example of a specific prompt is, "Make a high-protein, low-calorie smoothie to drink after exercise. Please meet the following conditions: Favorite ingredients: blueberries, bananas, low-fat yogurt. Disliked ingredients: spirulina. Allergy information: nut allergy. Calorie restrictions: 200 calories or less." This information is sent to the server by the user's operation.

[0840] Input: User preferences and conditions

[0841] Output: User information sent to the server

[0842] Step 2:

[0843] The device temporarily stores the information entered by the user and then transmits it to the server via a connection, specifically by using an HTTP POST request to transfer the data to the server, and then waits for a response to confirm that the information was sent correctly.

[0844] Input: Preferences and conditions data entered by the user

[0845] Output: User information sent to the server

[0846] Step 3:

[0847] The server receives user information sent from the device, analyzes this information, and generates a prompt that matches the user's request. This prompt is then passed to the generative AI model.

[0848] Input: User information sent from the device

[0849] Output: The prompt passed to the generative AI model

[0850] Step 4:

[0851] The server calls the generative AI model and inputs a prompt based on the user's information. The generative AI model generates the optimal recipe based on a huge amount of recipe data. Specifically, it uses natural language processing libraries and machine learning algorithms.

[0852] Input: prompt statement

[0853] Output: New recipes from generative AI models

[0854] Step 5:

[0855] The server sends the generated recipe data to the food printer, which receives the data, analyzes the recipe, and automatically mixes the necessary ingredients and creates the dish according to the specified cooking procedure.

[0856] Input: Recipe data from a generative AI model

[0857] Output: Physical food produced by a food printer

[0858] Step 6:

[0859] The food printer sends a message to the server notifying it that the food is ready. The server receives this notification and issues a delivery instruction to a local delivery center. The delivery center then assigns an available driver to pick up the food and deliver it to the user.

[0860] Input: Completion notification from food printer

[0861] Output: Delivery instructions to the distribution center

[0862] Step 7:

[0863] The user receives the delivered food and provides feedback on the food through the application, including taste, appearance, and overall satisfaction. The feedback is then sent to the server.

[0864] Input: User feedback

[0865] Output: Feedback data sent to the server

[0866] Step 8:

[0867] The server collects feedback data received from users and uses this data to retrain the generative AI model, which is then reflected in future recipe generation, resulting in continuous improvement of the service.

[0868] Input: User feedback data

[0869] Output: Improved recipes from a retrained generative AI model

[0870] (Application example 1)

[0871] 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."

[0872] Conventional food delivery systems have difficulty providing individually customized meals based on the user's preferences and conditions, leading to issues such as lower user satisfaction and reduced frequency of use due to regional disparities. Furthermore, there are also issues with the effort and efficiency involved in preparing and delivering meals, making it impossible to provide an environment that users can easily use.

[0873] 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.

[0874] In this invention, the server includes: means for providing an interface for a user to input preferences and conditions; means for using a generative AI model to output a recipe generated based on the user's input; means for operating a food printer to print a physical dish based on the recipe generated by the generative AI model; means for delivering the physical dish to the user; means for collecting feedback provided by the user and improving the generative AI model; and means including an application for generating recipes based on the preferences and conditions input by the user and managing delivery. This enables users to easily order and receive dishes optimized for their individual preferences and conditions, mitigating regional disparities in food delivery and improving user satisfaction and frequency of use.

[0875] A "user" is an entity that orders food based on specific preferences or requirements.

[0876] An "interface" is a means by which a user inputs preferences and requirements.

[0877] A "generative AI model" is an artificial intelligence technology that generates optimal recipes based on user input information.

[0878] A "food printer" is a device that automatically cooks and prints physical dishes according to a generated recipe.

[0879] "Delivery means" refers to the means or system for delivering the created meal to the user.

[0880] "Feedback" is user-provided evaluation information about a dish, and is data used to improve the generative AI model.

[0881] An "application" is software that allows a user to input food preferences and requirements and place an order.

[0882] This invention is a system that allows users to order food based on their specific preferences and requirements, creates a recipe for it through a generative AI model, and delivers the physically printed food to the user using a food printer.

[0883] System configuration and operation

[0884] 1. User Input Interface

[0885] Users use a dedicated application (smartphone application or web application) to input their cooking preferences and conditions (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.) This information is temporarily stored on the user's device and then sent to the server.

[0886] 2. Recipe generation using generative AI models

[0887] The server receives the information sent by the user and calls a generative AI model based on that information. This generative AI model is trained using multiple recipe data sets and generates new recipes optimized for the user's preferences. This process uses natural language processing and deep learning technologies and is executed on the server.

[0888] 3. Food printing to create dishes

[0889] The generated recipe is sent from the server to the food printer, which then automatically mixes the specified ingredients based on the recipe and completes the dish according to the instructions. The food printer has advanced cooking technology and can handle a variety of ingredients.

[0890] 4. Food delivery

[0891] Once the food is ready, the server issues a delivery order. Delivery is made from a local distribution center with multiple drivers waiting. An available driver will deliver the food to the user. The delivery process is tracked in real time, and users can check the current delivery status through the application.

[0892] 5. Gathering feedback and improving the generative AI model

[0893] After receiving the dish, the user uses the application to provide feedback on the dish, including the taste, appearance, and overall satisfaction level, which is sent to the server. This feedback data is used to retrain the generative AI model and is reflected in future recipe generation.

[0894] Hardware and Software Use

[0895] Hardware: smartphones, servers, food printers, delivery vehicles

[0896] Software: Django (web framework), generative AI model (natural language processing technology), REST API (calling the generative AI model)

[0897] Specific examples

[0898] If the user requests a "low carb, gluten-free dinner," the application will generate the following prompt:

[0899] I'd like a low carb, gluten free dinner please.

[0900] This prompt is sent to a generative AI model, and the generated recipe is printed as a meal using a food printer and delivered. The generated recipe is a low-carb, gluten-free menu based on protein-rich chicken breast and vegetables. After receiving the meal, the user provides feedback through the application, such as "The taste was very good, but I wish there was a little more," and this feedback is reflected in the next recipe generation.

[0901] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0902] Step 1:

[0903] The user uses the device to input preferences and conditions (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.) into the application. The device temporarily stores this information and sends it to the server. The input data is in text format and includes specific information about the user's preferences.

[0904] Step 2:

[0905] The server generates a prompt for the generative AI model based on the user's preferences and conditions sent from the device and sends it. The prompt is text that is automatically generated based on the user's request. The generative AI model receives this prompt and generates the optimal recipe. Data processing involves converting the user's preferences and conditions into a format suitable for the generative AI model.

[0906] Step 3:

[0907] The generated recipe is sent back to the server, which interprets the recipe content and sends recipe instructions to the food printer. The recipe data includes the necessary ingredients, cooking steps, cooking time, etc. The server converts this information into a format compatible with the food printer.

[0908] Step 4:

[0909] The food printer automatically mixes the specified ingredients based on the recipe instructions received from the server and creates the dish according to the cooking steps, measuring the amount of food ingredients and operating automated cooking equipment for each cooking step.

[0910] Step 5:

[0911] Once the food is ready, the food printer sends a notification to the server. When the server receives the notification, it issues a delivery instruction to the delivery center and assigns an available driver. During this process, it references the delivery center's database to select the most suitable driver.

[0912] Step 6:

[0913] The delivery driver will receive the requested food and deliver it to the user. The delivery progress is reported to the server in real time, and the user can check the delivery status through the application.

[0914] Step 7:

[0915] After receiving the food, the user provides feedback using the application. The feedback includes evaluation data on the taste, appearance, quantity, satisfaction level, etc. of the food. The device then sends this to the server.

[0916] Step 8:

[0917] The server accumulates the received feedback data and uses it to retrain the generative AI model, improving its accuracy and reflecting it in future recipe generation.

[0918] The above are the specific processing steps of the system that realizes the application example.

[0919] 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.

[0920] The present invention is a system that uses a generative AI model to create dishes based on a user's preferences and conditions, and further combines it with an emotion engine that recognizes the user's emotions. This makes it possible to provide dishes that are more accurately tailored to the user's preferences and emotions. The present invention is specifically implemented as follows.

[0921] First, a user opens an application (web app or mobile app) and uses an interface to input preferences and conditions (likes, dislikes, allergies, calorie restrictions, etc.) Dedicated input fields, checkboxes, and selection menus are provided for this input task.

[0922] The information entered by the user is temporarily stored on the device and then sent to a server, including details about the user's personal information and cooking preferences.

[0923] The server analyzes the user's preferences and conditions data and calls up a generative AI model. This generative AI model has been trained from multiple recipe data and automatically generates the optimal recipe based on the user's input conditions.

[0924] After the recipe is generated, the server calls the emotion engine to analyze the user's emotions. The emotion engine analyzes the user's facial expressions, voice, text data, etc. to recognize the user's emotional state. This emotion data is also reflected in the recipe generation process described above.

[0925] The server then sends the generated recipe to the food printer, which automatically mixes the specified ingredients and creates a physical dish according to the cooking instructions. For example, if a user requests a "soup to eat when you want to relax," the generative AI model will select ingredients and cooking methods that will enhance the relaxing effect based on the user's emotions recognized by the emotion engine.

[0926] Once the printed meal is ready, the server sends the information to a local distribution center, where multiple drivers are waiting, and an available driver will deliver the meal to the address specified by the user.

[0927] After the delivery is complete, the user again uses the application to provide feedback on the food, which may include the food's taste, appearance, overall satisfaction, and emotional response to the entire experience. This feedback is sent to and collected by the server.

[0928] The server retrains the generative AI model based on user feedback and data from the emotion engine, so that the next time it generates a recipe, it will provide dishes that better match the user's preferences and emotions.

[0929] As a concrete example, if a user requests a "light meal that helps relieve stress," the emotion engine will recognize that the user is under stress from their facial expressions and voice. Based on this information, the generative AI model will select ingredients and cooking methods that are effective in relieving stress and generate the optimal recipe. The food printer will create a meal based on the recipe and deliver it to the user. Feedback will add previously unrecognized stress factors and taste preferences, and these will be reflected in future services.

[0930] As described above, the present invention is a system that provides more personalized food delivery by combining emotion recognition using an emotion engine with user preferences and conditions, which can significantly improve user satisfaction and frequency of use.

[0931] The processing flow will be explained below.

[0932] Step 1:

[0933] The user opens the application and enters their preferences and requirements (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.) through the interface. Input operations are performed using text boxes, check boxes, drop-down menus, etc.

[0934] Step 2:

[0935] The device temporarily stores the preferences and conditions entered by the user and then transmits them to the server, including all the information entered.

[0936] Step 3:

[0937] The server processes the received user data and invokes the generative AI model, which uses pre-trained data to create optimal recipes based on the user's preferences and conditions.

[0938] Step 4:

[0939] The server passes the generated recipe information to the emotion engine, which acquires and analyzes emotion data based on the user's facial expressions, voice, or text to recognize the user's emotional state.

[0940] Step 5:

[0941] The server uses the emotional data obtained from the emotion engine to optimize the recipe, specifically selecting ingredients and cooking methods that best suit the user's emotional state and fine-tuning the recipe.

[0942] Step 6:

[0943] The server sends the optimized recipe to the food printer, including details such as the specific ingredient list, cooking instructions, and quantities required.

[0944] Step 7:

[0945] The food printer prints physical dishes based on the received recipe, for example, automatically mixing the specified ingredients and following the cooking instructions to complete the dish.

[0946] Step 8:

[0947] Once the food printer has completed the cooking process, it notifies the server, which then sends the information to a local distribution center.

[0948] Step 9:

[0949] Multiple drivers are waiting at the delivery center. The server sends printed delivery instructions to the appropriate driver, who then delivers the food to the address specified by the user.

[0950] Step 10:

[0951] After receiving their food, users use the application again to provide feedback on the food, including its taste, appearance, overall satisfaction, and emotional response to the entire experience.

[0952] Step 11:

[0953] The device sends the user's feedback to the server, which includes detailed evaluation information and emotion data.

[0954] Step 12:

[0955] The server retrains the generative AI model based on the collected feedback and emotional data, allowing it to provide dishes that better suit the user's preferences and emotions in future recipe generation.

[0956] Through these steps, the system of the present invention can provide more personalized food by incorporating emotion recognition in addition to user preferences and conditions, thereby improving user satisfaction and frequency of use.

[0957] Example 2

[0958] 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."

[0959] Conventional systems were unable to consider the user's emotional state when providing food based on the user's preferences and conditions. As a result, they were unable to provide food that matched the user's momentary mood or emotions, potentially reducing user satisfaction. Furthermore, mechanisms for effectively utilizing user feedback to improve generative AI models were limited, meaning that subsequent food offerings may not necessarily match the user's preferences or emotions. To address these issues, a more personalized food offering mechanism that reflects the user's emotional data is needed.

[0960] 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 means for providing an interface for a user to input preferences and conditions, means for using a generative AI model to output a recipe generated based on the user's input, and means for invoking an emotion engine to reflect the user's emotional data in the recipe generated by the generative AI model. This enables the provision of more personalized dishes that reflect not only the user's preferences and conditions but also their emotional state. Furthermore, by combining means for collecting feedback provided by users and improving the generative AI model, it is expected that the accuracy of the generative AI model and user satisfaction will be improved.

[0961] A "user" is an individual who uses the system to make a food request.

[0962] An "interface" is an input device or software screen provided for a user to input preferences and requirements.

[0963] A "generative AI model" is an artificial intelligence model that automatically generates optimal recipes based on input data.

[0964] A "food printer" is a device that creates physical dishes using specified ingredients based on a recipe generated by a generative AI model.

[0965] An "emotion engine" is a program or system that analyzes a user's facial expressions, voice, and text data to recognize their emotional state.

[0966] "Feedback" refers to ratings and comments about the taste and appearance of the food provided by the user, overall satisfaction, and emotional response.

[0967] A "server" is a computer system that receives and analyzes input data from users, and then calls generative AI models and emotion engines for processing.

[0968] "Delivery means" refers to a means for physically delivering the prepared meal to the address specified by the user.

[0969] "Temporary storage" refers to the short-term storage of data on preferences and conditions entered by the user.

[0970] "Data analysis" is the process of analyzing user input data, converting it into an appropriate format, and extracting the required information.

[0971] MODE FOR CARRYING OUT THE INVENTION

[0972] The present invention is a system that provides optimal dishes based on a user's preferences and conditions. The system aims to improve user satisfaction by analyzing the user's emotions and providing more personalized dishes. Specific embodiments for implementing the present invention are described below.

[0973] System Overview

[0974] First, a user opens an application (web app or mobile app) on their smartphone or computer. This application provides an interface for the user to input their preferences and conditions. The interface provides input fields, checkboxes, and drop-down menus for favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.

[0975] The information entered by the user is temporarily stored in the device's local storage or the browser's session storage. This input data is then sent to a server, where a computer system is located to analyze and process the data. This processing can be performed using cloud technologies such as AWS Lambda or Google Cloud Functions.

[0976] The server analyzes the received user data and calls up a generative AI model, which has been trained in advance using multiple recipe data sets and automatically generates optimal recipes based on the user's input conditions.

[0977] The server then invokes an emotion engine, which uses facial expressions, voice, and text data to analyze the user's emotional state. The emotion engine could be, for example, Microsoft Azure's Emotion API. The emotion data is also reflected in the generated recipe. For example, if a user wants to relax, the server can select ingredients and cooking methods that match that emotional state.

[0978] The generated optimal recipe information is sent from the server to the food printer, which automatically mixes the specified ingredients and creates a physical dish using 3D food printing technology. The information is then sent in real time to a local distribution center, where it is delivered to the user's specified address via a delivery method.

[0979] After the food is delivered to the user, the user uses the application to provide feedback on the food, which can range from taste and appearance to overall satisfaction and emotional response. The feedback is sent to the server, and the collected data is used to retrain the generative AI model, allowing it to provide a more personalized and optimal dish for future meals.

[0980] Specific examples

[0981] Consider a case where a user opens the app and requests a "stress-relieving snack." The emotion engine recognizes that the user is under stress from their facial expressions and voice. Based on this information, the generative AI model selects ingredients and cooking methods that are effective in relieving stress, generating a recipe such as herbal tea or nut bars. This is then printed using a food printer and delivered to the user. The user provides feedback on the food that arrives, and this information is reflected in future service plans.

[0982] Prompt Sentence Examples

[0983] An example of a prompt is as follows:

[0984] User: Opens the app and enters preferences and requirements.

[0985] Device: Temporarily save user information.

[0986] Server: Analyzes the data and invokes the generative AI model.

[0987] Generative AI model: Automatically generates optimal recipes.

[0988] Server: Calls the emotion engine and recognizes the user's emotional state.

[0989] Server: Sends the generated recipe to the food printer.

[0990] Food printer: Create your food.

[0991] Delivery point: delivers food to the user's address.

[0992] Users: Provide feedback.

[0993] Server: Retrain the generative AI model based on feedback and emotion data.

[0994] In this way, the embodiment of the present invention combines emotion recognition by the emotion engine with user preferences and conditions to provide more personalized food, which is expected to significantly improve user satisfaction and frequency of use.

[0995] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0996] Step 1:

[0997] The user opens the application and inputs their preferences and requirements. The application provides an interface for inputting their favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc. The user's input information is collected via text fields and check boxes. The input data is treated as information on preferences and requirements.

[0998] Input: User preferences and conditions

[0999] Output: User input data (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.)

[1000] Step 2:

[1001] The device temporarily stores the user's input data. The input data is stored in local storage or the browser's session storage and prepared for transmission to the server. The stored data may also be backed up to ensure reliability.

[1002] Input: User-entered data

[1003] Output: Temporarily saved data

[1004] Step 3:

[1005] The device sends the temporarily stored data to the server. Data such as the user's preferences and conditions are sent to the server via an HTTP request. Encryption technology such as SSL is used to ensure secure communication.

[1006] Input:Temporarily saved data

[1007] Output: Data sent to the server

[1008] Step 4:

[1009] The server analyzes the data received from the user. During the analysis process, the data items are appropriately classified and the necessary information is extracted. For example, the data can be divided into a list of favorite ingredients and a list of allergy information. Scripts written in Python or Java are often used for data analysis.

[1010] Input: Data sent to the server

[1011] Output: Categorized and organized data items

[1012] Step 5:

[1013] The server calls the generative AI model and generates a recipe based on the user's criteria. The generative AI model selects the optimal recipe from a large amount of recipe data it has learned in the past. To call the model, a request is sent via an API. Machine learning technology is used in the generation process.

[1014] Input: Categorised and organised data items

[1015] Output: The generated optimal recipe

[1016] Step 6:

[1017] The server calls the emotion engine to analyze the user's emotional state. The emotion engine inputs the user's facial expressions, voice, and text data to recognize the emotional state. For example, it uses data obtained from a camera and microphone to determine whether the user is stressed or relaxed.

[1018] Input: User's facial expressions, voice, and text data

[1019] Output: Analyzed user emotion data

[1020] Step 7:

[1021] The server then further adjusts the generated recipe based on the emotional data. The generative AI model evaluates the emotional data and selects ingredients and cooking methods that suit the user's emotional state. For example, it adds relaxing herbs or warm soup.

[1022] Input: Generated optimal recipe and sentiment data

[1023] Output: The final recipe reflecting the sentiment data

[1024] Step 8:

[1025] The server sends the final recipe to the food printer. The final recipe information is sent to the food printer as a data set including the ingredients list and cooking instructions. The food printer receives this data and automatically mixes the ingredients and cooks the food.

[1026] Input: Final recipe reflecting sentiment data

[1027] Output: Recipe data sent to the food printer

[1028] Step 9:

[1029] The food printer creates the meal based on the final recipe, using 3D food printing technology to build the ingredients layer by layer, with temperature and timing controlled according to the cooking instructions.

[1030] Input: Recipe data sent to the food printer

[1031] Output: A physically created dish

[1032] Step 10:

[1033] The server sends information about the completed meal to the delivery center, which then prepares the meal for delivery and issues delivery instructions to the driver. Information is updated in real time and managed to ensure efficient delivery.

[1034] Input: Information about the finished dish

[1035] Output: Information notification to delivery center

[1036] Step 11:

[1037] The driver delivers the food to the address specified by the user. The delivery system selects the optimal route based on the user's address information and provides navigation information to the driver. After delivery is complete, the user receives a delivery completion notification.

[1038] Input: Delivery instructions from the distribution center

[1039] Output: The meal delivered to the user

[1040] Step 12:

[1041] The user uses the application to provide feedback on the dish, including the dish's taste, appearance, overall satisfaction, and emotional response. Feedback data is entered in the form of text and choices.

[1042] Input: User ratings and opinions

[1043] Output: Feedback data

[1044] Step 13:

[1045] The server collects and analyzes the feedback provided by users. The feedback is used to evaluate the quality of the food and user satisfaction. The analysis results are used to generate future recipes.

[1046] Input: Feedback data

[1047] Output: Analysis results and evaluation data

[1048] Step 14:

[1049] The server retrains the generative AI model based on the feedback and emotion data. The retraining process improves the accuracy and user adaptability of the generative AI model, which in turn improves the accuracy of recipe generation from the next time onwards.

[1050] Input: Analysis results and feedback data

[1051] Output: Retrained generative AI model

[1052] (Application example 2)

[1053] 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."

[1054] Conventional food delivery services were able to provide food based on the user's preferences and conditions, but they did not provide services that took into account the user's emotional state. As a result, they were unable to suggest or provide the optimal dish based on the user's emotional state, making it difficult to improve user satisfaction. In addition, feedback on the delivered dish was not sufficiently reflected in the next dish suggestions, making it difficult to improve the quality of the service.

[1055] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for providing an interface for the user to input preferences and conditions, means for using a generative AI model that outputs a recipe generated based on the user's input, means for using an emotion engine that recognizes the user's emotional state, means for reflecting emotion data obtained from the emotion engine in the generative AI model, means for operating a cooking machine that prints a physical dish based on the recipe generated by the generative AI model, delivery means for delivering the physical dish to the user, and means for collecting feedback provided by the user and improving the generative AI model. This makes it possible to provide food that takes into account the user's emotional state in addition to their preferences and conditions, thereby improving user satisfaction and the quality of food delivery services.

[1056] "User" refers to an individual who uses the system to order food and input their preferences and requirements.

[1057] "Interface" refers to the screens and tools that users use to input information into a system.

[1058] A "generative AI model" refers to an artificial intelligence model that automatically generates optimal recipes based on the user's preferences and conditions.

[1059] An "emotion engine" refers to software or algorithms that recognize a user's emotional state from facial expressions, voice, text data, etc.

[1060] "Emotion data" refers to information about a user's emotional state obtained by an emotion engine.

[1061] "Cooking machine" refers to a device that prints or cooks physical dishes based on recipes generated by generative AI models.

[1062] "Delivery method" refers to the mechanism or method for delivering the created meal to the address specified by the user.

[1063] "Feedback" refers to the action of a user inputting their opinion or evaluation regarding the food or service provided.

[1064] "Server" refers to the computer system that receives and analyzes user input data and runs the generative AI model and emotion engine.

[1065] A specific embodiment of a system for realizing an application example of the present invention will be described below. The present invention is a system for providing optimal dishes based on a user's preferences and emotional state, and includes a server, an emotion engine, a generative AI model, a cooking machine, and a delivery means.

[1066] Overall system configuration

[1067] 1. User Device

[1068] Interface: Provides an application that allows users to input their preferences and conditions. A typical example is a smartphone app. Users input their favorite ingredients, disliked ingredients, allergy information, calorie restrictions, emotional state, etc.

[1069] 2. Server

[1070] Data Receipt and Storage: Information entered by the user is received and temporarily stored.

[1071] Generative AI model: Runs an artificial intelligence model that generates optimal recipes based on user preferences and conditions.

[1072] Emotion engine: Recognizes emotions from user input data (facial expressions, voice, text) and obtains emotional data.

[1073] Data integration: The acquired emotional data is fed into the generative AI model to generate recipes based on the emotional state.

[1074] 3. Cooking machine

[1075] Food Printer: Operates an automated cooking machine that creates physical food based on recipes sent from the server, allowing for precise mixing and cooking of ingredients.

[1076] 4. Delivery method

[1077] Delivery people and drones: The finished meal is delivered to the address specified by the user, either by automated drones or human delivery people.

[1078] 5. Feedback System

[1079] Rating collection: Provides an interface for users to enter feedback on the food and service provided.

[1080] Data analysis and learning: Retrain the generative AI model based on collected feedback to improve the quality of future recipe generation.

[1081] Specific examples

[1082] The user opens the smartphone app and enters the following information:

[1083] User name: Sato

[1084] Favorite ingredients: chicken, tomatoes

[1085] Disliked ingredient: Fish sauce

[1086] Allergens: nuts

[1087] Calorie restriction: 600 kcal or less

[1088] Current Emotion: High Stress

[1089] Based on this, the prompt would look like this:

[1090] User Sato is currently feeling stressed. Please suggest a dish that uses chicken and tomatoes, is nut-free, and is under 600 kcal. It should not contain fish sauce.

[1091] The server receives this data and generates an optimal recipe using the generative AI model and emotion engine. It then sends the recipe to the cooking machine, which creates the physical dish. The finished dish is delivered to the user via a delivery vehicle, and the user again provides feedback using the app. This feedback is collected by the server and used to retrain the generative AI model.

[1092] The key hardware and software used throughout the process include smartphones, servers, generative AI models, emotion engines, food printers, delivery drones and delivery people.

[1093] This allows for the provision of high-quality food that takes into account not only the user's preferences and conditions, but also their emotional state.

[1094] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1095] Step 1:

[1096] The user enters preferences and requirements.

[1097] Input: The user enters their favorite ingredients, disliked ingredients, allergy information, calorie restrictions, and current emotional state into the smartphone app.

[1098] How it works: An application on a user's device provides specialized input fields, checkboxes, and selection menus.

[1099] Output: User-entered preferences and conditions data.

[1100] Step 2:

[1101] Send and temporarily save input data.

[1102] Input: Data entered by the user through the application.

[1103] Operation: The user terminal temporarily stores this data and sends it to the server.

[1104] Output: User preferences and requirements data transferred to the server.

[1105] Step 3:

[1106] Recipe generation using generative AI models.

[1107] Input: User preferences and requirements data stored on the server.

[1108] How it works: The server invokes a generative AI model to generate the optimal recipe based on the user's preferences and conditions.

[1109] Output: The generated recipe data.

[1110] Step 4:

[1111] Acquiring emotion data.

[1112] Input: Data about the emotional state submitted by the user.

[1113] How it works: The server uses an emotion engine to analyze the user's emotional state, which may involve facial recognition, speech analysis, or text analysis.

[1114] Output: Emotion data from the emotion engine.

[1115] Step 5:

[1116] Reflecting emotional data.

[1117] Input: Generated recipe data and sentiment data.

[1118] How it works: The server applies the emotional data to the generative AI model and re-optimizes the recipe.

[1119] Output: Recipe data optimized for emotional states.

[1120] Step 6:

[1121] Cooking food using a cooking machine.

[1122] Input: Optimized recipe data.

[1123] Operation: The server sends the optimized recipe data to the cooking machine (food printer), which then automatically mixes the specified ingredients and prepares the dish according to the recipe.

[1124] Output: The finished physical dish.

[1125] Step 7:

[1126] Arrange delivery.

[1127] Input: The finished dish and the user's address information.

[1128] How it works: The server sends the completed meal and address information to a delivery vehicle (delivery person or drone) to arrange for delivery.

[1129] Output: The meal delivered to the user's address.

[1130] Step 8:

[1131] Get feedback.

[1132] Input: User's ratings and opinions about the food and service provided.

[1133] How it works: The user enters feedback through a smartphone app, which then sends this feedback to the server.

[1134] Output: User feedback data stored on the server.

[1135] Step 9:

[1136] Retraining generative AI models.

[1137] Input: Feedback data and emotion data.

[1138] How it works: The server retrains the generative AI model based on the collected feedback and emotion data, improving the accuracy of future recipe generation.

[1139] Output: An improved generative AI model.

[1140] The above is the specific processing flow of this system.

[1141] 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.

[1142] 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.

[1143] 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.

[1144] [Fourth embodiment]

[1145] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1146] 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.

[1147] 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).

[1148] 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.

[1149] 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.

[1150] 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).

[1151] 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. 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.

[1152] 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.

[1153] 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.

[1154] 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.

[1155] 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.

[1156] 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.

[1157] 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."

[1158] The present invention is a system that allows users to order food based on their specific preferences and conditions, creates a recipe for the food through a generative AI model, and delivers the physically printed food to the user. The present invention is specifically implemented as follows.

[1159] First, the user uses a dedicated application (web app or mobile app) to input their preferences and conditions (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.) This information is temporarily stored on the device and later sent to the server.

[1160] The server receives the information sent by the user and calls up a generative AI model based on that information. This generative AI model is trained using multiple recipe data sets and generates new recipes optimized for the user's preferences.

[1161] The server then sends the generated recipe to the food printer, which then generates a physical dish based on the recipe. Specifically, the food printer automatically mixes the specified ingredients and follows the cooking instructions to complete the dish.

[1162] After the food is ready, the server receives a notification from the food printer and issues a delivery instruction to a local delivery center. Multiple drivers are waiting at the delivery center, and an available driver will deliver the food to the user's location.

[1163] After the delivery is complete, the user uses the app again to provide feedback on the food. The feedback can cover a variety of topics, including the food's taste, appearance, and overall satisfaction. This feedback is sent to the server and used to improve the generative AI model. Specifically, the feedback data is used to retrain the generative AI model and reflect it in future recipe generation.

[1164] As a concrete example, suppose a user requests a "high-protein, low-calorie smoothie to drink after sports." The user inputs these requirements into the application and submits it. The server receives the request and generates an optimal smoothie recipe based on a generative AI model. The generated recipe is sent to a food printer, which creates a smoothie using the necessary ingredients (e.g., protein powder, low-fat yogurt, blueberries, etc.). The created smoothie is promptly delivered to the user. After enjoying the smoothie, the user can provide feedback on the taste and effects, which will be used to help with future orders.

[1165] As described above, the system of the present invention provides an environment where users can easily enjoy meals optimized to their preferences and conditions, regardless of where they live. This reduces regional disparities in food delivery services and improves user satisfaction and frequency of use.

[1166] The processing flow will be explained below.

[1167] Step 1:

[1168] The user opens the application. The user uses an interface to input their preferences and conditions (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.). The information entered by the user is temporarily stored on the device.

[1169] Step 2:

[1170] The device sends the user's preferences and requirements to the server, including the user's personal information and details of the desired dish.

[1171] Step 3:

[1172] The server analyzes the data received from the user and calls a generative AI model. The generative AI model generates a recipe that takes into account the user's preferences and conditions. This recipe is based on a model trained on multiple recipe data.

[1173] Step 4:

[1174] The server sends the generated recipe, which includes the ingredients, cooking steps, and quantities, to the food printer.

[1175] Step 5:

[1176] The food printer prints physical meals based on the recipe it receives, automatically mixing ingredients like protein powder, low-fat yogurt, and blueberries, and cooking them according to the instructions.

[1177] Step 6:

[1178] Once the food printer has printed the meal, it notifies the server, which then sends the information to a local distribution center.

[1179] Step 7:

[1180] Multiple drivers are waiting at the delivery center. The server issues printed delivery instructions for the food to an available driver. The driver then picks up the food and delivers it to the address specified by the user.

[1181] Step 8:

[1182] The user receives the food and provides feedback on it through the application, including the taste, appearance, and overall satisfaction with the food.

[1183] Step 9:

[1184] The terminal sends feedback from the user to the server, which collects and analyzes this feedback.

[1185] Step 10:

[1186] The server retrains the generative AI model based on the collected feedback, a process that ensures that future recipes are more tailored to the user's preferences.

[1187] Through the above steps, the system of the present invention can provide meals optimized to the preferences and conditions of the user regardless of the area where the user lives, thereby improving user satisfaction and frequency of use.

[1188] Example 1

[1189] 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."

[1190] Conventional food delivery systems have made it difficult for users to easily order food based on their specific preferences and conditions, and then automatically generate and deliver it. They also lacked a mechanism for improving recipes based on user feedback. As a result, it was difficult to improve user satisfaction and meet individual needs.

[1191] 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.

[1192] In this invention, the server includes means for providing an interface for users to input preferences and conditions, means for using a generative AI model that outputs recipes generated based on the user's input, means for operating a food printer that generates physical food based on the recipes generated by the generative AI model, means for collecting feedback provided by the user and improving the generative AI model, means for temporarily saving the preferences and conditions input by the user, means for calling the generative AI model to generate recipes, and means for generating prompt sentences for inputting user information into the generative AI model. This not only enables users, wherever they live, to easily order and enjoy food optimized for their preferences and conditions, but also enables the service to be continuously improved based on the provided feedback.

[1193] "User" refers to any person or entity that uses the System to order food based on specific preferences and requirements.

[1194] "Interface" refers to software, such as a web or mobile application, that provides a means for users to input their specific preferences or requirements.

[1195] "Generative AI model" refers to the artificial intelligence algorithm used to generate optimal recipes based on user input.

[1196] A "food printer" refers to a device that automatically produces physical food products based on recipes generated by a generative AI model.

[1197] "Feedback" refers to ratings and opinions provided by users regarding food quality and service.

[1198] "Server" refers to a computer system that receives and stores information from users and performs various processes such as calling up generative AI models.

[1199] A "prompt sentence" refers to the instructions or questions conveyed to a generative AI model based on user input information.

[1200] "Storage means" refers to a storage device or database for temporarily storing preferences and conditions entered by the user.

[1201] The present invention is a system that allows users to order food based on their specific preferences and requirements, creates a recipe for the food through a generative AI model, and delivers the physically printed food to the user. This system is implemented using the following specific hardware and software:

[1202] First, users input their preferences and conditions using a dedicated interface (web application or mobile application). This interface allows users to easily enter detailed information such as favorite ingredients, disliked ingredients, allergy information, and calorie restrictions.

[1203] For example, if a user requests a "high-protein, low-calorie smoothie to drink after sports," the following prompt text might be entered:

[1204] "Make a high-protein, low-calorie smoothie to drink after exercise. It must meet the following criteria: Favorite ingredients: blueberries, bananas, low-fat yogurt. Disliked ingredients: spirulina. Allergy information: nut allergy. Calorie limit: 200 calories or less."

[1205] The terminal (user's device) temporarily stores the input information and then transmits it to the server, which receives and analyzes the user's input information sent from the terminal.

[1206] The server then calls a generative AI model, which uses the user's input as a prompt, and the model (which may include natural language processing libraries or machine learning algorithms) generates recipes optimized for the user's preferences based on a vast amount of recipe data.

[1207] The generated recipe is sent from the server to the food printer in a standard format such as JSON, which then analyzes the recipe data and automatically mixes the necessary ingredients. Physical food is then produced according to the specific cooking instructions.

[1208] When the food is ready, the food printer sends a completion notification to the server. The server receives this notification and issues a delivery instruction to a local distribution center. The distribution center then issues a delivery instruction to an available driver based on the received notification and delivers the food to the user.

[1209] After enjoying the delivered food, the user again uses the interface to provide feedback, which can include various aspects such as the food's taste, appearance, and overall satisfaction. This feedback data is sent to the server and used to retrain the generative AI model.

[1210] In this way, the present invention provides an environment where users can easily order and enjoy food optimized for their preferences and conditions, regardless of where they live. This system can mitigate regional disparities in food delivery and improve user satisfaction and frequency of use.

[1211] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1212] Step 1:

[1213] The user launches a dedicated interface (web application or mobile application) and inputs their preferences and conditions. Input items include favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc. An example of a specific prompt is, "Make a high-protein, low-calorie smoothie to drink after exercise. Please meet the following conditions: Favorite ingredients: blueberries, bananas, low-fat yogurt. Disliked ingredients: spirulina. Allergy information: nut allergy. Calorie restrictions: 200 calories or less." This information is sent to the server by the user's operation.

[1214] Input: User preferences and conditions

[1215] Output: User information sent to the server

[1216] Step 2:

[1217] The device temporarily stores the information entered by the user and then transmits it to the server via a connection, specifically by using an HTTP POST request to transfer the data to the server, and then waits for a response to confirm that the information was sent correctly.

[1218] Input: Preferences and conditions data entered by the user

[1219] Output: User information sent to the server

[1220] Step 3:

[1221] The server receives user information sent from the device, analyzes this information, and generates a prompt that matches the user's request. This prompt is then passed to the generative AI model.

[1222] Input: User information sent from the device

[1223] Output: The prompt passed to the generative AI model

[1224] Step 4:

[1225] The server calls the generative AI model and inputs a prompt based on the user's information. The generative AI model generates the optimal recipe based on a huge amount of recipe data. Specifically, it uses natural language processing libraries and machine learning algorithms.

[1226] Input: prompt statement

[1227] Output: A new recipe from a generative AI model

[1228] Step 5:

[1229] The server sends the generated recipe data to the food printer, which receives the data, analyzes the recipe, and automatically mixes the necessary ingredients and creates the dish according to the specified cooking procedure.

[1230] Input: Recipe data from a generative AI model

[1231] Output: Physical food produced by a food printer

[1232] Step 6:

[1233] The food printer sends a message to the server notifying it that the food is ready. The server receives this notification and issues a delivery instruction to a local delivery center. The delivery center then assigns an available driver to pick up the food and deliver it to the user.

[1234] Input: Completion notification from food printer

[1235] Output: Delivery instructions to the distribution center

[1236] Step 7:

[1237] The user receives the delivered food and provides feedback on the food through the application, including taste, appearance, and overall satisfaction. The feedback is then sent to the server.

[1238] Input: User feedback

[1239] Output: Feedback data sent to the server

[1240] Step 8:

[1241] The server collects feedback data received from users and uses this data to retrain the generative AI model, which is then reflected in future recipe generation, resulting in continuous improvement of the service.

[1242] Input: User feedback data

[1243] Output: Improved recipes from a retrained generative AI model

[1244] (Application example 1)

[1245] 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."

[1246] Conventional food delivery systems have difficulty providing individually customized meals based on the user's preferences and conditions, leading to issues such as lower user satisfaction and reduced frequency of use due to regional disparities. Furthermore, there are also issues with the effort and efficiency involved in preparing and delivering meals, making it impossible to provide an environment that users can easily use.

[1247] 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.

[1248] In this invention, the server includes: means for providing an interface for a user to input preferences and conditions; means for using a generative AI model to output a recipe generated based on the user's input; means for operating a food printer to print a physical dish based on the recipe generated by the generative AI model; means for delivering the physical dish to the user; means for collecting feedback provided by the user and improving the generative AI model; and means including an application for generating recipes based on the preferences and conditions input by the user and managing delivery. This enables users to easily order and receive dishes optimized for their individual preferences and conditions, mitigating regional disparities in food delivery and improving user satisfaction and frequency of use.

[1249] A "user" is an entity that orders food based on specific preferences or requirements.

[1250] An "interface" is a means by which a user inputs preferences and requirements.

[1251] A "generative AI model" is an artificial intelligence technology that generates optimal recipes based on user input information.

[1252] A "food printer" is a device that automatically cooks and prints physical dishes according to a generated recipe.

[1253] "Delivery means" refers to the means or system for delivering the created meal to the user.

[1254] "Feedback" is user-provided evaluation information about a dish, and is data used to improve the generative AI model.

[1255] An "application" is software that allows a user to input food preferences and requirements and place an order.

[1256] This invention is a system that allows users to order food based on their specific preferences and requirements, creates a recipe for it through a generative AI model, and delivers the physically printed food to the user using a food printer.

[1257] System configuration and operation

[1258] 1. User Input Interface

[1259] Users use a dedicated application (smartphone application or web application) to input their cooking preferences and conditions (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.) This information is temporarily stored on the user's device and then sent to the server.

[1260] 2. Recipe generation using generative AI models

[1261] The server receives the information sent by the user and calls a generative AI model based on that information. This generative AI model is trained using multiple recipe data sets and generates new recipes optimized for the user's preferences. This process uses natural language processing and deep learning technologies and is executed on the server.

[1262] 3. Food printing to create dishes

[1263] The generated recipe is sent from the server to the food printer, which then automatically mixes the specified ingredients based on the recipe and completes the dish according to the instructions. The food printer has advanced cooking technology and can handle a variety of ingredients.

[1264] 4. Food delivery

[1265] Once the food is ready, the server issues a delivery order. Delivery is made from a local distribution center with multiple drivers waiting. An available driver will deliver the food to the user. The delivery process is tracked in real time, and users can check the current delivery status through the application.

[1266] 5. Gathering feedback and improving the generative AI model

[1267] After receiving the dish, the user uses the application to provide feedback on the dish, including the taste, appearance, and overall satisfaction level, which is sent to the server. This feedback data is used to retrain the generative AI model and is reflected in future recipe generation.

[1268] Hardware and Software Use

[1269] Hardware: smartphones, servers, food printers, delivery vehicles

[1270] Software: Django (web framework), generative AI model (natural language processing technology), REST API (calling the generative AI model)

[1271] Specific examples

[1272] If the user requests a "low carb, gluten-free dinner," the application will generate the following prompt:

[1273] I'd like a low carb, gluten free dinner please.

[1274] This prompt is sent to a generative AI model, and the generated recipe is printed as a meal using a food printer and delivered. The generated recipe is a low-carb, gluten-free menu based on protein-rich chicken breast and vegetables. After receiving the meal, the user provides feedback through the application, such as "The taste was very good, but I wish there was a little more," and this feedback is reflected in the next recipe generation.

[1275] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1276] Step 1:

[1277] The user uses the device to input preferences and conditions (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.) into the application. The device temporarily stores this information and sends it to the server. The input data is in text format and includes specific information about the user's preferences.

[1278] Step 2:

[1279] The server generates a prompt for the generative AI model based on the user's preferences and conditions sent from the device and sends it. The prompt is text that is automatically generated based on the user's request. The generative AI model receives this prompt and generates the optimal recipe. Data processing involves converting the user's preferences and conditions into a format suitable for the generative AI model.

[1280] Step 3:

[1281] The generated recipe is sent back to the server, which interprets the recipe content and sends recipe instructions to the food printer. The recipe data includes the necessary ingredients, cooking steps, cooking time, etc. The server converts this information into a format compatible with the food printer.

[1282] Step 4:

[1283] The food printer automatically mixes the specified ingredients based on the recipe instructions received from the server and creates the dish according to the cooking steps, measuring the amount of food ingredients and operating automated cooking equipment for each cooking step.

[1284] Step 5:

[1285] Once the food is ready, the food printer sends a notification to the server. When the server receives the notification, it issues a delivery instruction to the delivery center and assigns an available driver. During this process, it references the delivery center's database to select the most suitable driver.

[1286] Step 6:

[1287] The delivery driver will receive the requested food and deliver it to the user. The delivery progress is reported to the server in real time, and the user can check the delivery status through the application.

[1288] Step 7:

[1289] After receiving the food, the user provides feedback using the application. The feedback includes evaluation data on the taste, appearance, quantity, satisfaction level, etc. of the food. The device then sends this to the server.

[1290] Step 8:

[1291] The server accumulates the received feedback data and uses it to retrain the generative AI model, improving its accuracy and reflecting it in future recipe generation.

[1292] The above are the specific processing steps of the system that realizes the application example.

[1293] 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.

[1294] The present invention is a system that uses a generative AI model to create dishes based on a user's preferences and conditions, and further combines it with an emotion engine that recognizes the user's emotions. This makes it possible to provide dishes that are more accurately tailored to the user's preferences and emotions. The present invention is specifically implemented as follows.

[1295] First, a user opens an application (web app or mobile app) and uses an interface to input preferences and conditions (likes, dislikes, allergies, calorie restrictions, etc.) Dedicated input fields, checkboxes, and selection menus are provided for this input task.

[1296] The information entered by the user is temporarily stored on the device and then sent to a server, including details about the user's personal information and cooking preferences.

[1297] The server analyzes the user's preferences and conditions data and calls up a generative AI model. This generative AI model has been trained from multiple recipe data and automatically generates the optimal recipe based on the user's input conditions.

[1298] After the recipe is generated, the server calls the emotion engine to analyze the user's emotions. The emotion engine analyzes the user's facial expressions, voice, text data, etc. to recognize the user's emotional state. This emotion data is also reflected in the recipe generation process described above.

[1299] The server then sends the generated recipe to the food printer, which automatically mixes the specified ingredients and creates a physical dish according to the cooking instructions. For example, if a user requests a "soup to eat when you want to relax," the generative AI model will select ingredients and cooking methods that will enhance the relaxing effect based on the user's emotions recognized by the emotion engine.

[1300] Once the printed meal is ready, the server sends the information to a local distribution center, where multiple drivers are waiting, and an available driver will deliver the meal to the address specified by the user.

[1301] After the delivery is complete, the user again uses the application to provide feedback on the food, which may include the food's taste, appearance, overall satisfaction, and emotional response to the entire experience. This feedback is sent to and collected by the server.

[1302] The server retrains the generative AI model based on user feedback and data from the emotion engine, so that the next time it generates a recipe, it will provide dishes that better match the user's preferences and emotions.

[1303] As a concrete example, if a user requests a "light meal that helps relieve stress," the emotion engine will recognize that the user is under stress from their facial expressions and voice. Based on this information, the generative AI model will select ingredients and cooking methods that are effective in relieving stress and generate the optimal recipe. The food printer will create a meal based on the recipe and deliver it to the user. Feedback will add previously unrecognized stress factors and taste preferences, and these will be reflected in future services.

[1304] As described above, the present invention is a system that provides more personalized food delivery by combining emotion recognition using an emotion engine with user preferences and conditions, which can significantly improve user satisfaction and frequency of use.

[1305] The processing flow will be explained below.

[1306] Step 1:

[1307] The user opens the application and enters their preferences and requirements (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.) through the interface. Input operations are performed using text boxes, check boxes, drop-down menus, etc.

[1308] Step 2:

[1309] The device temporarily stores the preferences and conditions entered by the user and then transmits them to the server, including all the information entered.

[1310] Step 3:

[1311] The server processes the received user data and invokes the generative AI model, which uses pre-trained data to create optimal recipes based on the user's preferences and conditions.

[1312] Step 4:

[1313] The server passes the generated recipe information to the emotion engine, which acquires and analyzes emotion data based on the user's facial expressions, voice, or text to recognize the user's emotional state.

[1314] Step 5:

[1315] The server uses the emotional data obtained from the emotion engine to optimize the recipe, specifically selecting ingredients and cooking methods that best suit the user's emotional state and fine-tuning the recipe.

[1316] Step 6:

[1317] The server sends the optimized recipe to the food printer, including details such as the specific ingredient list, cooking instructions, and quantities required.

[1318] Step 7:

[1319] The food printer prints physical dishes based on the received recipe, for example, automatically mixing the specified ingredients and following the cooking instructions to complete the dish.

[1320] Step 8:

[1321] Once the food printer has completed the cooking process, it notifies the server, which then sends the information to a local distribution center.

[1322] Step 9:

[1323] Multiple drivers are waiting at the delivery center. The server sends printed delivery instructions to the appropriate driver, who then delivers the food to the address specified by the user.

[1324] Step 10:

[1325] After receiving their food, users use the application again to provide feedback on the food, including its taste, appearance, overall satisfaction, and emotional response to the entire experience.

[1326] Step 11:

[1327] The device sends the user's feedback to the server, which includes detailed evaluation information and emotion data.

[1328] Step 12:

[1329] The server retrains the generative AI model based on the collected feedback and emotional data, allowing it to provide dishes that better suit the user's preferences and emotions in future recipe generation.

[1330] Through these steps, the system of the present invention can provide more personalized food by incorporating emotion recognition in addition to user preferences and conditions, thereby improving user satisfaction and frequency of use.

[1331] Example 2

[1332] 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."

[1333] Conventional systems were unable to consider the user's emotional state when providing food based on the user's preferences and conditions. As a result, they were unable to provide food that matched the user's momentary mood or emotions, potentially reducing user satisfaction. Furthermore, mechanisms for effectively utilizing user feedback to improve generative AI models were limited, meaning that subsequent food offerings may not necessarily match the user's preferences or emotions. To address these issues, a more personalized food offering mechanism that reflects the user's emotional data is needed.

[1334] 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 means for providing an interface for a user to input preferences and conditions, means for using a generative AI model to output a recipe generated based on the user's input, and means for invoking an emotion engine to reflect the user's emotional data in the recipe generated by the generative AI model. This enables the provision of more personalized dishes that reflect not only the user's preferences and conditions but also their emotional state. Furthermore, by combining means for collecting feedback provided by users and improving the generative AI model, it is expected that the accuracy of the generative AI model and user satisfaction will be improved.

[1335] A "user" is an individual who uses the system to make a food request.

[1336] An "interface" is an input device or software screen provided for a user to input preferences and requirements.

[1337] A "generative AI model" is an artificial intelligence model that automatically generates optimal recipes based on input data.

[1338] A "food printer" is a device that creates physical dishes using specified ingredients based on a recipe generated by a generative AI model.

[1339] An "emotion engine" is a program or system that analyzes a user's facial expressions, voice, and text data to recognize their emotional state.

[1340] "Feedback" refers to ratings and comments about the taste and appearance of the food provided by the user, overall satisfaction, and emotional response.

[1341] A "server" is a computer system that receives and analyzes input data from users, and then calls generative AI models and emotion engines for processing.

[1342] "Delivery means" refers to a means for physically delivering the prepared meal to the address specified by the user.

[1343] "Temporary storage" refers to the short-term storage of data on preferences and conditions entered by the user.

[1344] "Data analysis" is the process of analyzing user input data, converting it into an appropriate format, and extracting the required information.

[1345] MODE FOR CARRYING OUT THE INVENTION

[1346] The present invention is a system that provides optimal dishes based on a user's preferences and conditions. The system aims to improve user satisfaction by analyzing the user's emotions and providing more personalized dishes. Specific embodiments for implementing the present invention are described below.

[1347] System Overview

[1348] First, a user opens an application (web app or mobile app) on their smartphone or computer. This application provides an interface for the user to input their preferences and conditions. The interface provides input fields, checkboxes, and drop-down menus for favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.

[1349] The information entered by the user is temporarily stored in the device's local storage or the browser's session storage. This input data is then sent to a server, where a computer system is located to analyze and process the data. This processing can be performed using cloud technologies such as AWS Lambda or Google Cloud Functions.

[1350] The server analyzes the received user data and calls up a generative AI model, which has been trained in advance using multiple recipe data sets and automatically generates optimal recipes based on the user's input conditions.

[1351] The server then invokes an emotion engine, which uses facial expressions, voice, and text data to analyze the user's emotional state. The emotion engine could be, for example, Microsoft Azure's Emotion API. The emotion data is also reflected in the generated recipe. For example, if a user wants to relax, the server can select ingredients and cooking methods that match that emotional state.

[1352] The generated optimal recipe information is sent from the server to the food printer, which automatically mixes the specified ingredients and creates a physical dish using 3D food printing technology. The information is then sent in real time to a local distribution center, where it is delivered to the user's specified address via a delivery method.

[1353] After the food is delivered to the user, the user uses the application to provide feedback on the food, which can range from taste and appearance to overall satisfaction and emotional response. The feedback is sent to the server, and the collected data is used to retrain the generative AI model, allowing it to provide a more personalized and optimal dish for future meals.

[1354] Specific examples

[1355] Consider a case where a user opens the app and requests a "stress-relieving snack." The emotion engine recognizes that the user is under stress from their facial expressions and voice. Based on this information, the generative AI model selects ingredients and cooking methods that are effective in relieving stress, generating a recipe such as herbal tea or nut bars. This is then printed using a food printer and delivered to the user. The user provides feedback on the food that arrives, and this information is reflected in future service plans.

[1356] Prompt Sentence Examples

[1357] An example of a prompt is as follows:

[1358] User: Opens the app and enters preferences and requirements.

[1359] Device: Temporarily save user information.

[1360] Server: Analyzes the data and invokes the generative AI model.

[1361] Generative AI model: Automatically generates optimal recipes.

[1362] Server: Calls the emotion engine and recognizes the user's emotional state.

[1363] Server: Sends the generated recipe to the food printer.

[1364] Food printer: Create your food.

[1365] Delivery point: delivers food to the user's address.

[1366] Users: Provide feedback.

[1367] Server: Retrain the generative AI model based on feedback and emotion data.

[1368] In this way, the embodiment of the present invention combines emotion recognition by the emotion engine with user preferences and conditions to provide more personalized food, which is expected to significantly improve user satisfaction and frequency of use.

[1369] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1370] Step 1:

[1371] The user opens the application and inputs their preferences and requirements. The application provides an interface for inputting their favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc. The user's input information is collected via text fields and check boxes. The input data is treated as information on preferences and requirements.

[1372] Input: User preferences and conditions

[1373] Output: User input data (favorite ingredients, disliked ingredients, allergy information, calorie restrictions, etc.)

[1374] Step 2:

[1375] The device temporarily stores the user's input data. The input data is stored in local storage or the browser's session storage and prepared for transmission to the server. The stored data may also be backed up to ensure reliability.

[1376] Input: User-entered data

[1377] Output: Temporarily saved data

[1378] Step 3:

[1379] The device sends the temporarily stored data to the server. Data such as the user's preferences and conditions are sent to the server via an HTTP request. Encryption technology such as SSL is used to ensure secure communication.

[1380] Input:Temporarily saved data

[1381] Output: Data sent to the server

[1382] Step 4:

[1383] The server analyzes the data received from the user. During the analysis process, the data items are appropriately classified and the necessary information is extracted. For example, the data can be divided into a list of favorite ingredients and a list of allergy information. Scripts written in Python or Java are often used for data analysis.

[1384] Input: Data sent to the server

[1385] Output: Categorized and organized data items

[1386] Step 5:

[1387] The server calls the generative AI model and generates a recipe based on the user's criteria. The generative AI model selects the optimal recipe from a large amount of recipe data it has learned in the past. To call the model, a request is sent via an API. Machine learning technology is used in the generation process.

[1388] Input: Categorised and organised data items

[1389] Output: The generated optimal recipe

[1390] Step 6:

[1391] The server calls the emotion engine to analyze the user's emotional state. The emotion engine inputs the user's facial expressions, voice, and text data to recognize the emotional state. For example, it uses data obtained from a camera and microphone to determine whether the user is stressed or relaxed.

[1392] Input: User's facial expressions, voice, and text data

[1393] Output: Analyzed user emotion data

[1394] Step 7:

[1395] The server then further adjusts the generated recipe based on the emotional data. The generative AI model evaluates the emotional data and selects ingredients and cooking methods that suit the user's emotional state. For example, it adds relaxing herbs or warm soup.

[1396] Input: Generated optimal recipe and sentiment data

[1397] Output: The final recipe reflecting the sentiment data

[1398] Step 8:

[1399] The server sends the final recipe to the food printer. The final recipe information is sent to the food printer as a data set including the ingredients list and cooking instructions. The food printer receives this data and automatically mixes the ingredients and cooks the food.

[1400] Input: Final recipe reflecting sentiment data

[1401] Output: Recipe data sent to the food printer

[1402] Step 9:

[1403] The food printer creates the meal based on the final recipe, using 3D food printing technology to build the ingredients layer by layer, with temperature and timing controlled according to the cooking instructions.

[1404] Input: Recipe data sent to the food printer

[1405] Output: A physically created dish

[1406] Step 10:

[1407] The server sends information about the completed meal to the delivery center, which then prepares the meal for delivery and issues delivery instructions to the driver. Information is updated in real time and managed to ensure efficient delivery.

[1408] Input: Information about the finished dish

[1409] Output: Information notification to delivery center

[1410] Step 11:

[1411] The driver delivers the food to the address specified by the user. The delivery system selects the optimal route based on the user's address information and provides navigation information to the driver. After delivery is complete, the user receives a delivery completion notification.

[1412] Input: Delivery instructions from the distribution center

[1413] Output: The meal delivered to the user

[1414] Step 12:

[1415] The user uses the application to provide feedback on the dish, including the dish's taste, appearance, overall satisfaction, and emotional response. Feedback data is entered in the form of text and choices.

[1416] Input: User ratings and opinions

[1417] Output: Feedback data

[1418] Step 13:

[1419] The server collects and analyzes the feedback provided by users. The feedback is used to evaluate the quality of the food and user satisfaction. The analysis results are used to generate future recipes.

[1420] Input: Feedback data

[1421] Output: Analysis results and evaluation data

[1422] Step 14:

[1423] The server retrains the generative AI model based on the feedback and emotion data. The retraining process improves the accuracy and user adaptability of the generative AI model, which in turn improves the accuracy of recipe generation from the next time onwards.

[1424] Input: Analysis results and feedback data

[1425] Output: Retrained generative AI model

[1426] (Application example 2)

[1427] 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."

[1428] Conventional food delivery services were able to provide food based on the user's preferences and conditions, but they did not provide services that took into account the user's emotional state. As a result, they were unable to suggest or provide the optimal dish based on the user's emotional state, making it difficult to improve user satisfaction. In addition, feedback on the delivered dish was not sufficiently reflected in the next dish suggestions, making it difficult to improve the quality of the service.

[1429] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for providing an interface for the user to input preferences and conditions, means for using a generative AI model that outputs a recipe generated based on the user's input, means for using an emotion engine that recognizes the user's emotional state, means for reflecting emotion data obtained from the emotion engine in the generative AI model, means for operating a cooking machine that prints a physical dish based on the recipe generated by the generative AI model, delivery means for delivering the physical dish to the user, and means for collecting feedback provided by the user and improving the generative AI model. This makes it possible to provide food that takes into account the user's emotional state in addition to their preferences and conditions, thereby improving user satisfaction and the quality of food delivery services.

[1430] "User" refers to an individual who uses the system to order food and input their preferences and requirements.

[1431] "Interface" refers to the screens and tools that users use to input information into a system.

[1432] A "generative AI model" refers to an artificial intelligence model that automatically generates optimal recipes based on the user's preferences and conditions.

[1433] An "emotion engine" refers to software or algorithms that recognize a user's emotional state from facial expressions, voice, text data, etc.

[1434] "Emotion data" refers to information about a user's emotional state obtained by an emotion engine.

[1435] "Cooking machine" refers to a device that prints or cooks physical dishes based on recipes generated by generative AI models.

[1436] "Delivery method" refers to the mechanism or method for delivering the created meal to the address specified by the user.

[1437] "Feedback" refers to the action of a user inputting their opinion or evaluation regarding the food or service provided.

[1438] "Server" refers to the computer system that receives and analyzes user input data and runs the generative AI model and emotion engine.

[1439] A specific embodiment of a system for realizing an application example of the present invention will be described below. The present invention is a system for providing optimal dishes based on a user's preferences and emotional state, and includes a server, an emotion engine, a generative AI model, a cooking machine, and a delivery means.

[1440] Overall system configuration

[1441] 1. User Device

[1442] Interface: Provides an application that allows users to input their preferences and conditions. A typical example is a smartphone app. Users input their favorite ingredients, disliked ingredients, allergy information, calorie restrictions, emotional state, etc.

[1443] 2. Server

[1444] Data Receipt and Storage: Information entered by the user is received and temporarily stored.

[1445] Generative AI model: Runs an artificial intelligence model that generates optimal recipes based on user preferences and conditions.

[1446] Emotion engine: Recognizes emotions from user input data (facial expressions, voice, text) and obtains emotional data.

[1447] Data integration: The acquired emotional data is fed into the generative AI model to generate recipes based on the emotional state.

[1448] 3. Cooking machine

[1449] Food Printer: Operates an automated cooking machine that creates physical food based on recipes sent from the server, allowing for precise mixing and cooking of ingredients.

[1450] 4. Delivery method

[1451] Delivery people and drones: The finished meal is delivered to the address specified by the user, either by automated drones or human delivery people.

[1452] 5. Feedback System

[1453] Rating collection: Provides an interface for users to enter feedback on the food and service provided.

[1454] Data analysis and learning: Retrain the generative AI model based on collected feedback to improve the quality of future recipe generation.

[1455] Specific examples

[1456] The user opens the smartphone app and enters the following information:

[1457] User name: Sato

[1458] Favorite ingredients: chicken, tomatoes

[1459] Disliked ingredient: Fish sauce

[1460] Allergens: nuts

[1461] Calorie restriction: 600 kcal or less

[1462] Current Emotion: High Stress

[1463] Based on this, the prompt would look like this:

[1464] User Sato is currently feeling stressed. Please suggest a dish that uses chicken and tomatoes, is nut-free, and is under 600 kcal. It should not contain fish sauce.

[1465] The server receives this data and generates an optimal recipe using the generative AI model and emotion engine. It then sends the recipe to the cooking machine, which creates the physical dish. The finished dish is delivered to the user via a delivery vehicle, and the user again provides feedback using the app. This feedback is collected by the server and used to retrain the generative AI model.

[1466] The key hardware and software used throughout the process include smartphones, servers, generative AI models, emotion engines, food printers, delivery drones and delivery people.

[1467] This allows for the provision of high-quality food that takes into account not only the user's preferences and conditions, but also their emotional state.

[1468] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1469] Step 1:

[1470] The user enters preferences and requirements.

[1471] Input: The user enters their favorite ingredients, disliked ingredients, allergy information, calorie restrictions, and current emotional state into the smartphone app.

[1472] How it works: An application on a user's device provides specialized input fields, checkboxes, and selection menus.

[1473] Output: User-entered preferences and conditions data.

[1474] Step 2:

[1475] Send and temporarily save input data.

[1476] Input: Data entered by the user through the application.

[1477] Operation: The user terminal temporarily stores this data and sends it to the server.

[1478] Output: User preferences and requirements data transferred to the server.

[1479] Step 3:

[1480] Recipe generation using generative AI models.

[1481] Input: User preferences and requirements data stored on the server.

[1482] How it works: The server invokes a generative AI model to generate the optimal recipe based on the user's preferences and conditions.

[1483] Output: The generated recipe data.

[1484] Step 4:

[1485] Acquiring emotion data.

[1486] Input: Data about the emotional state submitted by the user.

[1487] How it works: The server uses an emotion engine to analyze the user's emotional state, which may involve facial recognition, speech analysis, or text analysis.

[1488] Output: Emotion data from the emotion engine.

[1489] Step 5:

[1490] Reflecting emotional data.

[1491] Input: Generated recipe data and sentiment data.

[1492] How it works: The server applies the emotional data to the generative AI model and re-optimizes the recipe.

[1493] Output: Recipe data optimized for emotional states.

[1494] Step 6:

[1495] Cooking food using a cooking machine.

[1496] Input: Optimized recipe data.

[1497] Operation: The server sends the optimized recipe data to the cooking machine (food printer), which then automatically mixes the specified ingredients and prepares the dish according to the recipe.

[1498] Output: The finished physical dish.

[1499] Step 7:

[1500] Arrange delivery.

[1501] Input: The finished dish and the user's address information.

[1502] How it works: The server sends the completed meal and address information to a delivery vehicle (delivery person or drone) to arrange for delivery.

[1503] Output: The meal delivered to the user's address.

[1504] Step 8:

[1505] Get feedback.

[1506] Input: User's ratings and opinions about the food and service provided.

[1507] How it works: The user enters feedback through a smartphone app, which then sends this feedback to the server.

[1508] Output: User feedback data stored on the server.

[1509] Step 9:

[1510] Retraining generative AI models.

[1511] Input: Feedback data and emotion data.

[1512] How it works: The server retrains the generative AI model based on the collected feedback and emotion data, improving the accuracy of future recipe generation.

[1513] Output: An improved generative AI model.

[1514] The above is the specific processing flow of this system.

[1515] 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.

[1516] 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.

[1517] 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.

[1518] 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.

[1519] 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.

[1520] 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.

[1521] 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).

[1522] 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.

[1523] 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."

[1524] 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.

[1525] 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).

[1526] 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.

[1527] 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.

[1528] 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.

[1529] 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.

[1530] 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.

[1531] 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.

[1532] 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.

[1533] 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.

[1534] 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, in order to avoid confusion and to 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.

[1535] 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.

[1536] The following is further disclosed regarding the above embodiment.

[1537] (Claim 1)

[1538] means for providing an interface for a user to input preferences and requirements;

[1539] a means for using a generative AI model to output a recipe generated based on the user's input;

[1540] a means for operating a food printer that prints physical dishes based on the recipes generated by the generative AI model;

[1541] means for delivering the physical meal to a user;

[1542] means for collecting feedback provided by the user and improving the generative AI model;

[1543] A system including:

[1544] (Claim 2)

[1545] 10. The system of claim 1, further comprising means for temporarily storing user-entered preferences and conditions.

[1546] (Claim 3)

[1547] The system of claim 1 , further comprising: means for invoking the generative AI model to generate a recipe.

[1548] "Example 1"

[1549] (Claim 1)

[1550] means for providing an interface for a user to input preferences and requirements;

[1551] a means for using a generative AI model to output a generated recipe based on the user's input;

[1552] a means for operating a food printer that generates physical food products based on recipes generated by the generative AI model;

[1553] means for delivering the physical food to a user;

[1554] means for collecting feedback provided by the user and improving the generative AI model;

[1555] means for temporarily storing preferences and conditions entered by said user;

[1556] A means for calling the generative AI model to generate a recipe;

[1557] means for generating a prompt sentence for inputting user information into the generative AI model;

[1558] A system including:

[1559] (Claim 2)

[1560] 10. The system of claim 1, further comprising: means for analyzing a recipe provided by the generative AI model, automatically combining specified ingredients, and generating a dish according to specified cooking instructions.

[1561] (Claim 3)

[1562] The system of claim 1, further comprising means for retraining the generative AI model using the feedback and reflecting the feedback in subsequent recipe generation.

[1563] "Application Example 1"

[1564] (Claim 1)

[1565] means for providing an interface for a user to input preferences and requirements;

[1566] a means for using a generative AI model to output a recipe generated based on the user's input;

[1567] a means for operating a food printer that prints physical dishes based on the recipes generated by the generative AI model;

[1568] means for delivering the physical meal to a user;

[1569] means for collecting feedback provided by the user and improving the generative AI model;

[1570] means including an application for generating recipes and managing delivery based on preferences and conditions entered by the user;

[1571] A system including:

[1572] (Claim 2)

[1573] 10. The system of claim 1, further comprising means for temporarily storing user-entered preferences and conditions.

[1574] (Claim 3)

[1575] The system of claim 1, further comprising means for invoking the generative AI model to generate a recipe and controlling a food printer to create a physical dish based on the generated recipe.

[1576] "Example 2: Combining Emotion Engines"

[1577] (Claim 1)

[1578] means for providing an interface for a user to input preferences and requirements;

[1579] a means for using a generative AI model to output a recipe generated based on the user's input;

[1580] a means for operating a food printer that prints physical dishes based on the recipes generated by the generative AI model;

[1581] means for calling an emotion engine for reflecting user emotion data on the recipe generated by the generative AI model;

[1582] means for delivering the physical meal to a user;

[1583] means for collecting feedback provided by the user and improving the generative AI model;

[1584] A system including:

[1585] (Claim 2)

[1586] 10. The system of claim 1, further comprising means for temporarily storing user-entered preferences and conditions.

[1587] (Claim 3)

[1588] The system of claim 1 , further comprising: means for invoking the generative AI model to generate a recipe.

[1589] "Application example 2 when combining emotion engines"

[1590] (Claim 1)

[1591] means for providing an interface for a user to input preferences and requirements;

[1592] a means for using a generative AI model to output a recipe generated based on the user's input;

[1593] means for using an emotion engine to recognize the emotional state of the user;

[1594] A means for reflecting emotion data obtained from the emotion engine in the generative AI model;

[1595] a means for operating a cooking machine that prints physical dishes based on the recipes generated by the generative AI model;

[1596] a delivery means for delivering the physical meal to a user;

[1597] means for collecting feedback provided by the user and improving the generative AI model;

[1598] A system including:

[1599] (Claim 2)

[1600] 10. The system of claim 1, further comprising means for temporarily storing user-entered preferences and conditions.

[1601] (Claim 3)

[1602] The system of claim 1 , further comprising: means for invoking the generative AI model to generate a recipe. [Explanation of symbols]

[1603] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for providing an interface for a user to input preferences and requirements; a means for using a generative AI model to output a recipe generated based on the user's input; a means for operating a food printer that prints physical dishes based on the recipes generated by the generative AI model; means for delivering the physical meal to a user; means for collecting feedback provided by the user and improving the generative AI model; A system including:

2. 10. The system of claim 1, further comprising means for temporarily storing user-entered preferences and conditions.

3. The system of claim 1 , further comprising means for invoking the generative AI model to generate a recipe.

Images