system

Abstract

Provide a system. A means for a user to select conditions, input and register purchased ingredients and their quantities; means for receiving the input data and searching a database for recipes that meet the conditions; means for displaying the searched recipes as recommendations to the user; a means for saving a recipe selected by a user from the displayed recipes and learning the user's preferences; A means for reflecting the learned user preferences in the selection of recommended recipes from the next time onwards; A system including:

Description

[Technical Field]

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

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

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

[0004] There is a demand for a system that allows users to efficiently find recipes that suit their conditions and preferences, and that can also learn those preferences and reflect them in future recipe suggestions. Conventional recipe search systems require users to search through a large number of recipes to find one that suits them, making it particularly difficult to find recipes that meet specific conditions, such as baby food or nursing care food. Furthermore, there are few systems that can learn user preferences and reflect them in future suggestions, making it difficult to improve the user experience. [Means for solving the problem]

[0005] The present invention comprises: a means for a user to select conditions, input and register purchased ingredients and their quantities;

[0006] means for receiving the input data and searching a database for recipes that meet the conditions;

[0007] means for displaying the searched recipes as recommendations to the user;

[0008] a means for saving a recipe selected by a user from the displayed recipes and learning the user's preferences;

[0009] A means for reflecting the learned user preferences in the selection of recommended recipes from the next time onwards;

[0010] The system solves the above-mentioned problems. This allows users to easily find recipes that suit their requirements and preferences, and the accuracy of the suggested recipes improves with each use. Furthermore, by adding a means to display an interface to confirm the user's input and a means to store a database of purchased ingredients, a more convenient and user-friendly recipe suggestion system can be realized.

[0011] A "user" is an individual or organization that uses the system to search for and save recipes.

[0012] "Conditions" refer to specific requirements or restrictions such as baby food or nursing care food, and are information specified by the user as criteria for selecting a recipe.

[0013] "Purchased ingredients" refers to the food and the amount of food prepared by the user for cooking.

[0014] "Input" refers to the act of the user providing information about conditions and ingredients to the system.

[0015] The term "means" refers to a specific component of a method or apparatus used by the present invention to achieve a specific function.

[0016] A "database" is an information management system that stores recipes, ingredient information, and other information in an organized manner, and allows searching and updating as needed.

[0017] "Searching" is the act of extracting information from a database based on specific criteria.

[0018] "Recommendations" refers to recipe suggestions selected to match the user's conditions and preferences, and are presented in a way that makes it easy for the user to make a selection.

[0019] "Display" refers to the act of providing information to a user through the screen of a terminal.

[0020] "Selection" is the act of a user choosing the most appropriate option from among multiple options presented.

[0021] "Saving" is the act of recording the user's selected information in a database so that it can be used later.

[0022] "Learning" refers to the process by which a system uses technologies such as machine learning to analyze users' behavioral patterns and preferences, and then stores and utilizes that information.

[0023] An "interface" is a visual or operational means, such as an operation screen or input form, that allows a user to interact with a system.

[0024] "Reflection" is the act of using previously acquired data and knowledge in a concrete way to make new proposals or take action. [Brief explanation of the drawings]

[0025] [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 illustrating 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

[0026] 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.

[0027] First, the terms used in the following description will be explained.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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."

[0033] [First embodiment]

[0034] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0035] 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.

[0036] 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).

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0042] 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.

[0043] 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.

[0044] 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.

[0045] 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."

[0046] The present invention is a system that allows a user to efficiently find recipes that suit their own conditions and preferences, and reflects this in future recipe suggestions.

[0047] Program processing

[0048] 1. Select conditions and register ingredients

[0049] Terminal: The user launches applications and web services.

[0050] Device: A UI for selecting conditions is displayed on the screen. The user selects conditions such as baby food or nursing care food.

[0051] User: Selects conditions and enters purchased ingredients and their quantities.

[0052] For example, select "baby food" and enter "300g carrots" and "200g chicken."

[0053] Terminal: A screen to confirm the input information is displayed, and the user clicks the confirmation button.

[0054] Terminal: The entered data is sent to the server.

[0055] The transmitted information includes the user ID, selection criteria, ingredients and their quantities.

[0056] 2. Creating and displaying recipes

[0057] Server: Receives the user's input data.

[0058] Server: Searches the database for recipes that match the criteria.

[0059] For example, search for baby food recipes that use carrots and chicken.

[0060] Server: Select several recommended recipes from the search results.

[0061] For example: "Carrot and chicken puree", "Chicken and carrot stew", etc.

[0062] Server: Sends the selected recipe data to the terminal.

[0063] Device: Recommended recipes are displayed to the user.

[0064] 3. Select a recipe and view details

[0065] User: Select any recipe from the recommended recipes presented.

[0066] For example, select "Carrot and Chicken Puree."

[0067] On your device: Displays detailed information about the selected recipe, including specific ingredients, instructions, cooking time, etc.

[0068] 4. Learning User Preferences

[0069] Server: Stores the data of the recipe selected by the user.

[0070] The information saved is the user ID and the selected recipe ID.

[0071] Server: Applies algorithms to learn user preferences.

[0072] This allows the user's behavioral patterns and preferences to be analyzed.

[0073] Server: Updates the system to reflect the learning results in future recipe suggestions.

[0074] Specific examples

[0075] For example, suppose User A launches an application to make baby food, selects "baby food," and then enters "300g of carrots" and "200g of chicken." In this case, the server searches the database for baby food recipes that use "carrots" and "chicken," and generates recommended recipes such as "carrot and chicken puree" and "chicken and carrot stew." When the user selects "carrot and chicken puree," details of that recipe are displayed on the device. At the same time, the server saves the user's selection history and reflects it in the next recipe suggestion. This ensures that recipes that suit the user's preferences are provided each time the application is used.

[0076] The processing flow will be explained below.

[0077] Step 1:

[0078] Terminal: The user launches applications and web services.

[0079] Device: A UI for selecting conditions is displayed on the screen. The user is presented with options such as "baby food," "nursing care food," and "allergy-friendly food."

[0080] Step 2:

[0081] User: Select a condition. For example, select "baby food."

[0082] Terminal: Records the conditions (baby food) selected by the user.

[0083] Step 3:

[0084] Terminal: Displays an input form where the user can enter the ingredients and quantities purchased.

[0085] User: Enter the ingredients purchased and their quantities. For example, enter "300g carrots" and "200g chicken."

[0086] Step 4:

[0087] Terminal: A screen to confirm the input is displayed. After the user confirms the input, they click the confirmation button.

[0088] Terminal: Sends the user's input data (conditions and ingredients) to the server.

[0089] Step 5:

[0090] Server: Receives user input data, including the user ID, selection criteria, ingredients, and their quantities.

[0091] Server: Searches the database for recipes that match the conditions based on the received data.

[0092] Step 6:

[0093] Server: Generates a list of recipes that match the criteria. For example, it might select "carrot and chicken puree" or "chicken and carrot stew."

[0094] Server: Sends the generated recipe list to the terminal.

[0095] Step 7:

[0096] Device: Recommended recipes received from the server are displayed to the user. Recipe names and summaries are displayed in a list.

[0097] Step 8:

[0098] User: Select your preferred recipe from the recommended recipes displayed. For example, select "Carrot and Chicken Puree."

[0099] On your device: View detailed information about the selected recipe, including specific ingredients, cooking instructions, and cooking times.

[0100] Step 9:

[0101] Server: Stores the data of the recipe selected by the user. The stored information includes the user ID and the selected recipe ID.

[0102] Server: Applies algorithms to learn user preferences, which analyzes user behavior patterns and preferences.

[0103] Step 10:

[0104] Server: Updates the system to reflect the learning results in future recipe suggestions. This will enable the system to suggest recipes that better match the user's preferences when the user uses the system again.

[0105] Example 1

[0106] 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."

[0107] Conventional recipe suggestion systems have difficulty efficiently finding recipes that match the conditions and ingredients entered by the user, and lack the functionality to provide recipes that reflect the user's preferences in future recipes. For these reasons, there is a need to improve the user experience.

[0108] 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.

[0109] In this invention, the server includes means for a user to select conditions and input and register purchased ingredients and their quantities, means for receiving the input data and searching a database for recipes that match the conditions, means for displaying the searched recipes as recommendations to the user, means for saving the recipes selected by the user and learning the user's preferences, means for reflecting the learned user preferences in the selection of recommended recipes from the next time onwards, and means for displaying a corresponding interface when the user selects conditions. This allows the user to efficiently find recipes that match their conditions and preferences, and enables the system to reflect recipe suggestions that match the user's preferences from the next time onwards.

[0110] "User" refers to a person who uses a system or application.

[0111] "Conditions" refer to recipe categories and requirements that users specify to the system, such as baby food and nursing care food.

[0112] "Ingredients" refers to raw materials purchased by users and used to create recipes, such as carrots and chicken.

[0113] "Input" refers to the act of a user providing information to a system using a device such as a keyboard or touch panel.

[0114] "Registration means" refers to a function for recording data entered by a user and saving it within the system.

[0115] "Receiving means" refers to a function that allows the server to receive data sent from the user.

[0116] "Search means" refers to a function for searching a database for information that matches the conditions based on the received data.

[0117] A "database" refers to a system that organizes and stores large amounts of information, making it searchable and accessible as needed.

[0118] "Recommendation display means" refers to a function for suggesting information selected from search results to users.

[0119] "Storage means" refers to a function that records information selected by the user and saves it for later use.

[0120] "Learning means" refers to a function for analyzing stored information and learning user preferences and behavioral patterns.

[0121] "Reflection means" refers to the function of improving future suggestions based on the results of learning and providing them to users.

[0122] "Interface" refers to the screen and input devices that allow a user to interact with a system.

[0123] The present invention provides a system that allows a user to efficiently find recipes that suit their own conditions and preferences, and reflects these in future recipe suggestions. An embodiment of this system will be described in detail below.

[0124] When a user launches the smartphone application or web browser service, an initial screen appears. Here, the user can access the interface (UI) for setting the conditions for recipe suggestions. The UI provides options such as baby food and nursing care food.

[0125] When the user selects the conditions, an interface for inputting ingredients and their quantities is displayed on the screen. For example, the user can select "baby food" and input "300g of carrots" and "200g of chicken." This input data is displayed once on the confirmation screen on the device, and is sent to the server when the user clicks the confirm button.

[0126] The server receives the user's input data (user ID, selection criteria, ingredients and their quantities) and searches the database for recipes that match the criteria. Specifically, it searches for recipes that meet the criteria, for example, "baby food," "carrots," and "chicken." The server selects a recommended recipe from multiple matching recipes and sends that data to the device.

[0127] The device displays the recommended recipes received from the server on the user's screen. The user can select any recipe from the recommended recipes presented. For example, the user can select "carrot and chicken puree." Detailed information about the selected recipe (specific ingredients, cooking method, cooking time, etc.) is displayed on the device.

[0128] The data of the recipe selected by the user (user ID and selected recipe ID) is stored on the server. The server applies a machine learning algorithm to learn the user's preferences based on this data, analyzing the user's behavioral patterns and tastes. The learning results are updated in the system so that they are reflected in future recipe suggestions.

[0129] For example, if User A starts the application, selects "baby food," and enters "300g of carrots" and "200g of chicken," the server will search the database for baby food recipes that use "carrots" and "chicken," and recommend "carrot and chicken puree" or "chicken and carrot stew." If the user selects "carrot and chicken puree," its details are displayed. At the same time, the server records this selection and reflects it in the next recipe suggestion.

[0130] An example of a prompt sentence for the generative AI model is written as follows:

[0131] "I'd like to know what ingredients I have and what recipes I can use them in. For example, can you suggest a recipe that uses 300g of carrots and 200g of chicken?"

[0132] This system improves the user experience and provides the most suitable cooking method for each individual user by suggesting recipes that match the user's preferences. This process is carried out through cooperation between the server, terminals, and users.

[0133] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0134] Step 1:

[0135] The user launches an application or web service and the condition selection screen is displayed. The user selects conditions such as "baby food" or "care food." This input is used as initial condition data for the system to suggest appropriate recipes. The input data is the condition type, and the output is the display of the condition selection screen.

[0136] Step 2:

[0137] Based on the conditions selected by the user, a screen for inputting ingredients and their quantities is displayed on the terminal. Here, the user can input information such as "300g carrots" and "200g chicken." This input is used as additional condition data for recipe search. The input data is the names of ingredients and their quantities, and the output is the display of a confirmation screen.

[0138] Step 3:

[0139] The terminal sends the entered data to the server. When the user clicks the "Confirm" button on the confirmation screen, the user ID, selection criteria, ingredients, and their quantities are sent to the server. The input data is what the user entered when clicking the confirm button, and the output is the data sent to the server.

[0140] Step 4:

[0141] The server searches the database based on the data it receives. The server finds recipes that match the criteria "baby food," "carrots," and "chicken." The search algorithm selects the recipe that best fits the criteria specified by the user. The input data is the user's criteria and ingredient information sent, and the output is a list of matching recipes.

[0142] Step 5:

[0143] The server selects recommended recipes from the search results and sends the data to the device. In this case, recipes such as "carrot and chicken puree" and "chicken and carrot stew" are selected. The input data is the list of search results, and the output is the data sent to the user's device.

[0144] Step 6:

[0145] The device receives the data from the server and displays recommended recipes to the user. The user can select any recipe from the recipes presented on the screen. The input data is the recipe data received from the server, and the output is the recipe display to the user.

[0146] Step 7:

[0147] The user selects any recipe from the presented recipes. For example, if the user selects "carrot and chicken puree," detailed information about the recipe is displayed. The user's selection action is the input data, and the output is the display of detailed recipe information.

[0148] Step 8:

[0149] The server stores the user's selected recipe data. The user ID and selected recipe ID are recorded, and this data is used in an algorithm to learn the user's preferences. The input data is the user's selected action and the recipe ID, and the output is the storage of the selected data.

[0150] Step 9:

[0151] The server applies a machine learning algorithm to learn user preferences based on the stored data. The learning results are reflected in the selection of recommended recipes from the next time onwards, enabling the system to suggest recipes that are best suited to the user. The input data is the stored selection data, and the output is an updated recipe suggestion algorithm.

[0152] Through these steps, users can efficiently find recipes that suit their requirements and preferences, and the system can continue to improve its suggestions for future recipes.

[0153] (Application example 1)

[0154] 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."

[0155] Conventional recipe suggestion systems can suggest appropriate recipes based on a user's conditions and preferences, but they do not support ingredient delivery, which means users have to go through the trouble of obtaining the ingredients. Furthermore, while they have a mechanism for learning user preferences to reflect the results of that learning in selecting recommended recipes for the next time and beyond, they are unable to utilize this information in actual purchasing behavior or inventory management. The present invention aims to solve these problems and improve user convenience by enabling users to efficiently find recipes that meet their requirements and manage the delivery of those ingredients all in one place.

[0156] 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.

[0157] In this invention, the server includes means for allowing a user to select conditions and input and register the ingredients and their quantities to be purchased, means for receiving the input data and searching a database for recipes that match the conditions, means for displaying the searched recipes as recommendations to the user, means for saving a recipe selected by the user from the displayed recipes and learning the user's preferences, means for reflecting the learned user preferences in the selection of recommended recipes from the next time onwards, means for generating a list of necessary ingredients and ordering the ingredients, and means for managing the delivery of the ingredients. This allows a user to easily select a recipe that meets the conditions and order the ingredients for delivery all at once.

[0158] "Conditions" refer to specific requirements or constraints that a user specifies when receiving recipe suggestions.

[0159] "Ingredients" refers to the raw materials needed to create a dish or recipe.

[0160] "Quantity" refers to numerical information that indicates the specific quantity or weight of ingredients.

[0161] "Database" refers to a collection of information for efficiently managing, searching, and updating structured data.

[0162] A "recipe" refers to a document or data that contains instructions and a list of ingredients for creating a dish.

[0163] "Recommended" indicates candidates that are particularly recommended to the user based on specific conditions.

[0164] "Preferences" refer to the preferences or biases selected by a user based on specific conditions or criteria.

[0165] "Learning" refers to the process of analyzing and analysing a user's past behaviour and choices and reflecting this in future suggestions.

[0166] "Ingredient list" refers to a list of the names and amounts of ingredients required based on a recipe.

[0167] "Ordering" refers to the act of requesting the necessary ingredients from a specific delivery service.

[0168] "Delivery" refers to the service of delivering ordered ingredients to a specified location.

[0169] "Means" refers to a method or device used to achieve a particular purpose.

[0170] The present invention provides a system that enables a user to efficiently find a recipe that meets their own conditions and preferences, and to order delivery of the ingredients they need based on that recipe.

[0171] First, the user launches the application on a device such as a smartphone, smart glasses, or head-mounted display, and then uses the interface displayed on the screen to input specific conditions (e.g., baby food, vegetarian food), the ingredients purchased, and their quantities. The input data is then stored in a cloud database (e.g., Firebase) in real time.

[0172] The data recorded in the cloud database is sent to a server. The server receives the user's input data and searches the database for recipes that match the specified criteria. This search process uses a database management system and a recipe search API. For example, a search can be made for recipes in "baby food" that use "300g of carrots" and "200g of chicken."

[0173] From the search results, a generative AI model (e.g., TENSORFLOW®) is used to select the recipe that best suits the user's criteria. The selected recipe is sent to the user's device and displayed as a recommendation on the screen.

[0174] When a user selects a recipe from the recommended recipes, detailed information about that recipe (ingredients, cooking method, cooking time, etc.) is displayed. The information about the selected recipe is saved on the server and accumulated as user preference data. Based on this preference data, a machine learning algorithm (e.g., PyTorch) is used to learn the user's preference patterns and reflect them in future recipe suggestions.

[0175] Next, a list of ingredients is generated based on the selected recipe, and an order for delivery of the ingredients is placed using an API corresponding to the delivery service (e.g., Uber Eats, DoorDash, etc.) The generation of the ingredient list and the transmission of the delivery order are carried out on the server side, and the order is transmitted to the corresponding delivery company.

[0176] For example:

[0177] For example, if a user starts an application to make baby food, selects "baby food," and then enters "300g of carrots" and "200g of chicken," the server will search the database for baby food recipes that use "carrots" and "chicken," and generate recommended recipes such as "carrot and chicken puree" and "chicken and carrot stew." When the user selects "carrot and chicken puree," details of that recipe are displayed on the device. At the same time, the server saves the user's selection history and reflects it in the next recipe suggestion.

[0178] An example prompt would be:

[0179] "User selects baby food and enters 300g of carrots and 200g of chicken."

[0180] In this way, the present invention provides consistent support from the process of users finding a recipe that meets their requirements to purchasing and delivering the necessary ingredients, thereby greatly improving user convenience.

[0181] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0182] Step 1:

[0183] The user launches the application on their device and the condition selection interface is displayed. The user enters the conditions, ingredients, and their quantities, and sends this data to the device. The entered data is saved in real time to a cloud database (Firebase). This registers the user-specified conditions and ingredient information in the database.

[0184] Input: Condition (e.g., baby food), ingredients (e.g., 300g carrots, 200g chicken)

[0185] Output: Data stored in a cloud database

[0186] Specific behavior:

[0187] The user enters "Condition: Baby food," "Ingredients: 300g carrots," and "Ingredients: 200g chicken," and clicks the "Save" button.

[0188] Step 2:

[0189] The device sends the input data to the server. The server receives this data and searches the database for recipes that meet the criteria. This search uses a recipe search API or database management system. As a result, the server extracts and selects multiple recipes that meet the criteria.

[0190] Input: User data retrieved from a cloud database

[0191] Output: A list of recipes that match the criteria

[0192] Specific behavior:

[0193] The server searches for recipe data containing "baby food," "carrots," and "chicken," and extracts candidates such as "carrot and chicken puree" and "chicken and carrot stew."

[0194] Step 3:

[0195] The server uses a generative AI model (TensorFlow) to select the recipe that best suits the user's requirements. The selected recipe data is sent to the device and displayed as a recommendation on the user's screen.

[0196] Input: Multiple recipes that meet the criteria

[0197] Output: One or more recommended recipes

[0198] Specific behavior:

[0199] The server evaluates recipes using the generative AI model and sends the best candidates as "recommendations" to the device, which then displays "Recommended Recipe: Carrot and Chicken Puree."

[0200] Step 4:

[0201] The user selects any recipe from the recommended recipes and the details of that recipe (ingredients, cooking method, cooking time, etc.) are displayed. The selected recipe information is sent to the server and saved as the user's preference data.

[0202] Input: User selected recipe

[0203] Output: Display details of selected recipe, save preference data to server

[0204] Specific behavior:

[0205] When the user selects "Carrot and Chicken Puree," its detailed information is displayed on the screen. At the same time, the "User ID" and "Recipe ID" are saved on the server.

[0206] Step 5:

[0207] The server uses a machine learning algorithm (PyTorch) to learn the user's preference patterns and reflect them in future recipe suggestions. This learning process improves the accuracy of recipe suggestions based on the user's preferences.

[0208] Input: User preference data

[0209] Output: Updated user preference data pattern

[0210] Specific behavior:

[0211] The server analyzes the recipes the user has previously selected to reflect this in the next recipe suggestions.

[0212] Step 6:

[0213] The server generates a list of ingredients based on the selected recipe and sends the order to the partner delivery service API.

[0214] Input: A list of ingredients for the selected recipe

[0215] Output: Delivery order sent

[0216] Specific behavior:

[0217] The server generates an ingredient list of "300g of carrots" and "200g of chicken" and sends it to the delivery service API.

[0218] Step 7:

[0219] The delivery company receives the list of ingredients, prepares them, and delivers them to the specified address. The user can then pick up the ordered ingredients and create the dish according to the recipe.

[0220] Input: Delivery Order

[0221] Output: Food delivery to the specified address

[0222] Specific behavior:

[0223] The delivery company prepares the order and delivers 300g of carrots and 200g of chicken to the user's address.

[0224] 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.

[0225] The present invention is a system that allows users to efficiently find recipes that suit their own conditions and preferences, and further learns their preferences and feelings and reflects them in future recipe suggestions.

[0226] Program processing

[0227] 1. Select conditions and register ingredients

[0228] Terminal: The user launches applications and web services.

[0229] Device: A UI for selecting conditions is displayed on the screen. The user is presented with options such as "baby food," "nursing care food," and "allergy-friendly food."

[0230] User: Select a condition. For example, select "baby food."

[0231] Terminal: Records the conditions (baby food) selected by the user.

[0232] 2. Enter ingredients and emotions

[0233] Terminal: Displays an input form that allows the user to input the ingredients purchased and the amount, and also displays an interface for inputting or measuring the user's emotions.

[0234] User: Enter the ingredients purchased, their quantities, and their current emotions. For example, they can enter "300g of carrots," "200g of chicken," and "satisfied."

[0235] Terminal: A screen to confirm the input information is displayed, and the user clicks the confirmation button.

[0236] Terminal: Sends the user's input data (conditions, ingredients, emotions) to the server.

[0237] 3. Creating and displaying recipes

[0238] Server: Receives user input data, including the user ID, selection criteria, ingredients and their amounts, and emotions.

[0239] Server: Searches for recipes that match the criteria from the database based on the received data and past data. It also uses an emotion engine to select recipes that correspond to the user's emotions.

[0240] Server: Generates a list of recipes that match the criteria and are emotionally appropriate. For example, it might select "carrot and chicken puree" or "chicken and carrot stew."

[0241] Server: Sends the generated recipe list to the terminal.

[0242] Device: Recommended recipes are displayed to the user.

[0243] 4. Select a recipe and view details

[0244] User: Select a recipe from the suggested recipes. For example, select "Carrot and Chicken Puree."

[0245] On your device: View detailed information about the selected recipe, including specific ingredients, cooking instructions, and cooking times.

[0246] 5. Learning user preferences and emotions

[0247] Server: Stores the recipe data selected by the user and the emotion data at that time. The stored information includes the user ID, the selected recipe ID, and the emotion data.

[0248] Server: Applies algorithms to learn user preferences and emotions, which analyzes user behavior patterns, preferences, and emotions.

[0249] Server: Updates the system to reflect the learning results in future recipe suggestions. This ensures that when the user uses the system again, it will suggest recipes that better match their preferences and emotions.

[0250] Specific examples

[0251] For example, suppose User A launches an application to make baby food, selects "baby food," and then enters "300g carrots," "200g chicken," and "satisfied." In this case, the server searches the database for baby food recipes that use "carrots" and "chicken," and selects a recipe that matches the user's emotion of "satisfied." It generates recommended recipes such as "carrot and chicken puree" and "chicken and carrot stew" and sends them to the device. When the user selects "carrot and chicken puree," details of that recipe are displayed on the device. At the same time, the server saves the user's selection history and emotion data and reflects them in the next recipe suggestions. This ensures that recipes that match the user's preferences and emotions are provided each time the application is used.

[0252] The processing flow will be explained below.

[0253] Step 1:

[0254] Terminal: The user launches applications and web services.

[0255] Terminal: A UI for selecting conditions is displayed on the screen, and the user is presented with options such as "baby food," "nursing care food," and "allergy-friendly food."

[0256] Step 2:

[0257] User: Select a condition. For example, select "baby food."

[0258] Terminal: Records the conditions (baby food) selected by the user.

[0259] Step 3:

[0260] Terminal: Displays the screen for inputting ingredients and emotions. An interface is provided for the user to input the ingredients purchased, their quantities, and their current emotions.

[0261] User: Enter the ingredients purchased, their quantities, and their current emotions. For example, enter "300g of carrots," "200g of chicken," and "Satisfied."

[0262] Step 4:

[0263] Terminal: A screen to confirm the input information is displayed, and the user clicks the confirmation button.

[0264] Terminal: Sends the user's input data (conditions, ingredients, emotions) to the server.

[0265] Step 5:

[0266] Server: Receives the user's input data, including the user ID, selection criteria, ingredients, and emotions.

[0267] Step 6:

[0268] Server: Based on the input data and past data, the server searches the database for recipes that match the conditions, and uses an emotion engine to select a recipe that suits the user's emotions.

[0269] For example, if a user enters "satisfied," recipes chosen with similar emotions or highly rated recipes will be prioritized.

[0270] Step 7:

[0271] Server: Generates a list of recommended recipes that match the conditions and emotions.

[0272] For example, select "carrot and chicken puree" or "chicken and carrot stew."

[0273] Server: Sends the generated recipe list to the terminal.

[0274] Step 8:

[0275] Device: Recommended recipes received from the server are displayed to the user. Recipe names and summaries are displayed in a list.

[0276] Step 9:

[0277] User: Select your preferred recipe from the recommended recipes displayed.

[0278] For example, select "Carrot and Chicken Puree."

[0279] On your device: Detailed information about the selected recipe will be displayed, including specific ingredients, cooking instructions, and cooking time.

[0280] Step 10:

[0281] Server: Stores the data of the recipe selected by the user and the emotion data at that time.

[0282] The information stored includes the user ID, the selected recipe ID, and emotion data.

[0283] Step 11:

[0284] Server: Applies algorithms to learn user preferences and emotions.

[0285] User behavior patterns, preferences, and emotions are analyzed.

[0286] Step 12:

[0287] Server: Updates the system to reflect the learning results in future recipe suggestions.

[0288] This means that when a user uses the system again, recipes that better match their preferences and emotions will be suggested.

[0289] Example 2

[0290] 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."

[0291] Conventional recipe suggestion systems were able to provide recipes that matched the user's conditions and ingredients, but it was difficult to learn the user's emotions and preferences and reflect them in future suggestions. Furthermore, because they were unable to take into account the ingredients purchased by the user or their emotions, the accuracy of suggesting the optimal recipe for the user was low. This led to users being dissatisfied with the recipe selection, resulting in a decrease in the frequency of system use.

[0292] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0293] In this invention, the server includes means for allowing a user to select conditions and input and register purchased ingredients and their quantities, means for receiving the input data and searching a database for recipes that match the conditions, means for using an emotion engine to select a recipe according to emotions based on the received data and past data, means for displaying the searched recipes as recommendations to the user, means for saving a recipe selected by the user from the displayed recipes and learning the user's preferences and emotions, and means for reflecting the learned user preferences and emotions in the selection of recommended recipes from the next time onwards. This makes it possible to propose optimal recipes based on the user's conditions, ingredients, and emotions.

[0294] "Conditions" are user-selected constraints or requirements, including, for example, types of food and health restrictions.

[0295] "Ingredients" refer to the foods and ingredients used in a dish or recipe, and specifically include vegetables, meat, seasonings, etc.

[0296] "Quantity" is a numerical value indicating the quantity or weight of a material that the user has purchased or possesses.

[0297] A "database" is a collection of information that structures and stores user conditions, ingredients, and recipe information.

[0298] "Search" is the operation of searching a database for information that matches specified conditions.

[0299] A "prescription" is information that indicates a recipe or cooking method for a dish.

[0300] "Emotion" indicates the user's current psychological state, and is information such as "satisfied" or "dissatisfied," for example.

[0301] An "emotion engine" is an algorithm or system that selects the optimal prescription based on the user's emotions.

[0302] "Display" refers to the operation of visually showing prescription information and recommended recipes on the user's device.

[0303] "Preferences" indicate a user's tendency to prefer particular recipes or ingredients.

[0304] "Learning" is an information analysis process that uses user preferences and emotional data to reflect in future recipe suggestions.

[0305] A "system" is a set of mechanisms that combine multiple means and technologies to provide services to users.

[0306] MODE FOR CARRYING OUT THE INVENTION

[0307] This invention is a system that allows users to efficiently find recipes that suit their own conditions and preferences, and also learns their preferences and feelings and reflects them in future recipe suggestions.

[0308] System Overview

[0309] This system includes means for a user to select conditions and input and register purchased materials and their quantities, means for receiving the input data and searching a database for recipes that match the conditions, means for using an emotion engine to select a recipe according to emotions based on the received data and past data, means for displaying the searched recipes as recommendations to the user, means for saving a recipe selected by the user from the displayed recipes and learning the user's preferences and emotions, and means for reflecting the learned user preferences and emotions in the selection of recommended recipes from the next time onwards.

[0310] Hardware and Software Configuration

[0311] 1. Terminal: A device used by a user to access an application or web service, including a smartphone, tablet, or PC.

[0312] 2. Server: This is the central system that receives and processes input data from users. It includes a database server, machine learning engine, and emotion engine.

[0313] 3. Software:

[0314] User interface: A UI on an application or web browser that provides an interface for selecting conditions and inputting materials.

[0315] Database system: A database (e.g., SQL database) for storing and managing entered user and prescription data.

[0316] Emotion engine: An algorithm for analyzing user emotions and suggesting appropriate prescriptions based on them.

[0317] Machine learning algorithms: Recommendation systems that learn user preferences and history and reflect this in future recommendations.

[0318] Specific examples

[0319] For example, suppose User A launches the application, selects "baby food," and then enters "300g carrots," "200g chicken," and "satisfied." In this case, the server searches the database for baby food recipes that use "carrots" and "chicken," and selects a recipe that corresponds to the user's emotion of "satisfied." As a result, recommended recipes such as "carrot and chicken puree" and "chicken and carrot stew" are generated and sent to the device. When the user selects "carrot and chicken puree," details of the selection are displayed on the device. At the same time, the server saves the user's selection history and emotion data, and can reflect this in the next recipe suggestions. This allows the server to provide recipes that match the user's preferences and emotions each time the application is used.

[0320] Prompt Sentence Examples

[0321] By inputting the following prompt sentence into the generative AI model, a description of the above system can be generated in natural language.

[0322] "Users input conditions, ingredients, and emotions through an application or web service, and the AI ​​model uses a database and emotion engine to generate natural-sounding sentences that explain the system and suggest prescriptions that match the conditions and are appropriate for the emotions."

[0323] The prompts enable the generative AI model to generate detailed natural language descriptions of the system's functions and procedures.

[0324] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0325] Step 1:

[0326] Terminal: When a user launches an application or web service, the home screen appears.

[0327] Input: Application launch by user action

[0328] Output: Display of the home screen of the application or web service

[0329] Specific actions: Tap an icon on your smartphone to launch an app, or enter a URL in a web browser.

[0330] Step 2:

[0331] Terminal: A user interface (UI) for selecting conditions is displayed on the screen. The user is presented with options such as "baby food," "nursing care food," and "allergy-friendly food."

[0332] Input: The application initialization process calls the criteria selection UI

[0333] Output: Display of a screen where the user can select conditions

[0334] Specific operation: A screen will appear where you can select conditions using a drop-down menu or radio buttons.

[0335] Step 3:

[0336] User: Select a condition and click the Next button. For example, select "baby food."

[0337] Input: User selection of conditions

[0338] Output: Record of selected conditions and transition to the next input screen

[0339] Specific actions: Select with a mouse click or touch gesture and press the "Next" button.

[0340] Step 4:

[0341] Terminal: Displays a form that allows the user to input the ingredients and their quantities purchased, and also displays an interface for inputting or measuring the user's emotions.

[0342] Input: System response to condition selection

[0343] Output: Display of material and emotion input form

[0344] Specific operation: A section for entering ingredients and their quantities using text boxes or voice input, as well as a slider or button for entering emotions, will be displayed.

[0345] Step 5:

[0346] User: Enter the ingredients purchased (e.g., "300g carrots" and "200g chicken") and their current feelings (e.g., "Satisfied").

[0347] Input: User input of materials and emotions

[0348] Output: Display of input confirmation screen

[0349] Specific actions: Enter text or use voice recognition to enter material information, then drag the emotion slider to the appropriate value.

[0350] Step 6:

[0351] Terminal: A screen is displayed to confirm the input and the user is asked to click a confirmation button.

[0352] Input: Material and emotional input data

[0353] Output: Display confirmation screen

[0354] Specific operation: Displays the input data and displays a button to ask the user for confirmation.

[0355] Step 7:

[0356] User: Click the Verify button to verify that the data is correct.

[0357] Input: User clicks confirmation button

[0358] Output: Confirmed data transmission process

[0359] Specific operation: Press the confirmation button to confirm the input.

[0360] Step 8:

[0361] Terminal: Sends the user's input data (conditions, materials, emotions) to the server.

[0362] Input: Confirmed data

[0363] Output: Send data to the server

[0364] Specific operation: Executes an API call to send data to a server over the network.

[0365] Step 9:

[0366] Server: Receives input data sent by the user, searches the database for prescriptions that match the conditions, and uses an emotion engine to select a prescription that corresponds to the user's emotion.

[0367] Input: Input data sent from the terminal

[0368] Output: A list of prescriptions that match the criteria and are emotionally appropriate

[0369] Specific operation: Executes an SQL query to extract relevant prescriptions from the database and filters them using the emotion engine.

[0370] Step 10:

[0371] Server: Generates a list of recipes that match the conditions and are emotionally appropriate. For example, it might select "carrot and chicken puree" or "stewed chicken and carrots."

[0372] Input: Searched and filtered prescription data

[0373] Output: Generate a prescription list

[0374] Specific operation: Generate a list based on the filtered prescription data.

[0375] Step 11:

[0376] Server: Sends the generated prescription list to the user's terminal.

[0377] Input: Generated prescription list

[0378] Output: Send prescription list to terminal

[0379] Specific operation: Executes an API call to send a prescription list to the terminal via the network.

[0380] Step 12:

[0381] Device: Recommended recipes are displayed to the user.

[0382] Input: Prescription list sent from the server

[0383] Output: Display recommended recipes

[0384] Specific operation: Recipes appear on the screen in a list format using a design template.

[0385] Step 13:

[0386] User: Select a recipe from the suggested recipes. For example, select "Carrot and Chicken Puree."

[0387] Input: User selection of recipe

[0388] Output: Display detailed information about the selected recipe

[0389] Action: Tap or click to select a recipe from the list.

[0390] Step 14:

[0391] On your device: View detailed information about the selected recipe, including specific ingredients, cooking instructions, and cooking times.

[0392] Input: Recipe data selected by the user

[0393] Output: Display detailed recipe information

[0394] What Happens: A detailed view of the recipe appears, showing the ingredients list and steps in a scrollable format.

[0395] Step 15:

[0396] Server: Stores the data of the recipe selected by the user and the emotion data at that time.

[0397] Input: Recipe data and emotion data selected by the user

[0398] Output: Saved user data

[0399] Specific action: It is recorded as a new record in the database.

[0400] Step 16:

[0401] Server: Applies algorithms to learn user preferences and emotions, which analyzes user behavior patterns, preferences, and emotions.

[0402] Input: Stored user preference and emotion data

[0403] Output: Training data as analysis results

[0404] Specific actions: Run machine learning algorithms (e.g., recommendation systems) to analyze data.

[0405] Step 17:

[0406] Server: Updates the system to reflect the learning results in future recipe suggestions. This ensures that when the user uses the system again, it will suggest recipes that better match their preferences and emotions.

[0407] Input: Parsed training data

[0408] Output: Proposed features of the updated system

[0409] Specific operation: The proposed algorithm is updated based on the training data.

[0410] (Application example 2)

[0411] 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."

[0412] Conventional recipe suggestion systems were able to provide recipes that took into account the user's conditions and preferences, but they were unable to suggest recipes that reflected the user's emotions. As a result, suggestions that improved the user's emotional satisfaction and experience were insufficient. Furthermore, if a user's recipe preferences differed depending on a specific emotion, this was not recorded or learned, and could not be reflected in future suggestions. Therefore, the goal of this project is to further improve user satisfaction by providing a recipe suggestion system that also takes into account the user's emotions.

[0413] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0414] In this invention, the server includes a means for a user to select conditions and input and register purchased ingredients and their quantities, a means for receiving the input data and the user's emotional data, and a means for searching a database for recipes that match the conditions, and a means for displaying the searched recipes as recommendations to the user, thereby enabling recipe suggestions based on the user's emotions in addition to their conditions and preferences.

[0415] "User" means an individual or organization that uses the system.

[0416] "Conditions" are parameters that a user sets to search for a particular recipe.

[0417] "Ingredients" refers to the types and amounts of food used to prepare a recipe.

[0418] "Emotion data" is information that indicates the user's emotional state, and is data that the system receives to use in proposing recipes.

[0419] A "database" is a structured collection of information that stores recipe information and facilitates retrieval.

[0420] The "search means" is a software function that searches the database for recipes that meet the user's requirements.

[0421] The "displaying means" is an interface for displaying the selected recipe on the user's device.

[0422] The "storage means" is a system that records the user's selected recipes and emotional data for future reference and learning.

[0423] The "learning means" is an algorithm that analyzes stored user preference and emotion data and reflects that in future suggestions.

[0424] "Server" means a central management system for receiving, processing, and storing data.

[0425] This invention is a system that allows users to input ingredients and their quantities via a smartphone application or web interface, and suggests recipes that suit their preferences and conditions. This includes a means for users to select conditions, input purchased ingredients and emotional data, and provide recipes based on those.

[0426] System configuration and usage

[0427] 1. User selection of conditions and input of ingredients

[0428] The user launches the application and selects criteria such as "baby food," "caregiver food," and "allergy-friendly food" from their smartphone or computer terminal.

[0429] After selecting these conditions, the user inputs the type and quantity of ingredients purchased, as well as emotional data (such as "satisfied" or "sad").

[0430] 2. Data Receipt and Processing by the Server

[0431] The conditions, ingredients, and emotion data entered by the user are sent to the server, which receives this data and searches a database for recipes that match the ingredients and conditions.

[0432] The server uses an emotion engine, such as a TensorFlow-based emotion analysis model, to select recipes that match the user's emotional state based on the received emotion data.

[0433] 3. Creating and displaying recipes

[0434] The searched recipes are displayed as recommendations on the user's device. Recipe information includes the ingredients needed, cooking steps, cooking time, etc.

[0435] When the user selects a recipe from the ones presented, more detailed information about that recipe is displayed.

[0436] 4. Learning and storing user preference and emotion data

[0437] The server records the recipe selected by the user and their emotional state at the time. This data is used to make future recommendations.

[0438] It applies algorithms to learn user preferences and emotional data, analyzing user behavior patterns and preferences, so that future recipe suggestions are more tailored to the user's needs and emotions.

[0439] Hardware and software used

[0440] Hardware: Servers (e.g., Amazon EC2), user devices (smartphones, PCs, etc.)

[0441] Software: Flask (a web framework written in Python), SQLite (a local database), TensorFlow (a machine learning library for sentiment analysis)

[0442] Examples and prompts

[0443] For example, suppose User A starts an application to make baby food, selects "baby food," and then inputs "300g carrots," "200g chicken," and "satisfied." In this case, the server searches the database for baby food recipes that use "carrots" and "chicken," and selects a recipe that matches the user's emotion of "satisfied." Suggested recipes include "carrot and chicken puree" and "chicken and carrot stew."

[0444] Here is an example prompt:

[0445] Let's say a user selects "baby food" as a condition, and inputs "300g carrots," "200g chicken," and the emotion "satisfied." In this case, we'll suggest the following recipes:

[0446] 1. Carrot and chicken puree

[0447] 2. Chicken and carrot stew

[0448] By inputting this prompt into a generative AI model, recipes that match the user's conditions and emotions can be efficiently generated and suggested.

[0449] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0450] Step 1:

[0451] The user launches the application and selects conditions on a smartphone or computer. Specifically, options such as "baby food," "nursing care food," and "allergy-friendly food" are displayed, and the user selects one. The input data is sent to the server in the form of condition selection.

[0452] Step 2:

[0453] Based on the selected criteria, the user inputs the ingredients purchased, their quantities, and emotional data, such as "300g of carrots," "200g of chicken," and "satisfied." This data is also sent from the device to the server.

[0454] Step 3:

[0455] The server processes the received conditions, ingredient data, and emotion data. It then searches the database for recipes that match the conditions based on the type and amount of ingredients. It also takes into account the input emotion data and uses an emotion analysis model such as TensorFlow to select recipes that suit the emotion.

[0456] Step 4:

[0457] Based on the results of the search and sentiment analysis, the system generates recipe recommendations for the user. These recipes include, for example, "carrot and chicken puree" and "chicken and carrot stew." This list is sent to the user's device as recipe information and displayed on the screen.

[0458] Step 5:

[0459] The user selects a recipe from the list of recipes presented, and detailed information about the selected recipe (ingredients, cooking steps, cooking time, etc.) is displayed.

[0460] Step 6:

[0461] The server stores the recipe selected by the user and the emotion data at that time. The saved data is recorded along with the user ID and will be used for future recipe suggestions.

[0462] Step 7:

[0463] The server analyzes the stored data and applies algorithms that learn the user's preferences and emotions, allowing it to better tailor future recipe suggestions to the user's behavioral patterns, tastes, and emotions.

[0464] Specific explanation of processing operations

[0465] Step 1:

[0466] Input data: User selection of conditions (e.g., "baby food")

[0467] Output data: Criteria selection data sent to the server

[0468] How it works: A user launches the application and selects criteria on their smartphone or computer.

[0469] Step 2:

[0470] Input data: Food ingredient data and emotion data (e.g., "300g carrots," "200g chicken," "satisfied")

[0471] Output data: Ingredient data and emotion data sent to the server

[0472] How it works: Based on the selected criteria, the user inputs the ingredients purchased, their quantities, and emotional data.

[0473] Step 3:

[0474] Input data: condition data, ingredient data, emotion data

[0475] Output data: Recipe search results and sentiment analysis results

[0476] How it works: The server processes the received data, searches the database for recipes that match the criteria, and uses a sentiment analysis model to select an appropriate recipe.

[0477] Step 4:

[0478] Input data: Recipe search results and sentiment analysis results

[0479] Output data: A list of recipes recommended for the user

[0480] Operation: The server generates recommended recipes based on the search and analysis results, sends them to the user's device, and displays them on the screen.

[0481] Step 5:

[0482] Input data: User selected recipe

[0483] Output data: Detailed information about the selected recipe

[0484] How it works: The user selects a recipe from the ones presented and its details are displayed.

[0485] Step 6:

[0486] Input data: Selected recipes and sentiment data

[0487] Output data: Selection history and emotion data stored on the server

[0488] Operation: The server stores the recipe selected by the user and the emotion data at that time.

[0489] Step 7:

[0490] Input data: saved selection history and emotion data

[0491] Output data: Recipe suggestions for the next time and beyond that reflect the user's behavioral patterns, preferences, and emotions

[0492] How it works: The server analyzes the stored data and applies algorithms that learn the user's preferences and emotions to improve future recipe suggestions.

[0493] 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.

[0494] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0495] 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.

[0496] [Second embodiment]

[0497] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0498] 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.

[0499] 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).

[0500] 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.

[0501] 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.

[0502] 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).

[0503] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0504] 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.

[0505] 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.

[0506] 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.

[0507] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0508] 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."

[0509] The present invention is a system that allows a user to efficiently find recipes that suit their own conditions and preferences, and reflects this in future recipe suggestions.

[0510] Program processing

[0511] 1. Select conditions and register ingredients

[0512] Terminal: The user launches applications and web services.

[0513] Device: A UI for selecting conditions is displayed on the screen. The user selects conditions such as baby food or nursing care food.

[0514] User: Selects conditions and enters purchased ingredients and their quantities.

[0515] For example, select "baby food" and enter "300g carrots" and "200g chicken."

[0516] Terminal: A screen to confirm the input information is displayed, and the user clicks the confirmation button.

[0517] Terminal: The entered data is sent to the server.

[0518] The transmitted information includes the user ID, selection criteria, ingredients and their quantities.

[0519] 2. Creating and displaying recipes

[0520] Server: Receives the user's input data.

[0521] Server: Searches the database for recipes that match the criteria.

[0522] For example, search for baby food recipes that use carrots and chicken.

[0523] Server: Select several recommended recipes from the search results.

[0524] For example: "Carrot and chicken puree", "Chicken and carrot stew", etc.

[0525] Server: Sends the selected recipe data to the terminal.

[0526] Device: Recommended recipes are displayed to the user.

[0527] 3. Select a recipe and view details

[0528] User: Select any recipe from the recommended recipes presented.

[0529] For example, select "Carrot and Chicken Puree."

[0530] On your device: Displays detailed information about the selected recipe, including specific ingredients, instructions, cooking time, etc.

[0531] 4. Learning User Preferences

[0532] Server: Stores the data of the recipe selected by the user.

[0533] The information saved is the user ID and the selected recipe ID.

[0534] Server: Applies algorithms to learn user preferences.

[0535] This allows the user's behavioral patterns and preferences to be analyzed.

[0536] Server: Updates the system to reflect the learning results in future recipe suggestions.

[0537] Specific examples

[0538] For example, suppose User A launches an application to make baby food, selects "baby food," and then enters "300g of carrots" and "200g of chicken." In this case, the server searches the database for baby food recipes that use "carrots" and "chicken," and generates recommended recipes such as "carrot and chicken puree" and "chicken and carrot stew." When the user selects "carrot and chicken puree," details of that recipe are displayed on the device. At the same time, the server saves the user's selection history and reflects it in the next recipe suggestion. This ensures that recipes that suit the user's preferences are provided each time the application is used.

[0539] The processing flow will be explained below.

[0540] Step 1:

[0541] Terminal: The user launches applications and web services.

[0542] Device: A UI for selecting conditions is displayed on the screen. The user is presented with options such as "baby food," "nursing care food," and "allergy-friendly food."

[0543] Step 2:

[0544] User: Select a condition. For example, select "baby food."

[0545] Terminal: Records the conditions (baby food) selected by the user.

[0546] Step 3:

[0547] Terminal: Displays an input form where the user can enter the ingredients and quantities purchased.

[0548] User: Enter the ingredients purchased and their quantities. For example, enter "300g carrots" and "200g chicken."

[0549] Step 4:

[0550] Terminal: A screen to confirm the input is displayed. After the user confirms the input, they click the confirmation button.

[0551] Terminal: Sends the user's input data (conditions and ingredients) to the server.

[0552] Step 5:

[0553] Server: Receives user input data, including the user ID, selection criteria, ingredients, and their quantities.

[0554] Server: Searches the database for recipes that match the conditions based on the received data.

[0555] Step 6:

[0556] Server: Generates a list of recipes that match the criteria. For example, it might select "carrot and chicken puree" or "chicken and carrot stew."

[0557] Server: Sends the generated recipe list to the terminal.

[0558] Step 7:

[0559] Device: Recommended recipes received from the server are displayed to the user. Recipe names and summaries are displayed in a list.

[0560] Step 8:

[0561] User: Select your preferred recipe from the recommended recipes displayed. For example, select "Carrot and Chicken Puree."

[0562] On your device: View detailed information about the selected recipe, including specific ingredients, cooking instructions, and cooking times.

[0563] Step 9:

[0564] Server: Stores the data of the recipe selected by the user. The stored information includes the user ID and the selected recipe ID.

[0565] Server: Applies algorithms to learn user preferences, which analyzes user behavior patterns and preferences.

[0566] Step 10:

[0567] Server: Updates the system to reflect the learning results in future recipe suggestions. This will enable the system to suggest recipes that better match the user's preferences when the user uses the system again.

[0568] Example 1

[0569] 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."

[0570] Conventional recipe suggestion systems have difficulty efficiently finding recipes that match the conditions and ingredients entered by the user, and lack the functionality to provide recipes that reflect the user's preferences in future recipes. For these reasons, there is a need to improve the user experience.

[0571] 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.

[0572] In this invention, the server includes means for a user to select conditions and input and register purchased ingredients and their quantities, means for receiving the input data and searching a database for recipes that match the conditions, means for displaying the searched recipes as recommendations to the user, means for saving the recipes selected by the user and learning the user's preferences, means for reflecting the learned user preferences in the selection of recommended recipes from the next time onwards, and means for displaying a corresponding interface when the user selects conditions. This allows the user to efficiently find recipes that match their conditions and preferences, and enables the system to reflect recipe suggestions that match the user's preferences from the next time onwards.

[0573] "User" refers to a person who uses a system or application.

[0574] "Conditions" refer to recipe categories and requirements that users specify to the system, such as baby food and nursing care food.

[0575] "Ingredients" refers to raw materials purchased by users and used to create recipes, such as carrots and chicken.

[0576] "Input" refers to the act of a user providing information to a system using a device such as a keyboard or touch panel.

[0577] "Registration means" refers to a function for recording data entered by a user and saving it within the system.

[0578] "Receiving means" refers to a function that allows the server to receive data sent from the user.

[0579] "Search means" refers to a function for searching a database for information that matches the conditions based on the received data.

[0580] A "database" refers to a system that organizes and stores large amounts of information, making it searchable and accessible as needed.

[0581] "Recommendation display means" refers to a function for suggesting information selected from search results to users.

[0582] "Storage means" refers to a function that records information selected by the user and saves it for later use.

[0583] "Learning means" refers to a function for analyzing stored information and learning user preferences and behavioral patterns.

[0584] "Reflection means" refers to the function of improving future suggestions based on the results of learning and providing them to users.

[0585] "Interface" refers to the screen and input devices that allow a user to interact with a system.

[0586] The present invention provides a system that allows a user to efficiently find recipes that suit their own conditions and preferences, and reflects these in future recipe suggestions. An embodiment of this system will be described in detail below.

[0587] When a user launches the smartphone application or web browser service, an initial screen appears. Here, the user can access the interface (UI) for setting the conditions for recipe suggestions. The UI provides options such as baby food and nursing care food.

[0588] When the user selects the conditions, an interface for inputting ingredients and their quantities is displayed on the screen. For example, the user can select "baby food" and input "300g of carrots" and "200g of chicken." This input data is displayed once on the confirmation screen on the device, and is sent to the server when the user clicks the confirm button.

[0589] The server receives the user's input data (user ID, selection criteria, ingredients and their quantities) and searches the database for recipes that match the criteria. Specifically, it searches for recipes that meet the criteria, for example, "baby food," "carrots," and "chicken." The server selects a recommended recipe from multiple matching recipes and sends that data to the device.

[0590] The device displays the recommended recipes received from the server on the user's screen. The user can select any recipe from the recommended recipes presented. For example, the user can select "carrot and chicken puree." Detailed information about the selected recipe (specific ingredients, cooking method, cooking time, etc.) is displayed on the device.

[0591] The data of the recipe selected by the user (user ID and selected recipe ID) is stored on the server. The server applies a machine learning algorithm to learn the user's preferences based on this data, analyzing the user's behavioral patterns and tastes. The learning results are updated in the system so that they are reflected in future recipe suggestions.

[0592] For example, if User A starts the application, selects "baby food," and enters "300g of carrots" and "200g of chicken," the server will search the database for baby food recipes that use "carrots" and "chicken," and recommend "carrot and chicken puree" or "chicken and carrot stew." If the user selects "carrot and chicken puree," its details are displayed. At the same time, the server records this selection and reflects it in the next recipe suggestion.

[0593] An example of a prompt sentence for the generative AI model is written as follows:

[0594] "I'd like to know what ingredients I have and what recipes I can use them in. For example, can you suggest a recipe that uses 300g of carrots and 200g of chicken?"

[0595] This system improves the user experience and provides the most suitable cooking method for each individual user by suggesting recipes that match the user's preferences. This process is carried out through cooperation between the server, terminals, and users.

[0596] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0597] Step 1:

[0598] The user launches an application or web service and the condition selection screen is displayed. The user selects conditions such as "baby food" or "care food." This input is used as initial condition data for the system to suggest appropriate recipes. The input data is the condition type, and the output is the display of the condition selection screen.

[0599] Step 2:

[0600] Based on the conditions selected by the user, a screen for inputting ingredients and their quantities is displayed on the terminal. Here, the user can input information such as "300g carrots" and "200g chicken." This input is used as additional condition data for recipe search. The input data is the names of ingredients and their quantities, and the output is the display of a confirmation screen.

[0601] Step 3:

[0602] The terminal sends the entered data to the server. When the user clicks the "Confirm" button on the confirmation screen, the user ID, selection criteria, ingredients, and their quantities are sent to the server. The input data is what the user entered when clicking the confirm button, and the output is the data sent to the server.

[0603] Step 4:

[0604] The server searches the database based on the data it receives. The server finds recipes that match the criteria "baby food," "carrots," and "chicken." The search algorithm selects the recipe that best fits the criteria specified by the user. The input data is the user's criteria and ingredient information sent, and the output is a list of matching recipes.

[0605] Step 5:

[0606] The server selects recommended recipes from the search results and sends the data to the device. In this case, recipes such as "carrot and chicken puree" and "chicken and carrot stew" are selected. The input data is the list of search results, and the output is the data sent to the user's device.

[0607] Step 6:

[0608] The device receives the data from the server and displays recommended recipes to the user. The user can select any recipe from the recipes presented on the screen. The input data is the recipe data received from the server, and the output is the recipe display to the user.

[0609] Step 7:

[0610] The user selects any recipe from the presented recipes. For example, if the user selects "carrot and chicken puree," detailed information about the recipe is displayed. The user's selection action is the input data, and the output is the display of detailed recipe information.

[0611] Step 8:

[0612] The server stores the user's selected recipe data. The user ID and selected recipe ID are recorded, and this data is used in an algorithm to learn the user's preferences. The input data is the user's selected action and the recipe ID, and the output is the storage of the selected data.

[0613] Step 9:

[0614] The server applies a machine learning algorithm to learn user preferences based on the stored data. The learning results are reflected in the selection of recommended recipes from the next time onwards, enabling the system to suggest recipes that are best suited to the user. The input data is the stored selection data, and the output is an updated recipe suggestion algorithm.

[0615] Through these steps, users can efficiently find recipes that suit their requirements and preferences, and the system can continue to improve its suggestions for future recipes.

[0616] (Application example 1)

[0617] 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."

[0618] Conventional recipe suggestion systems can suggest appropriate recipes based on a user's conditions and preferences, but they do not support ingredient delivery, which means users have to go through the trouble of obtaining the ingredients. Furthermore, while they have a mechanism for learning user preferences to reflect the results of that learning in selecting recommended recipes for the next time and beyond, they are unable to utilize this information in actual purchasing behavior or inventory management. The present invention aims to solve these problems and improve user convenience by enabling users to efficiently find recipes that meet their requirements and manage the delivery of those ingredients all in one place.

[0619] 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.

[0620] In this invention, the server includes means for allowing a user to select conditions and input and register the ingredients and their quantities to be purchased, means for receiving the input data and searching a database for recipes that match the conditions, means for displaying the searched recipes as recommendations to the user, means for saving a recipe selected by the user from the displayed recipes and learning the user's preferences, means for reflecting the learned user preferences in the selection of recommended recipes from the next time onwards, means for generating a list of necessary ingredients and ordering the ingredients, and means for managing the delivery of the ingredients. This allows a user to easily select a recipe that meets the conditions and order the ingredients for delivery all at once.

[0621] "Conditions" refer to specific requirements or constraints that a user specifies when receiving recipe suggestions.

[0622] "Ingredients" refers to the raw materials needed to create a dish or recipe.

[0623] "Quantity" refers to numerical information that indicates the specific quantity or weight of ingredients.

[0624] "Database" refers to a collection of information for efficiently managing, searching, and updating structured data.

[0625] A "recipe" refers to a document or data that contains instructions and a list of ingredients for creating a dish.

[0626] "Recommended" indicates candidates that are particularly recommended to the user based on specific conditions.

[0627] "Preferences" refer to the preferences or biases selected by a user based on specific conditions or criteria.

[0628] "Learning" refers to the process of analyzing and analysing a user's past behaviour and choices and reflecting this in future suggestions.

[0629] "Ingredient list" refers to a list of the names and amounts of ingredients required based on a recipe.

[0630] "Ordering" refers to the act of requesting the necessary ingredients from a specific delivery service.

[0631] "Delivery" refers to the service of delivering ordered ingredients to a specified location.

[0632] "Means" refers to a method or device used to achieve a particular purpose.

[0633] The present invention provides a system that enables a user to efficiently find a recipe that meets their own conditions and preferences, and to order delivery of the ingredients they need based on that recipe.

[0634] First, the user launches the application on a device such as a smartphone, smart glasses, or head-mounted display, and then uses the interface displayed on the screen to input specific conditions (e.g., baby food, vegetarian food), the ingredients purchased, and their quantities. The input data is then stored in a cloud database (e.g., Firebase) in real time.

[0635] The data recorded in the cloud database is sent to a server. The server receives the user's input data and searches the database for recipes that match the specified criteria. This search process uses a database management system and a recipe search API. For example, a search can be made for recipes in "baby food" that use "300g of carrots" and "200g of chicken."

[0636] From the search results, a generative AI model (e.g., TensorFlow) is used to select the recipe that best suits the user's criteria. The selected recipe is sent to the user's device and displayed as a recommendation on the screen.

[0637] When a user selects a recipe from the recommended recipes, detailed information about that recipe (ingredients, cooking method, cooking time, etc.) is displayed. The information about the selected recipe is saved on the server and accumulated as user preference data. Based on this preference data, a machine learning algorithm (e.g., PyTorch) is used to learn the user's preference patterns and reflect them in future recipe suggestions.

[0638] Next, a list of ingredients is generated based on the selected recipe, and an order for delivery of the ingredients is placed using an API corresponding to the delivery service (e.g., Uber Eats, DoorDash, etc.) The generation of the ingredient list and the transmission of the delivery order are carried out on the server side, and the order is transmitted to the corresponding delivery company.

[0639] For example:

[0640] For example, if a user starts an application to make baby food, selects "baby food," and then enters "300g of carrots" and "200g of chicken," the server will search the database for baby food recipes that use "carrots" and "chicken," and generate recommended recipes such as "carrot and chicken puree" and "chicken and carrot stew." When the user selects "carrot and chicken puree," details of that recipe are displayed on the device. At the same time, the server saves the user's selection history and reflects it in the next recipe suggestion.

[0641] An example prompt would be:

[0642] "User selects baby food and enters 300g of carrots and 200g of chicken."

[0643] In this way, the present invention provides consistent support from the process of users finding a recipe that meets their requirements to purchasing and delivering the necessary ingredients, thereby greatly improving user convenience.

[0644] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0645] Step 1:

[0646] The user launches the application on their device and the condition selection interface is displayed. The user enters the conditions, ingredients, and their quantities, and sends this data to the device. The entered data is saved in real time to a cloud database (Firebase). This registers the user-specified conditions and ingredient information in the database.

[0647] Input: Condition (e.g., baby food), ingredients (e.g., 300g carrots, 200g chicken)

[0648] Output: Data stored in a cloud database

[0649] Specific behavior:

[0650] The user enters "Condition: Baby food," "Ingredients: 300g carrots," and "Ingredients: 200g chicken," and clicks the "Save" button.

[0651] Step 2:

[0652] The device sends the input data to the server. The server receives this data and searches the database for recipes that meet the criteria. This search uses a recipe search API or database management system. As a result, the server extracts and selects multiple recipes that meet the criteria.

[0653] Input: User data retrieved from a cloud database

[0654] Output: A list of recipes that match the criteria

[0655] Specific behavior:

[0656] The server searches for recipe data containing "baby food," "carrots," and "chicken," and extracts candidates such as "carrot and chicken puree" and "chicken and carrot stew."

[0657] Step 3:

[0658] The server uses a generative AI model (TensorFlow) to select the recipe that best suits the user's requirements. The selected recipe data is sent to the device and displayed as a recommendation on the user's screen.

[0659] Input: Multiple recipes that meet the criteria

[0660] Output: One or more recommended recipes

[0661] Specific behavior:

[0662] The server evaluates recipes using the generative AI model and sends the best candidates as "recommendations" to the device, which then displays "Recommended Recipe: Carrot and Chicken Puree."

[0663] Step 4:

[0664] The user selects any recipe from the recommended recipes and the details of that recipe (ingredients, cooking method, cooking time, etc.) are displayed. The selected recipe information is sent to the server and saved as the user's preference data.

[0665] Input: User selected recipe

[0666] Output: Display details of selected recipe, save preference data to server

[0667] Specific behavior:

[0668] When the user selects "Carrot and Chicken Puree," its detailed information is displayed on the screen. At the same time, the "User ID" and "Recipe ID" are saved on the server.

[0669] Step 5:

[0670] The server uses a machine learning algorithm (PyTorch) to learn the user's preference patterns and reflect them in future recipe suggestions. This learning process improves the accuracy of recipe suggestions based on the user's preferences.

[0671] Input: User preference data

[0672] Output: Updated user preference data pattern

[0673] Specific behavior:

[0674] The server analyzes the recipes the user has previously selected to reflect this in the next recipe suggestions.

[0675] Step 6:

[0676] The server generates a list of ingredients based on the selected recipe and sends the order to the partner delivery service API.

[0677] Input: A list of ingredients for the selected recipe

[0678] Output: Delivery order sent

[0679] Specific behavior:

[0680] The server generates an ingredient list of "300g of carrots" and "200g of chicken" and sends it to the delivery service API.

[0681] Step 7:

[0682] The delivery company receives the list of ingredients, prepares them, and delivers them to the specified address. The user can then pick up the ordered ingredients and create the dish according to the recipe.

[0683] Input: Delivery Order

[0684] Output: Food delivery to the specified address

[0685] Specific behavior:

[0686] The delivery company prepares the order and delivers 300g of carrots and 200g of chicken to the user's address.

[0687] 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.

[0688] The present invention is a system that allows users to efficiently find recipes that suit their own conditions and preferences, and further learns their preferences and feelings and reflects them in future recipe suggestions.

[0689] Program processing

[0690] 1. Select conditions and register ingredients

[0691] Terminal: The user launches applications and web services.

[0692] Device: A UI for selecting conditions is displayed on the screen. The user is presented with options such as "baby food," "nursing care food," and "allergy-friendly food."

[0693] User: Select a condition. For example, select "baby food."

[0694] Terminal: Records the conditions (baby food) selected by the user.

[0695] 2. Enter ingredients and emotions

[0696] Terminal: Displays an input form that allows the user to input the ingredients purchased and the amount, and also displays an interface for inputting or measuring the user's emotions.

[0697] User: Enter the ingredients purchased, their quantities, and their current emotions. For example, they can enter "300g of carrots," "200g of chicken," and "satisfied."

[0698] Terminal: A screen to confirm the input information is displayed, and the user clicks the confirmation button.

[0699] Terminal: Sends the user's input data (conditions, ingredients, emotions) to the server.

[0700] 3. Creating and displaying recipes

[0701] Server: Receives user input data, including the user ID, selection criteria, ingredients and their amounts, and emotions.

[0702] Server: Searches for recipes that match the criteria from the database based on the received data and past data. It also uses an emotion engine to select recipes that correspond to the user's emotions.

[0703] Server: Generates a list of recipes that match the criteria and are emotionally appropriate. For example, it might select "carrot and chicken puree" or "chicken and carrot stew."

[0704] Server: Sends the generated recipe list to the terminal.

[0705] Device: Recommended recipes are displayed to the user.

[0706] 4. Select a recipe and view details

[0707] User: Select a recipe from the suggested recipes. For example, select "Carrot and Chicken Puree."

[0708] On your device: View detailed information about the selected recipe, including specific ingredients, cooking instructions, and cooking times.

[0709] 5. Learning user preferences and emotions

[0710] Server: Stores the recipe data selected by the user and the emotion data at that time. The stored information includes the user ID, the selected recipe ID, and the emotion data.

[0711] Server: Applies algorithms to learn user preferences and emotions, which analyzes user behavior patterns, preferences, and emotions.

[0712] Server: Updates the system to reflect the learning results in future recipe suggestions. This ensures that when the user uses the system again, it will suggest recipes that better match their preferences and emotions.

[0713] Specific examples

[0714] For example, suppose User A launches an application to make baby food, selects "baby food," and then enters "300g carrots," "200g chicken," and "satisfied." In this case, the server searches the database for baby food recipes that use "carrots" and "chicken," and selects a recipe that matches the user's emotion of "satisfied." It generates recommended recipes such as "carrot and chicken puree" and "chicken and carrot stew" and sends them to the device. When the user selects "carrot and chicken puree," details of that recipe are displayed on the device. At the same time, the server saves the user's selection history and emotion data and reflects them in the next recipe suggestions. This ensures that recipes that match the user's preferences and emotions are provided each time the application is used.

[0715] The processing flow will be explained below.

[0716] Step 1:

[0717] Terminal: The user launches applications and web services.

[0718] Terminal: A UI for selecting conditions is displayed on the screen, and the user is presented with options such as "baby food," "nursing care food," and "allergy-friendly food."

[0719] Step 2:

[0720] User: Select a condition. For example, select "baby food."

[0721] Terminal: Records the conditions (baby food) selected by the user.

[0722] Step 3:

[0723] Terminal: Displays the screen for inputting ingredients and emotions. An interface is provided for the user to input the ingredients purchased, their quantities, and their current emotions.

[0724] User: Enter the ingredients purchased, their quantities, and their current emotions. For example, enter "300g of carrots," "200g of chicken," and "Satisfied."

[0725] Step 4:

[0726] Terminal: A screen to confirm the input information is displayed, and the user clicks the confirmation button.

[0727] Terminal: Sends the user's input data (conditions, ingredients, emotions) to the server.

[0728] Step 5:

[0729] Server: Receives the user's input data, including the user ID, selection criteria, ingredients, and emotions.

[0730] Step 6:

[0731] Server: Based on the input data and past data, the server searches the database for recipes that match the conditions, and uses an emotion engine to select a recipe that suits the user's emotions.

[0732] For example, if a user enters "satisfied," recipes chosen with similar emotions or highly rated recipes will be prioritized.

[0733] Step 7:

[0734] Server: Generates a list of recommended recipes that match the conditions and emotions.

[0735] For example, select "carrot and chicken puree" or "chicken and carrot stew."

[0736] Server: Sends the generated recipe list to the terminal.

[0737] Step 8:

[0738] Device: Recommended recipes received from the server are displayed to the user. Recipe names and summaries are displayed in a list.

[0739] Step 9:

[0740] User: Select your preferred recipe from the recommended recipes displayed.

[0741] For example, select "Carrot and Chicken Puree."

[0742] On your device: Detailed information about the selected recipe will be displayed, including specific ingredients, cooking instructions, and cooking time.

[0743] Step 10:

[0744] Server: Stores the data of the recipe selected by the user and the emotion data at that time.

[0745] The information stored includes the user ID, the selected recipe ID, and emotion data.

[0746] Step 11:

[0747] Server: Applies algorithms to learn user preferences and emotions.

[0748] User behavior patterns, preferences, and emotions are analyzed.

[0749] Step 12:

[0750] Server: Updates the system to reflect the learning results in future recipe suggestions.

[0751] This means that when a user uses the system again, recipes that better match their preferences and emotions will be suggested.

[0752] Example 2

[0753] 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."

[0754] Conventional recipe suggestion systems were able to provide recipes that matched the user's conditions and ingredients, but it was difficult to learn the user's emotions and preferences and reflect them in future suggestions. Furthermore, because they were unable to take into account the ingredients purchased by the user or their emotions, the accuracy of suggesting the optimal recipe for the user was low. This led to users being dissatisfied with the recipe selection, resulting in a decrease in the frequency of system use.

[0755] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0756] In this invention, the server includes means for allowing a user to select conditions and input and register purchased ingredients and their quantities, means for receiving the input data and searching a database for recipes that match the conditions, means for using an emotion engine to select a recipe according to emotions based on the received data and past data, means for displaying the searched recipes as recommendations to the user, means for saving a recipe selected by the user from the displayed recipes and learning the user's preferences and emotions, and means for reflecting the learned user preferences and emotions in the selection of recommended recipes from the next time onwards. This makes it possible to propose optimal recipes based on the user's conditions, ingredients, and emotions.

[0757] "Conditions" are user-selected constraints or requirements, including, for example, types of food and health restrictions.

[0758] "Ingredients" refer to the foods and ingredients used in a dish or recipe, and specifically include vegetables, meat, seasonings, etc.

[0759] "Quantity" is a numerical value indicating the quantity or weight of a material that the user has purchased or possesses.

[0760] A "database" is a collection of information that structures and stores user conditions, ingredients, and recipe information.

[0761] "Search" is the operation of searching a database for information that matches specified conditions.

[0762] A "prescription" is information that indicates a recipe or cooking method for a dish.

[0763] "Emotion" indicates the user's current psychological state, and is information such as "satisfied" or "dissatisfied," for example.

[0764] An "emotion engine" is an algorithm or system that selects the optimal prescription based on the user's emotions.

[0765] "Display" refers to the operation of visually showing prescription information and recommended recipes on the user's device.

[0766] "Preferences" indicate a user's tendency to prefer particular recipes or ingredients.

[0767] "Learning" is an information analysis process that uses user preferences and emotional data to reflect in future recipe suggestions.

[0768] A "system" is a set of mechanisms that combine multiple means and technologies to provide services to users.

[0769] MODE FOR CARRYING OUT THE INVENTION

[0770] This invention is a system that allows users to efficiently find recipes that suit their own conditions and preferences, and also learns their preferences and feelings and reflects them in future recipe suggestions.

[0771] System Overview

[0772] This system includes means for a user to select conditions and input and register purchased materials and their quantities, means for receiving the input data and searching a database for recipes that match the conditions, means for using an emotion engine to select a recipe according to emotions based on the received data and past data, means for displaying the searched recipes as recommendations to the user, means for saving a recipe selected by the user from the displayed recipes and learning the user's preferences and emotions, and means for reflecting the learned user preferences and emotions in the selection of recommended recipes from the next time onwards.

[0773] Hardware and Software Configuration

[0774] 1. Terminal: A device used by a user to access an application or web service, including a smartphone, tablet, or PC.

[0775] 2. Server: This is the central system that receives and processes input data from users. It includes a database server, machine learning engine, and emotion engine.

[0776] 3. Software:

[0777] User interface: A UI on an application or web browser that provides an interface for selecting conditions and inputting materials.

[0778] Database system: A database (e.g., SQL database) for storing and managing entered user and prescription data.

[0779] Emotion engine: An algorithm for analyzing user emotions and suggesting appropriate prescriptions based on them.

[0780] Machine learning algorithms: Recommendation systems that learn user preferences and history and reflect this in future recommendations.

[0781] Specific examples

[0782] For example, suppose User A launches the application, selects "baby food," and then enters "300g carrots," "200g chicken," and "satisfied." In this case, the server searches the database for baby food recipes that use "carrots" and "chicken," and selects a recipe that corresponds to the user's emotion of "satisfied." As a result, recommended recipes such as "carrot and chicken puree" and "chicken and carrot stew" are generated and sent to the device. When the user selects "carrot and chicken puree," details of the selection are displayed on the device. At the same time, the server saves the user's selection history and emotion data, and can reflect this in the next recipe suggestions. This allows the server to provide recipes that match the user's preferences and emotions each time the application is used.

[0783] Prompt Sentence Examples

[0784] By inputting the following prompt sentence into the generative AI model, a description of the above system can be generated in natural language.

[0785] "Users input conditions, ingredients, and emotions through an application or web service, and the AI ​​model uses a database and emotion engine to generate natural-sounding sentences that explain the system and suggest prescriptions that match the conditions and are appropriate for the emotions."

[0786] The prompts enable the generative AI model to generate detailed natural language descriptions of the system's functions and procedures.

[0787] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0788] Step 1:

[0789] Terminal: When a user launches an application or web service, the home screen appears.

[0790] Input: Application launch by user action

[0791] Output: Display of the home screen of the application or web service

[0792] Specific actions: Tap an icon on your smartphone to launch an app, or enter a URL in a web browser.

[0793] Step 2:

[0794] Terminal: A user interface (UI) for selecting conditions is displayed on the screen. The user is presented with options such as "baby food," "nursing care food," and "allergy-friendly food."

[0795] Input: The application initialization process calls the criteria selection UI

[0796] Output: Display of a screen where the user can select conditions

[0797] Specific operation: A screen will appear where you can select conditions using a drop-down menu or radio buttons.

[0798] Step 3:

[0799] User: Select a condition and click the Next button. For example, select "baby food."

[0800] Input: User selection of conditions

[0801] Output: Record of selected conditions and transition to the next input screen

[0802] Specific actions: Select with a mouse click or touch gesture and press the "Next" button.

[0803] Step 4:

[0804] Terminal: Displays a form that allows the user to input the ingredients and their quantities purchased, and also displays an interface for inputting or measuring the user's emotions.

[0805] Input: System response to condition selection

[0806] Output: Display of material and emotion input form

[0807] Specific operation: A section for entering ingredients and their quantities using text boxes or voice input, as well as a slider or button for entering emotions, will be displayed.

[0808] Step 5:

[0809] User: Enter the ingredients purchased (e.g., "300g carrots" and "200g chicken") and their current feelings (e.g., "Satisfied").

[0810] Input: User input of materials and emotions

[0811] Output: Display of input confirmation screen

[0812] Specific actions: Enter text or use voice recognition to enter material information, then drag the emotion slider to the appropriate value.

[0813] Step 6:

[0814] Terminal: A screen is displayed to confirm the input and the user is asked to click a confirmation button.

[0815] Input: Material and emotional input data

[0816] Output: Display confirmation screen

[0817] Specific operation: Displays the input data and displays a button to ask the user for confirmation.

[0818] Step 7:

[0819] User: Click the Verify button to verify that the data is correct.

[0820] Input: User clicks confirmation button

[0821] Output: Confirmed data transmission process

[0822] Specific operation: Press the confirmation button to confirm the input.

[0823] Step 8:

[0824] Terminal: Sends the user's input data (conditions, materials, emotions) to the server.

[0825] Input: Confirmed data

[0826] Output: Send data to the server

[0827] Specific operation: Executes an API call to send data to a server over the network.

[0828] Step 9:

[0829] Server: Receives input data sent by the user, searches the database for prescriptions that match the conditions, and uses an emotion engine to select a prescription that corresponds to the user's emotion.

[0830] Input: Input data sent from the terminal

[0831] Output: A list of prescriptions that match the criteria and are emotionally appropriate

[0832] Specific operation: Executes an SQL query to extract relevant prescriptions from the database and filters them using the emotion engine.

[0833] Step 10:

[0834] Server: Generates a list of recipes that match the conditions and are emotionally appropriate. For example, it might select "carrot and chicken puree" or "stewed chicken and carrots."

[0835] Input: Searched and filtered prescription data

[0836] Output: Generate a prescription list

[0837] Specific operation: Generate a list based on the filtered prescription data.

[0838] Step 11:

[0839] Server: Sends the generated prescription list to the user's terminal.

[0840] Input: Generated prescription list

[0841] Output: Send prescription list to terminal

[0842] Specific operation: Executes an API call to send a prescription list to the terminal via the network.

[0843] Step 12:

[0844] Device: Recommended recipes are displayed to the user.

[0845] Input: Prescription list sent from the server

[0846] Output: Display recommended recipes

[0847] Specific operation: Recipes appear on the screen in a list format using a design template.

[0848] Step 13:

[0849] User: Select a recipe from the suggested recipes. For example, select "Carrot and Chicken Puree."

[0850] Input: User selection of recipe

[0851] Output: Display detailed information about the selected recipe

[0852] Action: Tap or click to select a recipe from the list.

[0853] Step 14:

[0854] On your device: View detailed information about the selected recipe, including specific ingredients, cooking instructions, and cooking times.

[0855] Input: Recipe data selected by the user

[0856] Output: Display detailed recipe information

[0857] What Happens: A detailed view of the recipe appears, showing the ingredients list and steps in a scrollable format.

[0858] Step 15:

[0859] Server: Stores the data of the recipe selected by the user and the emotion data at that time.

[0860] Input: Recipe data and emotion data selected by the user

[0861] Output: Saved user data

[0862] Specific action: It is recorded as a new record in the database.

[0863] Step 16:

[0864] Server: Applies algorithms to learn user preferences and emotions, which analyzes user behavior patterns, preferences, and emotions.

[0865] Input: Stored user preference and emotion data

[0866] Output: Training data as analysis results

[0867] Specific actions: Run machine learning algorithms (e.g., recommendation systems) to analyze data.

[0868] Step 17:

[0869] Server: Updates the system to reflect the learning results in future recipe suggestions. This ensures that when the user uses the system again, it will suggest recipes that better match their preferences and emotions.

[0870] Input: Parsed training data

[0871] Output: Proposed features of the updated system

[0872] Specific operation: The proposed algorithm is updated based on the training data.

[0873] (Application example 2)

[0874] 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."

[0875] Conventional recipe suggestion systems were able to provide recipes that took into account the user's conditions and preferences, but they were unable to suggest recipes that reflected the user's emotions. As a result, suggestions that improved the user's emotional satisfaction and experience were insufficient. Furthermore, if a user's recipe preferences differed depending on a specific emotion, this was not recorded or learned, and could not be reflected in future suggestions. Therefore, the goal of this project is to further improve user satisfaction by providing a recipe suggestion system that also takes into account the user's emotions.

[0876] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0877] In this invention, the server includes a means for a user to select conditions and input and register purchased ingredients and their quantities, a means for receiving the input data and the user's emotional data, and a means for searching a database for recipes that match the conditions, and a means for displaying the searched recipes as recommendations to the user, thereby enabling recipe suggestions based on the user's emotions in addition to their conditions and preferences.

[0878] "User" means an individual or organization that uses the system.

[0879] "Conditions" are parameters that a user sets to search for a particular recipe.

[0880] "Ingredients" refers to the types and amounts of food used to prepare a recipe.

[0881] "Emotion data" is information that indicates the user's emotional state, and is data that the system receives to use in proposing recipes.

[0882] A "database" is a structured collection of information that stores recipe information and facilitates retrieval.

[0883] The "search means" is a software function that searches the database for recipes that meet the user's requirements.

[0884] The "displaying means" is an interface for displaying the selected recipe on the user's device.

[0885] The "storage means" is a system that records the user's selected recipes and emotional data for future reference and learning.

[0886] The "learning means" is an algorithm that analyzes stored user preference and emotion data and reflects that in future suggestions.

[0887] "Server" means a central management system for receiving, processing, and storing data.

[0888] This invention is a system that allows users to input ingredients and their quantities via a smartphone application or web interface, and suggests recipes that suit their preferences and conditions. This includes a means for users to select conditions, input purchased ingredients and emotional data, and provide recipes based on those.

[0889] System configuration and usage

[0890] 1. User selection of conditions and input of ingredients

[0891] The user launches the application and selects criteria such as "baby food," "caregiver food," and "allergy-friendly food" from their smartphone or computer terminal.

[0892] After selecting these conditions, the user inputs the type and quantity of ingredients purchased, as well as emotional data (such as "satisfied" or "sad").

[0893] 2. Data Receipt and Processing by the Server

[0894] The conditions, ingredients, and emotion data entered by the user are sent to the server, which receives this data and searches a database for recipes that match the ingredients and conditions.

[0895] The server uses an emotion engine, such as a TensorFlow-based emotion analysis model, to select recipes that match the user's emotional state based on the received emotion data.

[0896] 3. Creating and displaying recipes

[0897] The searched recipes are displayed as recommendations on the user's device. Recipe information includes the ingredients needed, cooking steps, cooking time, etc.

[0898] When the user selects a recipe from the ones presented, more detailed information about that recipe is displayed.

[0899] 4. Learning and storing user preference and emotion data

[0900] The server records the recipe selected by the user and their emotional state at the time. This data is used to make future recommendations.

[0901] It applies algorithms to learn user preferences and emotional data, analyzing user behavior patterns and preferences, so that future recipe suggestions are more tailored to the user's needs and emotions.

[0902] Hardware and software used

[0903] Hardware: Servers (e.g., Amazon EC2), user devices (smartphones, PCs, etc.)

[0904] Software: Flask (a web framework written in Python), SQLite (a local database), TensorFlow (a machine learning library for sentiment analysis)

[0905] Examples and prompts

[0906] For example, suppose User A starts an application to make baby food, selects "baby food," and then inputs "300g carrots," "200g chicken," and "satisfied." In this case, the server searches the database for baby food recipes that use "carrots" and "chicken," and selects a recipe that matches the user's emotion of "satisfied." Suggested recipes include "carrot and chicken puree" and "chicken and carrot stew."

[0907] Here is an example prompt:

[0908] Let's say a user selects "baby food" as a condition, and inputs "300g carrots," "200g chicken," and the emotion "satisfied." In this case, we'll suggest the following recipes:

[0909] 1. Carrot and chicken puree

[0910] 2. Chicken and carrot stew

[0911] By inputting this prompt into a generative AI model, recipes that match the user's conditions and emotions can be efficiently generated and suggested.

[0912] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0913] Step 1:

[0914] The user launches the application and selects conditions on a smartphone or computer. Specifically, options such as "baby food," "nursing care food," and "allergy-friendly food" are displayed, and the user selects one. The input data is sent to the server in the form of condition selection.

[0915] Step 2:

[0916] Based on the selected criteria, the user inputs the ingredients purchased, their quantities, and emotional data, such as "300g of carrots," "200g of chicken," and "satisfied." This data is also sent from the device to the server.

[0917] Step 3:

[0918] The server processes the received conditions, ingredient data, and emotion data. It then searches the database for recipes that match the conditions based on the type and amount of ingredients. It also takes into account the input emotion data and uses an emotion analysis model such as TensorFlow to select recipes that suit the emotion.

[0919] Step 4:

[0920] Based on the results of the search and sentiment analysis, the system generates recipe recommendations for the user. These recipes include, for example, "carrot and chicken puree" and "chicken and carrot stew." This list is sent to the user's device as recipe information and displayed on the screen.

[0921] Step 5:

[0922] The user selects a recipe from the list of recipes presented, and detailed information about the selected recipe (ingredients, cooking steps, cooking time, etc.) is displayed.

[0923] Step 6:

[0924] The server stores the recipe selected by the user and the emotion data at that time. The saved data is recorded along with the user ID and will be used for future recipe suggestions.

[0925] Step 7:

[0926] The server analyzes the stored data and applies algorithms that learn the user's preferences and emotions, allowing it to better tailor future recipe suggestions to the user's behavioral patterns, tastes, and emotions.

[0927] Specific explanation of processing operations

[0928] Step 1:

[0929] Input data: User selection of conditions (e.g., "baby food")

[0930] Output data: Criteria selection data sent to the server

[0931] How it works: A user launches the application and selects criteria on their smartphone or computer.

[0932] Step 2:

[0933] Input data: Food ingredient data and emotion data (e.g., "300g carrots," "200g chicken," "satisfied")

[0934] Output data: Ingredient data and emotion data sent to the server

[0935] How it works: Based on the selected criteria, the user inputs the ingredients purchased, their quantities, and emotional data.

[0936] Step 3:

[0937] Input data: condition data, ingredient data, emotion data

[0938] Output data: Recipe search results and sentiment analysis results

[0939] How it works: The server processes the received data, searches the database for recipes that match the criteria, and uses a sentiment analysis model to select an appropriate recipe.

[0940] Step 4:

[0941] Input data: Recipe search results and sentiment analysis results

[0942] Output data: A list of recipes recommended for the user

[0943] Operation: The server generates recommended recipes based on the search and analysis results, sends them to the user's device, and displays them on the screen.

[0944] Step 5:

[0945] Input data: User selected recipe

[0946] Output data: Detailed information about the selected recipe

[0947] How it works: The user selects a recipe from the ones presented and its details are displayed.

[0948] Step 6:

[0949] Input data: Selected recipes and sentiment data

[0950] Output data: Selection history and emotion data stored on the server

[0951] Operation: The server stores the recipe selected by the user and the emotion data at that time.

[0952] Step 7:

[0953] Input data: saved selection history and emotion data

[0954] Output data: Recipe suggestions for the next time and beyond that reflect the user's behavioral patterns, preferences, and emotions

[0955] How it works: The server analyzes the stored data and applies algorithms that learn the user's preferences and emotions to improve future recipe suggestions.

[0956] 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.

[0957] 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.

[0958] 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.

[0959] [Third embodiment]

[0960] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0961] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0962] 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).

[0963] 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.

[0964] 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.

[0965] 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).

[0966] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0967] 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.

[0968] 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.

[0969] 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.

[0970] 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.

[0971] 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."

[0972] The present invention is a system that allows a user to efficiently find recipes that suit their own conditions and preferences, and reflects this in future recipe suggestions.

[0973] Program processing

[0974] 1. Select conditions and register ingredients

[0975] Terminal: The user launches applications and web services.

[0976] Device: A UI for selecting conditions is displayed on the screen. The user selects conditions such as baby food or nursing care food.

[0977] User: Selects conditions and enters purchased ingredients and their quantities.

[0978] For example, select "baby food" and enter "300g carrots" and "200g chicken."

[0979] Terminal: A screen to confirm the input information is displayed, and the user clicks the confirmation button.

[0980] Terminal: The entered data is sent to the server.

[0981] The transmitted information includes the user ID, selection criteria, ingredients and their quantities.

[0982] 2. Creating and displaying recipes

[0983] Server: Receives the user's input data.

[0984] Server: Searches the database for recipes that match the criteria.

[0985] For example, search for baby food recipes that use carrots and chicken.

[0986] Server: Select several recommended recipes from the search results.

[0987] For example: "Carrot and chicken puree", "Chicken and carrot stew", etc.

[0988] Server: Sends the selected recipe data to the terminal.

[0989] Device: Recommended recipes are displayed to the user.

[0990] 3. Select a recipe and view details

[0991] User: Select any recipe from the recommended recipes presented.

[0992] For example, select "Carrot and Chicken Puree."

[0993] On your device: Displays detailed information about the selected recipe, including specific ingredients, instructions, cooking time, etc.

[0994] 4. Learning User Preferences

[0995] Server: Stores the data of the recipe selected by the user.

[0996] The information saved is the user ID and the selected recipe ID.

[0997] Server: Applies algorithms to learn user preferences.

[0998] This allows the user's behavioral patterns and preferences to be analyzed.

[0999] Server: Updates the system to reflect the learning results in future recipe suggestions.

[1000] Specific examples

[1001] For example, suppose User A launches an application to make baby food, selects "baby food," and then enters "300g of carrots" and "200g of chicken." In this case, the server searches the database for baby food recipes that use "carrots" and "chicken," and generates recommended recipes such as "carrot and chicken puree" and "chicken and carrot stew." When the user selects "carrot and chicken puree," details of that recipe are displayed on the device. At the same time, the server saves the user's selection history and reflects it in the next recipe suggestion. This ensures that recipes that suit the user's preferences are provided each time the application is used.

[1002] The processing flow will be explained below.

[1003] Step 1:

[1004] Terminal: The user launches applications and web services.

[1005] Device: A UI for selecting conditions is displayed on the screen. The user is presented with options such as "baby food," "nursing care food," and "allergy-friendly food."

[1006] Step 2:

[1007] User: Select a condition. For example, select "baby food."

[1008] Terminal: Records the conditions (baby food) selected by the user.

[1009] Step 3:

[1010] Terminal: Displays an input form where the user can enter the ingredients and quantities purchased.

[1011] User: Enter the ingredients purchased and their quantities. For example, enter "300g carrots" and "200g chicken."

[1012] Step 4:

[1013] Terminal: A screen to confirm the input is displayed. After the user confirms the input, they click the confirmation button.

[1014] Terminal: Sends the user's input data (conditions and ingredients) to the server.

[1015] Step 5:

[1016] Server: Receives user input data, including the user ID, selection criteria, ingredients, and their quantities.

[1017] Server: Searches the database for recipes that match the conditions based on the received data.

[1018] Step 6:

[1019] Server: Generates a list of recipes that match the criteria. For example, it might select "carrot and chicken puree" or "chicken and carrot stew."

[1020] Server: Sends the generated recipe list to the terminal.

[1021] Step 7:

[1022] Device: Recommended recipes received from the server are displayed to the user. Recipe names and summaries are displayed in a list.

[1023] Step 8:

[1024] User: Select your preferred recipe from the recommended recipes displayed. For example, select "Carrot and Chicken Puree."

[1025] On your device: View detailed information about the selected recipe, including specific ingredients, cooking instructions, and cooking times.

[1026] Step 9:

[1027] Server: Stores the data of the recipe selected by the user. The stored information includes the user ID and the selected recipe ID.

[1028] Server: Applies algorithms to learn user preferences, which analyzes user behavior patterns and preferences.

[1029] Step 10:

[1030] Server: Updates the system to reflect the learning results in future recipe suggestions. This will enable the system to suggest recipes that better match the user's preferences when the user uses the system again.

[1031] Example 1

[1032] 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."

[1033] Conventional recipe suggestion systems have difficulty efficiently finding recipes that match the conditions and ingredients entered by the user, and lack the functionality to provide recipes that reflect the user's preferences in future recipes. For these reasons, there is a need to improve the user experience.

[1034] 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.

[1035] In this invention, the server includes means for a user to select conditions and input and register purchased ingredients and their quantities, means for receiving the input data and searching a database for recipes that match the conditions, means for displaying the searched recipes as recommendations to the user, means for saving the recipes selected by the user and learning the user's preferences, means for reflecting the learned user preferences in the selection of recommended recipes from the next time onwards, and means for displaying a corresponding interface when the user selects conditions. This allows the user to efficiently find recipes that match their conditions and preferences, and enables the system to reflect recipe suggestions that match the user's preferences from the next time onwards.

[1036] "User" refers to a person who uses a system or application.

[1037] "Conditions" refer to recipe categories and requirements that users specify to the system, such as baby food and nursing care food.

[1038] "Ingredients" refers to raw materials purchased by users and used to create recipes, such as carrots and chicken.

[1039] "Input" refers to the act of a user providing information to a system using a device such as a keyboard or touch panel.

[1040] "Registration means" refers to a function for recording data entered by a user and saving it within the system.

[1041] "Receiving means" refers to a function that allows the server to receive data sent from the user.

[1042] "Search means" refers to a function for searching a database for information that matches the conditions based on the received data.

[1043] A "database" refers to a system that organizes and stores large amounts of information, making it searchable and accessible as needed.

[1044] "Recommendation display means" refers to a function for suggesting information selected from search results to users.

[1045] "Storage means" refers to a function that records information selected by the user and saves it for later use.

[1046] "Learning means" refers to a function for analyzing stored information and learning user preferences and behavioral patterns.

[1047] "Reflection means" refers to the function of improving future suggestions based on the results of learning and providing them to users.

[1048] "Interface" refers to the screen and input devices that allow a user to interact with a system.

[1049] The present invention provides a system that allows a user to efficiently find recipes that suit their own conditions and preferences, and reflects these in future recipe suggestions. An embodiment of this system will be described in detail below.

[1050] When a user launches the smartphone application or web browser service, an initial screen appears. Here, the user can access the interface (UI) for setting the conditions for recipe suggestions. The UI provides options such as baby food and nursing care food.

[1051] When the user selects the conditions, an interface for inputting ingredients and their quantities is displayed on the screen. For example, the user can select "baby food" and input "300g of carrots" and "200g of chicken." This input data is displayed once on the confirmation screen on the device, and is sent to the server when the user clicks the confirm button.

[1052] The server receives the user's input data (user ID, selection criteria, ingredients and their quantities) and searches the database for recipes that match the criteria. Specifically, it searches for recipes that meet the criteria, for example, "baby food," "carrots," and "chicken." The server selects a recommended recipe from multiple matching recipes and sends that data to the device.

[1053] The device displays the recommended recipes received from the server on the user's screen. The user can select any recipe from the recommended recipes presented. For example, the user can select "carrot and chicken puree." Detailed information about the selected recipe (specific ingredients, cooking method, cooking time, etc.) is displayed on the device.

[1054] The data of the recipe selected by the user (user ID and selected recipe ID) is stored on the server. The server applies a machine learning algorithm to learn the user's preferences based on this data, analyzing the user's behavioral patterns and tastes. The learning results are updated in the system so that they are reflected in future recipe suggestions.

[1055] For example, if User A starts the application, selects "baby food," and enters "300g of carrots" and "200g of chicken," the server will search the database for baby food recipes that use "carrots" and "chicken," and recommend "carrot and chicken puree" or "chicken and carrot stew." If the user selects "carrot and chicken puree," its details are displayed. At the same time, the server records this selection and reflects it in the next recipe suggestion.

[1056] An example of a prompt sentence for the generative AI model is written as follows:

[1057] "I'd like to know what ingredients I have and what recipes I can use them in. For example, can you suggest a recipe that uses 300g of carrots and 200g of chicken?"

[1058] This system improves the user experience and provides the most suitable cooking method for each individual user by suggesting recipes that match the user's preferences. This process is carried out through cooperation between the server, terminals, and users.

[1059] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1060] Step 1:

[1061] The user launches an application or web service and the condition selection screen is displayed. The user selects conditions such as "baby food" or "care food." This input is used as initial condition data for the system to suggest appropriate recipes. The input data is the condition type, and the output is the display of the condition selection screen.

[1062] Step 2:

[1063] Based on the conditions selected by the user, a screen for inputting ingredients and their quantities is displayed on the terminal. Here, the user can input information such as "300g carrots" and "200g chicken." This input is used as additional condition data for recipe search. The input data is the names of ingredients and their quantities, and the output is the display of a confirmation screen.

[1064] Step 3:

[1065] The terminal sends the entered data to the server. When the user clicks the "Confirm" button on the confirmation screen, the user ID, selection criteria, ingredients, and their quantities are sent to the server. The input data is what the user entered when clicking the confirm button, and the output is the data sent to the server.

[1066] Step 4:

[1067] The server searches the database based on the data it receives. The server finds recipes that match the criteria "baby food," "carrots," and "chicken." The search algorithm selects the recipe that best fits the criteria specified by the user. The input data is the user's criteria and ingredient information sent, and the output is a list of matching recipes.

[1068] Step 5:

[1069] The server selects recommended recipes from the search results and sends the data to the device. In this case, recipes such as "carrot and chicken puree" and "chicken and carrot stew" are selected. The input data is the list of search results, and the output is the data sent to the user's device.

[1070] Step 6:

[1071] The device receives the data from the server and displays recommended recipes to the user. The user can select any recipe from the recipes presented on the screen. The input data is the recipe data received from the server, and the output is the recipe display to the user.

[1072] Step 7:

[1073] The user selects any recipe from the presented recipes. For example, if the user selects "carrot and chicken puree," detailed information about the recipe is displayed. The user's selection action is the input data, and the output is the display of detailed recipe information.

[1074] Step 8:

[1075] The server stores the user's selected recipe data. The user ID and selected recipe ID are recorded, and this data is used in an algorithm to learn the user's preferences. The input data is the user's selected action and the recipe ID, and the output is the storage of the selected data.

[1076] Step 9:

[1077] The server applies a machine learning algorithm to learn user preferences based on the stored data. The learning results are reflected in the selection of recommended recipes from the next time onwards, enabling the system to suggest recipes that are best suited to the user. The input data is the stored selection data, and the output is an updated recipe suggestion algorithm.

[1078] Through these steps, users can efficiently find recipes that suit their requirements and preferences, and the system can continue to improve its suggestions for future recipes.

[1079] (Application example 1)

[1080] 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."

[1081] Conventional recipe suggestion systems can suggest appropriate recipes based on a user's conditions and preferences, but they do not support ingredient delivery, which means users have to go through the trouble of obtaining the ingredients. Furthermore, while they have a mechanism for learning user preferences to reflect the results of that learning in selecting recommended recipes for the next time and beyond, they are unable to utilize this information in actual purchasing behavior or inventory management. The present invention aims to solve these problems and improve user convenience by enabling users to efficiently find recipes that meet their requirements and manage the delivery of those ingredients all in one place.

[1082] 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.

[1083] In this invention, the server includes means for allowing a user to select conditions and input and register the ingredients and their quantities to be purchased, means for receiving the input data and searching a database for recipes that match the conditions, means for displaying the searched recipes as recommendations to the user, means for saving a recipe selected by the user from the displayed recipes and learning the user's preferences, means for reflecting the learned user preferences in the selection of recommended recipes from the next time onwards, means for generating a list of necessary ingredients and ordering the ingredients, and means for managing the delivery of the ingredients. This allows a user to easily select a recipe that meets the conditions and order the ingredients for delivery all at once.

[1084] "Conditions" refer to specific requirements or constraints that a user specifies when receiving recipe suggestions.

[1085] "Ingredients" refers to the raw materials needed to create a dish or recipe.

[1086] "Quantity" refers to numerical information that indicates the specific quantity or weight of ingredients.

[1087] "Database" refers to a collection of information for efficiently managing, searching, and updating structured data.

[1088] A "recipe" refers to a document or data that contains instructions and a list of ingredients for creating a dish.

[1089] "Recommended" indicates candidates that are particularly recommended to the user based on specific conditions.

[1090] "Preferences" refer to the preferences or biases selected by a user based on specific conditions or criteria.

[1091] "Learning" refers to the process of analyzing and analysing a user's past behaviour and choices and reflecting this in future suggestions.

[1092] "Ingredient list" refers to a list of the names and amounts of ingredients required based on a recipe.

[1093] "Ordering" refers to the act of requesting the necessary ingredients from a specific delivery service.

[1094] "Delivery" refers to the service of delivering ordered ingredients to a specified location.

[1095] "Means" refers to a method or device used to achieve a particular purpose.

[1096] The present invention provides a system that enables a user to efficiently find a recipe that meets their own conditions and preferences, and to order delivery of the ingredients they need based on that recipe.

[1097] First, the user launches the application on a device such as a smartphone, smart glasses, or head-mounted display, and then uses the interface displayed on the screen to input specific conditions (e.g., baby food, vegetarian food), the ingredients purchased, and their quantities. The input data is then stored in a cloud database (e.g., Firebase) in real time.

[1098] The data recorded in the cloud database is sent to a server. The server receives the user's input data and searches the database for recipes that match the specified criteria. This search process uses a database management system and a recipe search API. For example, a search can be made for recipes in "baby food" that use "300g of carrots" and "200g of chicken."

[1099] From the search results, a generative AI model (e.g., TensorFlow) is used to select the recipe that best suits the user's criteria. The selected recipe is sent to the user's device and displayed as a recommendation on the screen.

[1100] When a user selects a recipe from the recommended recipes, detailed information about that recipe (ingredients, cooking method, cooking time, etc.) is displayed. The information about the selected recipe is saved on the server and accumulated as user preference data. Based on this preference data, a machine learning algorithm (e.g., PyTorch) is used to learn the user's preference patterns and reflect them in future recipe suggestions.

[1101] Next, a list of ingredients is generated based on the selected recipe, and an order for delivery of the ingredients is placed using an API corresponding to the delivery service (e.g., Uber Eats, DoorDash, etc.) The generation of the ingredient list and the transmission of the delivery order are carried out on the server side, and the order is transmitted to the corresponding delivery company.

[1102] For example:

[1103] For example, if a user starts an application to make baby food, selects "baby food," and then enters "300g of carrots" and "200g of chicken," the server will search the database for baby food recipes that use "carrots" and "chicken," and generate recommended recipes such as "carrot and chicken puree" and "chicken and carrot stew." When the user selects "carrot and chicken puree," details of that recipe are displayed on the device. At the same time, the server saves the user's selection history and reflects it in the next recipe suggestion.

[1104] An example prompt would be:

[1105] "User selects baby food and enters 300g of carrots and 200g of chicken."

[1106] In this way, the present invention provides consistent support from the process of users finding a recipe that meets their requirements to purchasing and delivering the necessary ingredients, thereby greatly improving user convenience.

[1107] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1108] Step 1:

[1109] The user launches the application on their device and the condition selection interface is displayed. The user enters the conditions, ingredients, and their quantities, and sends this data to the device. The entered data is saved in real time to a cloud database (Firebase). This registers the user-specified conditions and ingredient information in the database.

[1110] Input: Condition (e.g., baby food), ingredients (e.g., 300g carrots, 200g chicken)

[1111] Output: Data stored in a cloud database

[1112] Specific behavior:

[1113] The user enters "Condition: Baby food," "Ingredients: 300g carrots," and "Ingredients: 200g chicken," and clicks the "Save" button.

[1114] Step 2:

[1115] The device sends the input data to the server. The server receives this data and searches the database for recipes that meet the criteria. This search uses a recipe search API or database management system. As a result, the server extracts and selects multiple recipes that meet the criteria.

[1116] Input: User data retrieved from a cloud database

[1117] Output: A list of recipes that match the criteria

[1118] Specific behavior:

[1119] The server searches for recipe data containing "baby food," "carrots," and "chicken," and extracts candidates such as "carrot and chicken puree" and "chicken and carrot stew."

[1120] Step 3:

[1121] The server uses a generative AI model (TensorFlow) to select the recipe that best suits the user's requirements. The selected recipe data is sent to the device and displayed as a recommendation on the user's screen.

[1122] Input: Multiple recipes that meet the criteria

[1123] Output: One or more recommended recipes

[1124] Specific behavior:

[1125] The server evaluates recipes using the generative AI model and sends the best candidates as "recommendations" to the device, which then displays "Recommended Recipe: Carrot and Chicken Puree."

[1126] Step 4:

[1127] The user selects any recipe from the recommended recipes and the details of that recipe (ingredients, cooking method, cooking time, etc.) are displayed. The selected recipe information is sent to the server and saved as the user's preference data.

[1128] Input: User selected recipe

[1129] Output: Display details of selected recipe, save preference data to server

[1130] Specific behavior:

[1131] When the user selects "Carrot and Chicken Puree," its detailed information is displayed on the screen. At the same time, the "User ID" and "Recipe ID" are saved on the server.

[1132] Step 5:

[1133] The server uses a machine learning algorithm (PyTorch) to learn the user's preference patterns and reflect them in future recipe suggestions. This learning process improves the accuracy of recipe suggestions based on the user's preferences.

[1134] Input: User preference data

[1135] Output: Updated user preference data pattern

[1136] Specific behavior:

[1137] The server analyzes the recipes the user has previously selected to reflect this in the next recipe suggestions.

[1138] Step 6:

[1139] The server generates a list of ingredients based on the selected recipe and sends the order to the partner delivery service API.

[1140] Input: A list of ingredients for the selected recipe

[1141] Output: Delivery order sent

[1142] Specific behavior:

[1143] The server generates an ingredient list of "300g of carrots" and "200g of chicken" and sends it to the delivery service API.

[1144] Step 7:

[1145] The delivery company receives the list of ingredients, prepares them, and delivers them to the specified address. The user can then pick up the ordered ingredients and create the dish according to the recipe.

[1146] Input: Delivery Order

[1147] Output: Food delivery to the specified address

[1148] Specific behavior:

[1149] The delivery company prepares the order and delivers 300g of carrots and 200g of chicken to the user's address.

[1150] 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.

[1151] The present invention is a system that allows users to efficiently find recipes that suit their own conditions and preferences, and further learns their preferences and feelings and reflects them in future recipe suggestions.

[1152] Program processing

[1153] 1. Select conditions and register ingredients

[1154] Terminal: The user launches applications and web services.

[1155] Device: A UI for selecting conditions is displayed on the screen. The user is presented with options such as "baby food," "nursing care food," and "allergy-friendly food."

[1156] User: Select a condition. For example, select "baby food."

[1157] Terminal: Records the conditions (baby food) selected by the user.

[1158] 2. Enter ingredients and emotions

[1159] Terminal: Displays an input form that allows the user to input the ingredients purchased and the amount, and also displays an interface for inputting or measuring the user's emotions.

[1160] User: Enter the ingredients purchased, their quantities, and their current emotions. For example, they can enter "300g of carrots," "200g of chicken," and "satisfied."

[1161] Terminal: A screen to confirm the input information is displayed, and the user clicks the confirmation button.

[1162] Terminal: Sends the user's input data (conditions, ingredients, emotions) to the server.

[1163] 3. Creating and displaying recipes

[1164] Server: Receives user input data, including the user ID, selection criteria, ingredients and their amounts, and emotions.

[1165] Server: Searches for recipes that match the criteria from the database based on the received data and past data. It also uses an emotion engine to select recipes that correspond to the user's emotions.

[1166] Server: Generates a list of recipes that match the criteria and are emotionally appropriate. For example, it might select "carrot and chicken puree" or "chicken and carrot stew."

[1167] Server: Sends the generated recipe list to the terminal.

[1168] Device: Recommended recipes are displayed to the user.

[1169] 4. Select a recipe and view details

[1170] User: Select a recipe from the suggested recipes. For example, select "Carrot and Chicken Puree."

[1171] On your device: View detailed information about the selected recipe, including specific ingredients, cooking instructions, and cooking times.

[1172] 5. Learning user preferences and emotions

[1173] Server: Stores the recipe data selected by the user and the emotion data at that time. The stored information includes the user ID, the selected recipe ID, and the emotion data.

[1174] Server: Applies algorithms to learn user preferences and emotions, which analyzes user behavior patterns, preferences, and emotions.

[1175] Server: Updates the system to reflect the learning results in future recipe suggestions. This ensures that when the user uses the system again, it will suggest recipes that better match their preferences and emotions.

[1176] Specific examples

[1177] For example, suppose User A launches an application to make baby food, selects "baby food," and then enters "300g carrots," "200g chicken," and "satisfied." In this case, the server searches the database for baby food recipes that use "carrots" and "chicken," and selects a recipe that matches the user's emotion of "satisfied." It generates recommended recipes such as "carrot and chicken puree" and "chicken and carrot stew" and sends them to the device. When the user selects "carrot and chicken puree," details of that recipe are displayed on the device. At the same time, the server saves the user's selection history and emotion data and reflects them in the next recipe suggestions. This ensures that recipes that match the user's preferences and emotions are provided each time the application is used.

[1178] The processing flow will be explained below.

[1179] Step 1:

[1180] Terminal: The user launches applications and web services.

[1181] Terminal: A UI for selecting conditions is displayed on the screen, and the user is presented with options such as "baby food," "nursing care food," and "allergy-friendly food."

[1182] Step 2:

[1183] User: Select a condition. For example, select "baby food."

[1184] Terminal: Records the conditions (baby food) selected by the user.

[1185] Step 3:

[1186] Terminal: Displays the screen for inputting ingredients and emotions. An interface is provided for the user to input the ingredients purchased, their quantities, and their current emotions.

[1187] User: Enter the ingredients purchased, their quantities, and their current emotions. For example, enter "300g of carrots," "200g of chicken," and "Satisfied."

[1188] Step 4:

[1189] Terminal: A screen to confirm the input information is displayed, and the user clicks the confirmation button.

[1190] Terminal: Sends the user's input data (conditions, ingredients, emotions) to the server.

[1191] Step 5:

[1192] Server: Receives the user's input data, including the user ID, selection criteria, ingredients, and emotions.

[1193] Step 6:

[1194] Server: Based on the input data and past data, the server searches the database for recipes that match the conditions, and uses an emotion engine to select a recipe that suits the user's emotions.

[1195] For example, if a user enters "satisfied," recipes chosen with similar emotions or highly rated recipes will be prioritized.

[1196] Step 7:

[1197] Server: Generates a list of recommended recipes that match the conditions and emotions.

[1198] For example, select "carrot and chicken puree" or "chicken and carrot stew."

[1199] Server: Sends the generated recipe list to the terminal.

[1200] Step 8:

[1201] Device: Recommended recipes received from the server are displayed to the user. Recipe names and summaries are displayed in a list.

[1202] Step 9:

[1203] User: Select your preferred recipe from the recommended recipes displayed.

[1204] For example, select "Carrot and Chicken Puree."

[1205] On your device: Detailed information about the selected recipe will be displayed, including specific ingredients, cooking instructions, and cooking time.

[1206] Step 10:

[1207] Server: Stores the data of the recipe selected by the user and the emotion data at that time.

[1208] The information stored includes the user ID, the selected recipe ID, and emotion data.

[1209] Step 11:

[1210] Server: Applies algorithms to learn user preferences and emotions.

[1211] User behavior patterns, preferences, and emotions are analyzed.

[1212] Step 12:

[1213] Server: Updates the system to reflect the learning results in future recipe suggestions.

[1214] This means that when a user uses the system again, recipes that better match their preferences and emotions will be suggested.

[1215] Example 2

[1216] 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."

[1217] Conventional recipe suggestion systems were able to provide recipes that matched the user's conditions and ingredients, but it was difficult to learn the user's emotions and preferences and reflect them in future suggestions. Furthermore, because they were unable to take into account the ingredients purchased by the user or their emotions, the accuracy of suggesting the optimal recipe for the user was low. This led to users being dissatisfied with the recipe selection, resulting in a decrease in the frequency of system use.

[1218] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1219] In this invention, the server includes means for allowing a user to select conditions and input and register purchased ingredients and their quantities, means for receiving the input data and searching a database for recipes that match the conditions, means for using an emotion engine to select a recipe according to emotions based on the received data and past data, means for displaying the searched recipes as recommendations to the user, means for saving a recipe selected by the user from the displayed recipes and learning the user's preferences and emotions, and means for reflecting the learned user preferences and emotions in the selection of recommended recipes from the next time onwards. This makes it possible to propose optimal recipes based on the user's conditions, ingredients, and emotions.

[1220] "Conditions" are user-selected constraints or requirements, including, for example, types of food and health restrictions.

[1221] "Ingredients" refer to the foods and ingredients used in a dish or recipe, and specifically include vegetables, meat, seasonings, etc.

[1222] "Quantity" is a numerical value indicating the quantity or weight of a material that the user has purchased or possesses.

[1223] A "database" is a collection of information that structures and stores user conditions, ingredients, and recipe information.

[1224] "Search" is the operation of searching a database for information that matches specified conditions.

[1225] A "prescription" is information that indicates a recipe or cooking method for a dish.

[1226] "Emotion" indicates the user's current psychological state, and is information such as "satisfied" or "dissatisfied," for example.

[1227] An "emotion engine" is an algorithm or system that selects the optimal prescription based on the user's emotions.

[1228] "Display" refers to the operation of visually showing prescription information and recommended recipes on the user's device.

[1229] "Preferences" indicate a user's tendency to prefer particular recipes or ingredients.

[1230] "Learning" is an information analysis process that uses user preferences and emotional data to reflect in future recipe suggestions.

[1231] A "system" is a set of mechanisms that combine multiple means and technologies to provide services to users.

[1232] MODE FOR CARRYING OUT THE INVENTION

[1233] This invention is a system that allows users to efficiently find recipes that suit their own conditions and preferences, and also learns their preferences and feelings and reflects them in future recipe suggestions.

[1234] System Overview

[1235] This system includes means for a user to select conditions and input and register purchased materials and their quantities, means for receiving the input data and searching a database for recipes that match the conditions, means for using an emotion engine to select a recipe according to emotions based on the received data and past data, means for displaying the searched recipes as recommendations to the user, means for saving a recipe selected by the user from the displayed recipes and learning the user's preferences and emotions, and means for reflecting the learned user preferences and emotions in the selection of recommended recipes from the next time onwards.

[1236] Hardware and Software Configuration

[1237] 1. Terminal: A device used by a user to access an application or web service, including a smartphone, tablet, or PC.

[1238] 2. Server: This is the central system that receives and processes input data from users. It includes a database server, machine learning engine, and emotion engine.

[1239] 3. Software:

[1240] User interface: A UI on an application or web browser that provides an interface for selecting conditions and inputting materials.

[1241] Database system: A database (e.g., SQL database) for storing and managing entered user and prescription data.

[1242] Emotion engine: An algorithm for analyzing user emotions and suggesting appropriate prescriptions based on them.

[1243] Machine learning algorithms: Recommendation systems that learn user preferences and history and reflect this in future recommendations.

[1244] Specific examples

[1245] For example, suppose User A launches the application, selects "baby food," and then enters "300g carrots," "200g chicken," and "satisfied." In this case, the server searches the database for baby food recipes that use "carrots" and "chicken," and selects a recipe that corresponds to the user's emotion of "satisfied." As a result, recommended recipes such as "carrot and chicken puree" and "chicken and carrot stew" are generated and sent to the device. When the user selects "carrot and chicken puree," details of the selection are displayed on the device. At the same time, the server saves the user's selection history and emotion data, and can reflect this in the next recipe suggestions. This allows the server to provide recipes that match the user's preferences and emotions each time the application is used.

[1246] Prompt Sentence Examples

[1247] By inputting the following prompt sentence into the generative AI model, a description of the above system can be generated in natural language.

[1248] "Users input conditions, ingredients, and emotions through an application or web service, and the AI ​​model uses a database and emotion engine to generate natural-sounding sentences that explain the system and suggest prescriptions that match the conditions and are appropriate for the emotions."

[1249] The prompts enable the generative AI model to generate detailed natural language descriptions of the system's functions and procedures.

[1250] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1251] Step 1:

[1252] Terminal: When a user launches an application or web service, the home screen appears.

[1253] Input: Application launch by user action

[1254] Output: Display of the home screen of the application or web service

[1255] Specific actions: Tap an icon on your smartphone to launch an app, or enter a URL in a web browser.

[1256] Step 2:

[1257] Terminal: A user interface (UI) for selecting conditions is displayed on the screen. The user is presented with options such as "baby food," "nursing care food," and "allergy-friendly food."

[1258] Input: The application initialization process calls the criteria selection UI

[1259] Output: Display of a screen where the user can select conditions

[1260] Specific operation: A screen will appear where you can select conditions using a drop-down menu or radio buttons.

[1261] Step 3:

[1262] User: Select a condition and click the Next button. For example, select "baby food."

[1263] Input: User selection of conditions

[1264] Output: Record of selected conditions and transition to the next input screen

[1265] Specific actions: Select with a mouse click or touch gesture and press the "Next" button.

[1266] Step 4:

[1267] Terminal: Displays a form that allows the user to input the ingredients and their quantities purchased, and also displays an interface for inputting or measuring the user's emotions.

[1268] Input: System response to condition selection

[1269] Output: Display of material and emotion input form

[1270] Specific operation: A section for entering ingredients and their quantities using text boxes or voice input, as well as a slider or button for entering emotions, will be displayed.

[1271] Step 5:

[1272] User: Enter the ingredients purchased (e.g., "300g carrots" and "200g chicken") and their current feelings (e.g., "Satisfied").

[1273] Input: User input of materials and emotions

[1274] Output: Display of input confirmation screen

[1275] Specific actions: Enter text or use voice recognition to enter material information, then drag the emotion slider to the appropriate value.

[1276] Step 6:

[1277] Terminal: A screen is displayed to confirm the input and the user is asked to click a confirmation button.

[1278] Input: Material and emotional input data

[1279] Output: Display confirmation screen

[1280] Specific operation: Displays the input data and displays a button to ask the user for confirmation.

[1281] Step 7:

[1282] User: Click the Verify button to verify that the data is correct.

[1283] Input: User clicks confirmation button

[1284] Output: Confirmed data transmission process

[1285] Specific operation: Press the confirmation button to confirm the input.

[1286] Step 8:

[1287] Terminal: Sends the user's input data (conditions, materials, emotions) to the server.

[1288] Input: Confirmed data

[1289] Output: Send data to the server

[1290] Specific operation: Executes an API call to send data to a server over the network.

[1291] Step 9:

[1292] Server: Receives input data sent by the user, searches the database for prescriptions that match the conditions, and uses an emotion engine to select a prescription that corresponds to the user's emotion.

[1293] Input: Input data sent from the terminal

[1294] Output: A list of prescriptions that match the criteria and are emotionally appropriate

[1295] Specific operation: Executes an SQL query to extract relevant prescriptions from the database and filters them using the emotion engine.

[1296] Step 10:

[1297] Server: Generates a list of recipes that match the conditions and are emotionally appropriate. For example, it might select "carrot and chicken puree" or "stewed chicken and carrots."

[1298] Input: Searched and filtered prescription data

[1299] Output: Generate a prescription list

[1300] Specific operation: Generate a list based on the filtered prescription data.

[1301] Step 11:

[1302] Server: Sends the generated prescription list to the user's terminal.

[1303] Input: Generated prescription list

[1304] Output: Send prescription list to terminal

[1305] Specific operation: Executes an API call to send a prescription list to the terminal via the network.

[1306] Step 12:

[1307] Device: Recommended recipes are displayed to the user.

[1308] Input: Prescription list sent from the server

[1309] Output: Display recommended recipes

[1310] Specific operation: Recipes appear on the screen in a list format using a design template.

[1311] Step 13:

[1312] User: Select a recipe from the suggested recipes. For example, select "Carrot and Chicken Puree."

[1313] Input: User selection of recipe

[1314] Output: Display detailed information about the selected recipe

[1315] Action: Tap or click to select a recipe from the list.

[1316] Step 14:

[1317] On your device: View detailed information about the selected recipe, including specific ingredients, cooking instructions, and cooking times.

[1318] Input: Recipe data selected by the user

[1319] Output: Display detailed recipe information

[1320] What Happens: A detailed view of the recipe appears, showing the ingredients list and steps in a scrollable format.

[1321] Step 15:

[1322] Server: Stores the data of the recipe selected by the user and the emotion data at that time.

[1323] Input: Recipe data and emotion data selected by the user

[1324] Output: Saved user data

[1325] Specific action: It is recorded as a new record in the database.

[1326] Step 16:

[1327] Server: Applies algorithms to learn user preferences and emotions, which analyzes user behavior patterns, preferences, and emotions.

[1328] Input: Stored user preference and emotion data

[1329] Output: Training data as analysis results

[1330] Specific actions: Run machine learning algorithms (e.g., recommendation systems) to analyze data.

[1331] Step 17:

[1332] Server: Updates the system to reflect the learning results in future recipe suggestions. This ensures that when the user uses the system again, it will suggest recipes that better match their preferences and emotions.

[1333] Input: Parsed training data

[1334] Output: Proposed features of the updated system

[1335] Specific operation: The proposed algorithm is updated based on the training data.

[1336] (Application example 2)

[1337] 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."

[1338] Conventional recipe suggestion systems were able to provide recipes that took into account the user's conditions and preferences, but they were unable to suggest recipes that reflected the user's emotions. As a result, suggestions that improved the user's emotional satisfaction and experience were insufficient. Furthermore, if a user's recipe preferences differed depending on a specific emotion, this was not recorded or learned, and could not be reflected in future suggestions. Therefore, the goal of this project is to further improve user satisfaction by providing a recipe suggestion system that also takes into account the user's emotions.

[1339] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1340] In this invention, the server includes a means for a user to select conditions and input and register purchased ingredients and their quantities, a means for receiving the input data and the user's emotional data, and a means for searching a database for recipes that match the conditions, and a means for displaying the searched recipes as recommendations to the user, thereby enabling recipe suggestions based on the user's emotions in addition to their conditions and preferences.

[1341] "User" means an individual or organization that uses the system.

[1342] "Conditions" are parameters that a user sets to search for a particular recipe.

[1343] "Ingredients" refers to the types and amounts of food used to prepare a recipe.

[1344] "Emotion data" is information that indicates the user's emotional state, and is data that the system receives to use in proposing recipes.

[1345] A "database" is a structured collection of information that stores recipe information and facilitates retrieval.

[1346] The "search means" is a software function that searches the database for recipes that meet the user's requirements.

[1347] The "displaying means" is an interface for displaying the selected recipe on the user's device.

[1348] The "storage means" is a system that records the user's selected recipes and emotional data for future reference and learning.

[1349] The "learning means" is an algorithm that analyzes stored user preference and emotion data and reflects that in future suggestions.

[1350] "Server" means a central management system for receiving, processing, and storing data.

[1351] This invention is a system that allows users to input ingredients and their quantities via a smartphone application or web interface, and suggests recipes that suit their preferences and conditions. This includes a means for users to select conditions, input purchased ingredients and emotional data, and provide recipes based on those.

[1352] System configuration and usage

[1353] 1. User selection of conditions and input of ingredients

[1354] The user launches the application and selects criteria such as "baby food," "caregiver food," and "allergy-friendly food" from their smartphone or computer terminal.

[1355] After selecting these conditions, the user inputs the type and quantity of ingredients purchased, as well as emotional data (such as "satisfied" or "sad").

[1356] 2. Data Receipt and Processing by the Server

[1357] The conditions, ingredients, and emotion data entered by the user are sent to the server, which receives this data and searches a database for recipes that match the ingredients and conditions.

[1358] The server uses an emotion engine, such as a TensorFlow-based emotion analysis model, to select recipes that match the user's emotional state based on the received emotion data.

[1359] 3. Creating and displaying recipes

[1360] The searched recipes are displayed as recommendations on the user's device. Recipe information includes the ingredients needed, cooking steps, cooking time, etc.

[1361] When the user selects a recipe from the ones presented, more detailed information about that recipe is displayed.

[1362] 4. Learning and storing user preference and emotion data

[1363] The server records the recipe selected by the user and their emotional state at the time. This data is used to make future recommendations.

[1364] It applies algorithms to learn user preferences and emotional data, analyzing user behavior patterns and preferences, so that future recipe suggestions are more tailored to the user's needs and emotions.

[1365] Hardware and software used

[1366] Hardware: Servers (e.g., Amazon EC2), user devices (smartphones, PCs, etc.)

[1367] Software: Flask (a web framework written in Python), SQLite (a local database), TensorFlow (a machine learning library for sentiment analysis)

[1368] Examples and prompts

[1369] For example, suppose User A starts an application to make baby food, selects "baby food," and then inputs "300g carrots," "200g chicken," and "satisfied." In this case, the server searches the database for baby food recipes that use "carrots" and "chicken," and selects a recipe that matches the user's emotion of "satisfied." Suggested recipes include "carrot and chicken puree" and "chicken and carrot stew."

[1370] Here is an example prompt:

[1371] Let's say a user selects "baby food" as a condition, and inputs "300g carrots," "200g chicken," and the emotion "satisfied." In this case, we'll suggest the following recipes:

[1372] 1. Carrot and chicken puree

[1373] 2. Chicken and carrot stew

[1374] By inputting this prompt into a generative AI model, recipes that match the user's conditions and emotions can be efficiently generated and suggested.

[1375] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1376] Step 1:

[1377] The user launches the application and selects conditions on a smartphone or computer. Specifically, options such as "baby food," "nursing care food," and "allergy-friendly food" are displayed, and the user selects one. The input data is sent to the server in the form of condition selection.

[1378] Step 2:

[1379] Based on the selected criteria, the user inputs the ingredients purchased, their quantities, and emotional data, such as "300g of carrots," "200g of chicken," and "satisfied." This data is also sent from the device to the server.

[1380] Step 3:

[1381] The server processes the received conditions, ingredient data, and emotion data. It then searches the database for recipes that match the conditions based on the type and amount of ingredients. It also takes into account the input emotion data and uses an emotion analysis model such as TensorFlow to select recipes that suit the emotion.

[1382] Step 4:

[1383] Based on the results of the search and sentiment analysis, the system generates recipe recommendations for the user. These recipes include, for example, "carrot and chicken puree" and "chicken and carrot stew." This list is sent to the user's device as recipe information and displayed on the screen.

[1384] Step 5:

[1385] The user selects a recipe from the list of recipes presented, and detailed information about the selected recipe (ingredients, cooking steps, cooking time, etc.) is displayed.

[1386] Step 6:

[1387] The server stores the recipe selected by the user and the emotion data at that time. The saved data is recorded along with the user ID and will be used for future recipe suggestions.

[1388] Step 7:

[1389] The server analyzes the stored data and applies algorithms that learn the user's preferences and emotions, allowing it to better tailor future recipe suggestions to the user's behavioral patterns, tastes, and emotions.

[1390] Specific explanation of processing operations

[1391] Step 1:

[1392] Input data: User selection of conditions (e.g., "baby food")

[1393] Output data: Criteria selection data sent to the server

[1394] How it works: A user launches the application and selects criteria on their smartphone or computer.

[1395] Step 2:

[1396] Input data: Food ingredient data and emotion data (e.g., "300g carrots," "200g chicken," "satisfied")

[1397] Output data: Ingredient data and emotion data sent to the server

[1398] How it works: Based on the selected criteria, the user inputs the ingredients purchased, their quantities, and emotional data.

[1399] Step 3:

[1400] Input data: condition data, ingredient data, emotion data

[1401] Output data: Recipe search results and sentiment analysis results

[1402] How it works: The server processes the received data, searches the database for recipes that match the criteria, and uses a sentiment analysis model to select an appropriate recipe.

[1403] Step 4:

[1404] Input data: Recipe search results and sentiment analysis results

[1405] Output data: A list of recipes recommended for the user

[1406] Operation: The server generates recommended recipes based on the search and analysis results, sends them to the user's device, and displays them on the screen.

[1407] Step 5:

[1408] Input data: User selected recipe

[1409] Output data: Detailed information about the selected recipe

[1410] How it works: The user selects a recipe from the ones presented and its details are displayed.

[1411] Step 6:

[1412] Input data: Selected recipes and sentiment data

[1413] Output data: Selection history and emotion data stored on the server

[1414] Operation: The server stores the recipe selected by the user and the emotion data at that time.

[1415] Step 7:

[1416] Input data: saved selection history and emotion data

[1417] Output data: Recipe suggestions for the next time and beyond that reflect the user's behavioral patterns, preferences, and emotions

[1418] How it works: The server analyzes the stored data and applies algorithms that learn the user's preferences and emotions to improve future recipe suggestions.

[1419] 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.

[1420] 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.

[1421] 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.

[1422] [Fourth embodiment]

[1423] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1424] 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.

[1425] 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).

[1426] 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.

[1427] 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.

[1428] 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).

[1429] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1430] 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.

[1431] 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.

[1432] 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.

[1433] 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.

[1434] 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.

[1435] 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."

[1436] The present invention is a system that allows a user to efficiently find recipes that suit their own conditions and preferences, and reflects this in future recipe suggestions.

[1437] Program processing

[1438] 1. Select conditions and register ingredients

[1439] Terminal: The user launches applications and web services.

[1440] Device: A UI for selecting conditions is displayed on the screen. The user selects conditions such as baby food or nursing care food.

[1441] User: Selects conditions and enters purchased ingredients and their quantities.

[1442] For example, select "baby food" and enter "300g carrots" and "200g chicken."

[1443] Terminal: A screen to confirm the input information is displayed, and the user clicks the confirmation button.

[1444] Terminal: The entered data is sent to the server.

[1445] The transmitted information includes the user ID, selection criteria, ingredients and their quantities.

[1446] 2. Creating and displaying recipes

[1447] Server: Receives the user's input data.

[1448] Server: Searches the database for recipes that match the criteria.

[1449] For example, search for baby food recipes that use carrots and chicken.

[1450] Server: Select several recommended recipes from the search results.

[1451] For example: "Carrot and chicken puree", "Chicken and carrot stew", etc.

[1452] Server: Sends the selected recipe data to the terminal.

[1453] Device: Recommended recipes are displayed to the user.

[1454] 3. Select a recipe and view details

[1455] User: Select any recipe from the recommended recipes presented.

[1456] For example, select "Carrot and Chicken Puree."

[1457] On your device: Displays detailed information about the selected recipe, including specific ingredients, instructions, cooking time, etc.

[1458] 4. Learning User Preferences

[1459] Server: Stores the data of the recipe selected by the user.

[1460] The information saved is the user ID and the selected recipe ID.

[1461] Server: Applies algorithms to learn user preferences.

[1462] This allows the user's behavioral patterns and preferences to be analyzed.

[1463] Server: Updates the system to reflect the learning results in future recipe suggestions.

[1464] Specific examples

[1465] For example, suppose User A launches an application to make baby food, selects "baby food," and then enters "300g of carrots" and "200g of chicken." In this case, the server searches the database for baby food recipes that use "carrots" and "chicken," and generates recommended recipes such as "carrot and chicken puree" and "chicken and carrot stew." When the user selects "carrot and chicken puree," details of that recipe are displayed on the device. At the same time, the server saves the user's selection history and reflects it in the next recipe suggestion. This ensures that recipes that suit the user's preferences are provided each time the application is used.

[1466] The processing flow will be explained below.

[1467] Step 1:

[1468] Terminal: The user launches applications and web services.

[1469] Device: A UI for selecting conditions is displayed on the screen. The user is presented with options such as "baby food," "nursing care food," and "allergy-friendly food."

[1470] Step 2:

[1471] User: Select a condition. For example, select "baby food."

[1472] Terminal: Records the conditions (baby food) selected by the user.

[1473] Step 3:

[1474] Terminal: Displays an input form where the user can enter the ingredients and quantities purchased.

[1475] User: Enter the ingredients purchased and their quantities. For example, enter "300g carrots" and "200g chicken."

[1476] Step 4:

[1477] Terminal: A screen to confirm the input is displayed. After the user confirms the input, they click the confirmation button.

[1478] Terminal: Sends the user's input data (conditions and ingredients) to the server.

[1479] Step 5:

[1480] Server: Receives user input data, including the user ID, selection criteria, ingredients, and their quantities.

[1481] Server: Searches the database for recipes that match the conditions based on the received data.

[1482] Step 6:

[1483] Server: Generates a list of recipes that match the criteria. For example, it might select "carrot and chicken puree" or "chicken and carrot stew."

[1484] Server: Sends the generated recipe list to the terminal.

[1485] Step 7:

[1486] Device: Recommended recipes received from the server are displayed to the user. Recipe names and summaries are displayed in a list.

[1487] Step 8:

[1488] User: Select your preferred recipe from the recommended recipes displayed. For example, select "Carrot and Chicken Puree."

[1489] On your device: View detailed information about the selected recipe, including specific ingredients, cooking instructions, and cooking times.

[1490] Step 9:

[1491] Server: Stores the data of the recipe selected by the user. The stored information includes the user ID and the selected recipe ID.

[1492] Server: Applies algorithms to learn user preferences, which analyzes user behavior patterns and preferences.

[1493] Step 10:

[1494] Server: Updates the system to reflect the learning results in future recipe suggestions. This will enable the system to suggest recipes that better match the user's preferences when the user uses the system again.

[1495] Example 1

[1496] 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."

[1497] Conventional recipe suggestion systems have difficulty efficiently finding recipes that match the conditions and ingredients entered by the user, and lack the functionality to provide recipes that reflect the user's preferences in future recipes. For these reasons, there is a need to improve the user experience.

[1498] 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.

[1499] In this invention, the server includes means for a user to select conditions and input and register purchased ingredients and their quantities, means for receiving the input data and searching a database for recipes that match the conditions, means for displaying the searched recipes as recommendations to the user, means for saving the recipes selected by the user and learning the user's preferences, means for reflecting the learned user preferences in the selection of recommended recipes from the next time onwards, and means for displaying a corresponding interface when the user selects conditions. This allows the user to efficiently find recipes that match their conditions and preferences, and enables the system to reflect recipe suggestions that match the user's preferences from the next time onwards.

[1500] "User" refers to a person who uses a system or application.

[1501] "Conditions" refer to recipe categories and requirements that users specify to the system, such as baby food and nursing care food.

[1502] "Ingredients" refers to raw materials purchased by users and used to create recipes, such as carrots and chicken.

[1503] "Input" refers to the act of a user providing information to a system using a device such as a keyboard or touch panel.

[1504] "Registration means" refers to a function for recording data entered by a user and saving it within the system.

[1505] "Receiving means" refers to a function that allows the server to receive data sent from the user.

[1506] "Search means" refers to a function for searching a database for information that matches the conditions based on the received data.

[1507] A "database" refers to a system that organizes and stores large amounts of information, making it searchable and accessible as needed.

[1508] "Recommendation display means" refers to a function for suggesting information selected from search results to users.

[1509] "Storage means" refers to a function that records information selected by the user and saves it for later use.

[1510] "Learning means" refers to a function for analyzing stored information and learning user preferences and behavioral patterns.

[1511] "Reflection means" refers to the function of improving future suggestions based on the results of learning and providing them to users.

[1512] "Interface" refers to the screen and input devices that allow a user to interact with a system.

[1513] The present invention provides a system that allows a user to efficiently find recipes that suit their own conditions and preferences, and reflects these in future recipe suggestions. An embodiment of this system will be described in detail below.

[1514] When a user launches the smartphone application or web browser service, an initial screen appears. Here, the user can access the interface (UI) for setting the conditions for recipe suggestions. The UI provides options such as baby food and nursing care food.

[1515] When the user selects the conditions, an interface for inputting ingredients and their quantities is displayed on the screen. For example, the user can select "baby food" and input "300g of carrots" and "200g of chicken." This input data is displayed once on the confirmation screen on the device, and is sent to the server when the user clicks the confirm button.

[1516] The server receives the user's input data (user ID, selection criteria, ingredients and their quantities) and searches the database for recipes that match the criteria. Specifically, it searches for recipes that meet the criteria, for example, "baby food," "carrots," and "chicken." The server selects a recommended recipe from multiple matching recipes and sends that data to the device.

[1517] The device displays the recommended recipes received from the server on the user's screen. The user can select any recipe from the recommended recipes presented. For example, the user can select "carrot and chicken puree." Detailed information about the selected recipe (specific ingredients, cooking method, cooking time, etc.) is displayed on the device.

[1518] The data of the recipe selected by the user (user ID and selected recipe ID) is stored on the server. The server applies a machine learning algorithm to learn the user's preferences based on this data, analyzing the user's behavioral patterns and tastes. The learning results are updated in the system so that they are reflected in future recipe suggestions.

[1519] For example, if User A starts the application, selects "baby food," and enters "300g of carrots" and "200g of chicken," the server will search the database for baby food recipes that use "carrots" and "chicken," and recommend "carrot and chicken puree" or "chicken and carrot stew." If the user selects "carrot and chicken puree," its details are displayed. At the same time, the server records this selection and reflects it in the next recipe suggestion.

[1520] An example of a prompt sentence for the generative AI model is written as follows:

[1521] "I'd like to know what ingredients I have and what recipes I can use them in. For example, can you suggest a recipe that uses 300g of carrots and 200g of chicken?"

[1522] This system improves the user experience and provides the most suitable cooking method for each individual user by suggesting recipes that match the user's preferences. This process is carried out through cooperation between the server, terminals, and users.

[1523] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1524] Step 1:

[1525] The user launches an application or web service and the condition selection screen is displayed. The user selects conditions such as "baby food" or "care food." This input is used as initial condition data for the system to suggest appropriate recipes. The input data is the condition type, and the output is the display of the condition selection screen.

[1526] Step 2:

[1527] Based on the conditions selected by the user, a screen for inputting ingredients and their quantities is displayed on the terminal. Here, the user can input information such as "300g carrots" and "200g chicken." This input is used as additional condition data for recipe search. The input data is the names of ingredients and their quantities, and the output is the display of a confirmation screen.

[1528] Step 3:

[1529] The terminal sends the entered data to the server. When the user clicks the "Confirm" button on the confirmation screen, the user ID, selection criteria, ingredients, and their quantities are sent to the server. The input data is what the user entered when clicking the confirm button, and the output is the data sent to the server.

[1530] Step 4:

[1531] The server searches the database based on the data it receives. The server finds recipes that match the criteria "baby food," "carrots," and "chicken." The search algorithm selects the recipe that best fits the criteria specified by the user. The input data is the user's criteria and ingredient information sent, and the output is a list of matching recipes.

[1532] Step 5:

[1533] The server selects recommended recipes from the search results and sends the data to the device. In this case, recipes such as "carrot and chicken puree" and "chicken and carrot stew" are selected. The input data is the list of search results, and the output is the data sent to the user's device.

[1534] Step 6:

[1535] The device receives the data from the server and displays recommended recipes to the user. The user can select any recipe from the recipes presented on the screen. The input data is the recipe data received from the server, and the output is the recipe display to the user.

[1536] Step 7:

[1537] The user selects any recipe from the presented recipes. For example, if the user selects "carrot and chicken puree," detailed information about the recipe is displayed. The user's selection action is the input data, and the output is the display of detailed recipe information.

[1538] Step 8:

[1539] The server stores the user's selected recipe data. The user ID and selected recipe ID are recorded, and this data is used in an algorithm to learn the user's preferences. The input data is the user's selected action and the recipe ID, and the output is the storage of the selected data.

[1540] Step 9:

[1541] The server applies a machine learning algorithm to learn user preferences based on the stored data. The learning results are reflected in the selection of recommended recipes from the next time onwards, enabling the system to suggest recipes that are best suited to the user. The input data is the stored selection data, and the output is an updated recipe suggestion algorithm.

[1542] Through these steps, users can efficiently find recipes that suit their requirements and preferences, and the system can continue to improve its suggestions for future recipes.

[1543] (Application example 1)

[1544] 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."

[1545] Conventional recipe suggestion systems can suggest appropriate recipes based on a user's conditions and preferences, but they do not support ingredient delivery, which means users have to go through the trouble of obtaining the ingredients. Furthermore, while they have a mechanism for learning user preferences to reflect the results of that learning in selecting recommended recipes for the next time and beyond, they are unable to utilize this information in actual purchasing behavior or inventory management. The present invention aims to solve these problems and improve user convenience by enabling users to efficiently find recipes that meet their requirements and manage the delivery of those ingredients all in one place.

[1546] 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.

[1547] In this invention, the server includes means for allowing a user to select conditions and input and register the ingredients and their quantities to be purchased, means for receiving the input data and searching a database for recipes that match the conditions, means for displaying the searched recipes as recommendations to the user, means for saving a recipe selected by the user from the displayed recipes and learning the user's preferences, means for reflecting the learned user preferences in the selection of recommended recipes from the next time onwards, means for generating a list of necessary ingredients and ordering the ingredients, and means for managing the delivery of the ingredients. This allows a user to easily select a recipe that meets the conditions and order the ingredients for delivery all at once.

[1548] "Conditions" refer to specific requirements or constraints that a user specifies when receiving recipe suggestions.

[1549] "Ingredients" refers to the raw materials needed to create a dish or recipe.

[1550] "Quantity" refers to numerical information that indicates the specific quantity or weight of ingredients.

[1551] "Database" refers to a collection of information for efficiently managing, searching, and updating structured data.

[1552] A "recipe" refers to a document or data that contains instructions and a list of ingredients for creating a dish.

[1553] "Recommended" indicates candidates that are particularly recommended to the user based on specific conditions.

[1554] "Preferences" refer to the preferences or biases selected by a user based on specific conditions or criteria.

[1555] "Learning" refers to the process of analyzing and analysing a user's past behaviour and choices and reflecting this in future suggestions.

[1556] "Ingredient list" refers to a list of the names and amounts of ingredients required based on a recipe.

[1557] "Ordering" refers to the act of requesting the necessary ingredients from a specific delivery service.

[1558] "Delivery" refers to the service of delivering ordered ingredients to a specified location.

[1559] "Means" refers to a method or device used to achieve a particular purpose.

[1560] The present invention provides a system that enables a user to efficiently find a recipe that meets their own conditions and preferences, and to order delivery of the ingredients they need based on that recipe.

[1561] First, the user launches the application on a device such as a smartphone, smart glasses, or head-mounted display, and then uses the interface displayed on the screen to input specific conditions (e.g., baby food, vegetarian food), the ingredients purchased, and their quantities. The input data is then stored in a cloud database (e.g., Firebase) in real time.

[1562] The data recorded in the cloud database is sent to a server. The server receives the user's input data and searches the database for recipes that match the specified criteria. This search process uses a database management system and a recipe search API. For example, a search can be made for recipes in "baby food" that use "300g of carrots" and "200g of chicken."

[1563] From the search results, a generative AI model (e.g., TensorFlow) is used to select the recipe that best suits the user's criteria. The selected recipe is sent to the user's device and displayed as a recommendation on the screen.

[1564] When a user selects a recipe from the recommended recipes, detailed information about that recipe (ingredients, cooking method, cooking time, etc.) is displayed. The information about the selected recipe is saved on the server and accumulated as user preference data. Based on this preference data, a machine learning algorithm (e.g., PyTorch) is used to learn the user's preference patterns and reflect them in future recipe suggestions.

[1565] Next, a list of ingredients is generated based on the selected recipe, and an order for delivery of the ingredients is placed using an API corresponding to the delivery service (e.g., Uber Eats, DoorDash, etc.) The generation of the ingredient list and the transmission of the delivery order are carried out on the server side, and the order is transmitted to the corresponding delivery company.

[1566] For example:

[1567] For example, if a user starts an application to make baby food, selects "baby food," and then enters "300g of carrots" and "200g of chicken," the server will search the database for baby food recipes that use "carrots" and "chicken," and generate recommended recipes such as "carrot and chicken puree" and "chicken and carrot stew." When the user selects "carrot and chicken puree," details of that recipe are displayed on the device. At the same time, the server saves the user's selection history and reflects it in the next recipe suggestion.

[1568] An example prompt would be:

[1569] "User selects baby food and enters 300g of carrots and 200g of chicken."

[1570] In this way, the present invention provides consistent support from the process of users finding a recipe that meets their requirements to purchasing and delivering the necessary ingredients, thereby greatly improving user convenience.

[1571] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1572] Step 1:

[1573] The user launches the application on their device and the condition selection interface is displayed. The user enters the conditions, ingredients, and their quantities, and sends this data to the device. The entered data is saved in real time to a cloud database (Firebase). This registers the user-specified conditions and ingredient information in the database.

[1574] Input: Condition (e.g., baby food), ingredients (e.g., 300g carrots, 200g chicken)

[1575] Output: Data stored in a cloud database

[1576] Specific behavior:

[1577] The user enters "Condition: Baby food," "Ingredients: 300g carrots," and "Ingredients: 200g chicken," and clicks the "Save" button.

[1578] Step 2:

[1579] The device sends the input data to the server. The server receives this data and searches the database for recipes that meet the criteria. This search uses a recipe search API or database management system. As a result, the server extracts and selects multiple recipes that meet the criteria.

[1580] Input: User data retrieved from a cloud database

[1581] Output: A list of recipes that match the criteria

[1582] Specific behavior:

[1583] The server searches for recipe data containing "baby food," "carrots," and "chicken," and extracts candidates such as "carrot and chicken puree" and "chicken and carrot stew."

[1584] Step 3:

[1585] The server uses a generative AI model (TensorFlow) to select the recipe that best suits the user's requirements. The selected recipe data is sent to the device and displayed as a recommendation on the user's screen.

[1586] Input: Multiple recipes that meet the criteria

[1587] Output: One or more recommended recipes

[1588] Specific behavior:

[1589] The server evaluates recipes using the generative AI model and sends the best candidates as "recommendations" to the device, which then displays "Recommended Recipe: Carrot and Chicken Puree."

[1590] Step 4:

[1591] The user selects any recipe from the recommended recipes and the details of that recipe (ingredients, cooking method, cooking time, etc.) are displayed. The selected recipe information is sent to the server and saved as the user's preference data.

[1592] Input: User selected recipe

[1593] Output: Display details of selected recipe, save preference data to server

[1594] Specific behavior:

[1595] When the user selects "Carrot and Chicken Puree," its detailed information is displayed on the screen. At the same time, the "User ID" and "Recipe ID" are saved on the server.

[1596] Step 5:

[1597] The server uses a machine learning algorithm (PyTorch) to learn the user's preference patterns and reflect them in future recipe suggestions. This learning process improves the accuracy of recipe suggestions based on the user's preferences.

[1598] Input: User preference data

[1599] Output: Updated user preference data pattern

[1600] Specific behavior:

[1601] The server analyzes the recipes the user has previously selected to reflect this in the next recipe suggestions.

[1602] Step 6:

[1603] The server generates a list of ingredients based on the selected recipe and sends the order to the partner delivery service API.

[1604] Input: A list of ingredients for the selected recipe

[1605] Output: Delivery order sent

[1606] Specific behavior:

[1607] The server generates an ingredient list of "300g of carrots" and "200g of chicken" and sends it to the delivery service API.

[1608] Step 7:

[1609] The delivery company receives the list of ingredients, prepares them, and delivers them to the specified address. The user can then pick up the ordered ingredients and create the dish according to the recipe.

[1610] Input: Delivery Order

[1611] Output: Food delivery to the specified address

[1612] Specific behavior:

[1613] The delivery company prepares the order and delivers 300g of carrots and 200g of chicken to the user's address.

[1614] 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.

[1615] The present invention is a system that allows users to efficiently find recipes that suit their own conditions and preferences, and further learns their preferences and feelings and reflects them in future recipe suggestions.

[1616] Program processing

[1617] 1. Select conditions and register ingredients

[1618] Terminal: The user launches applications and web services.

[1619] Device: A UI for selecting conditions is displayed on the screen. The user is presented with options such as "baby food," "nursing care food," and "allergy-friendly food."

[1620] User: Select a condition. For example, select "baby food."

[1621] Terminal: Records the conditions (baby food) selected by the user.

[1622] 2. Enter ingredients and emotions

[1623] Terminal: Displays an input form that allows the user to input the ingredients purchased and the amount, and also displays an interface for inputting or measuring the user's emotions.

[1624] User: Enter the ingredients purchased, their quantities, and their current emotions. For example, they can enter "300g of carrots," "200g of chicken," and "satisfied."

[1625] Terminal: A screen to confirm the input information is displayed, and the user clicks the confirmation button.

[1626] Terminal: Sends the user's input data (conditions, ingredients, emotions) to the server.

[1627] 3. Creating and displaying recipes

[1628] Server: Receives user input data, including the user ID, selection criteria, ingredients and their amounts, and emotions.

[1629] Server: Searches for recipes that match the criteria from the database based on the received data and past data. It also uses an emotion engine to select recipes that correspond to the user's emotions.

[1630] Server: Generates a list of recipes that match the criteria and are emotionally appropriate. For example, it might select "carrot and chicken puree" or "chicken and carrot stew."

[1631] Server: Sends the generated recipe list to the terminal.

[1632] Device: Recommended recipes are displayed to the user.

[1633] 4. Select a recipe and view details

[1634] User: Select a recipe from the suggested recipes. For example, select "Carrot and Chicken Puree."

[1635] On your device: View detailed information about the selected recipe, including specific ingredients, cooking instructions, and cooking times.

[1636] 5. Learning user preferences and emotions

[1637] Server: Stores the recipe data selected by the user and the emotion data at that time. The stored information includes the user ID, the selected recipe ID, and the emotion data.

[1638] Server: Applies algorithms to learn user preferences and emotions, which analyzes user behavior patterns, preferences, and emotions.

[1639] Server: Updates the system to reflect the learning results in future recipe suggestions. This ensures that when the user uses the system again, it will suggest recipes that better match their preferences and emotions.

[1640] Specific examples

[1641] For example, suppose User A launches an application to make baby food, selects "baby food," and then enters "300g carrots," "200g chicken," and "satisfied." In this case, the server searches the database for baby food recipes that use "carrots" and "chicken," and selects a recipe that matches the user's emotion of "satisfied." It generates recommended recipes such as "carrot and chicken puree" and "chicken and carrot stew" and sends them to the device. When the user selects "carrot and chicken puree," details of that recipe are displayed on the device. At the same time, the server saves the user's selection history and emotion data and reflects them in the next recipe suggestions. This ensures that recipes that match the user's preferences and emotions are provided each time the application is used.

[1642] The processing flow will be explained below.

[1643] Step 1:

[1644] Terminal: The user launches applications and web services.

[1645] Terminal: A UI for selecting conditions is displayed on the screen, and the user is presented with options such as "baby food," "nursing care food," and "allergy-friendly food."

[1646] Step 2:

[1647] User: Select a condition. For example, select "baby food."

[1648] Terminal: Records the conditions (baby food) selected by the user.

[1649] Step 3:

[1650] Terminal: Displays the screen for inputting ingredients and emotions. An interface is provided for the user to input the ingredients purchased, their quantities, and their current emotions.

[1651] User: Enter the ingredients purchased, their quantities, and their current emotions. For example, enter "300g of carrots," "200g of chicken," and "Satisfied."

[1652] Step 4:

[1653] Terminal: A screen to confirm the input information is displayed, and the user clicks the confirmation button.

[1654] Terminal: Sends the user's input data (conditions, ingredients, emotions) to the server.

[1655] Step 5:

[1656] Server: Receives the user's input data, including the user ID, selection criteria, ingredients, and emotions.

[1657] Step 6:

[1658] Server: Based on the input data and past data, the server searches the database for recipes that match the conditions, and uses an emotion engine to select a recipe that suits the user's emotions.

[1659] For example, if a user enters "satisfied," recipes chosen with similar emotions or highly rated recipes will be prioritized.

[1660] Step 7:

[1661] Server: Generates a list of recommended recipes that match the conditions and emotions.

[1662] For example, select "carrot and chicken puree" or "chicken and carrot stew."

[1663] Server: Sends the generated recipe list to the terminal.

[1664] Step 8:

[1665] Device: Recommended recipes received from the server are displayed to the user. Recipe names and summaries are displayed in a list.

[1666] Step 9:

[1667] User: Select your preferred recipe from the recommended recipes displayed.

[1668] For example, select "Carrot and Chicken Puree."

[1669] On your device: Detailed information about the selected recipe will be displayed, including specific ingredients, cooking instructions, and cooking time.

[1670] Step 10:

[1671] Server: Stores the data of the recipe selected by the user and the emotion data at that time.

[1672] The information stored includes the user ID, the selected recipe ID, and emotion data.

[1673] Step 11:

[1674] Server: Applies algorithms to learn user preferences and emotions.

[1675] User behavior patterns, preferences, and emotions are analyzed.

[1676] Step 12:

[1677] Server: Updates the system to reflect the learning results in future recipe suggestions.

[1678] This means that when a user uses the system again, recipes that better match their preferences and emotions will be suggested.

[1679] Example 2

[1680] 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."

[1681] Conventional recipe suggestion systems were able to provide recipes that matched the user's conditions and ingredients, but it was difficult to learn the user's emotions and preferences and reflect them in future suggestions. Furthermore, because they were unable to take into account the ingredients purchased by the user or their emotions, the accuracy of suggesting the optimal recipe for the user was low. This led to users being dissatisfied with the recipe selection, resulting in a decrease in the frequency of system use.

[1682] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1683] In this invention, the server includes means for allowing a user to select conditions and input and register purchased ingredients and their quantities, means for receiving the input data and searching a database for recipes that match the conditions, means for using an emotion engine to select a recipe according to emotions based on the received data and past data, means for displaying the searched recipes as recommendations to the user, means for saving a recipe selected by the user from the displayed recipes and learning the user's preferences and emotions, and means for reflecting the learned user preferences and emotions in the selection of recommended recipes from the next time onwards. This makes it possible to propose optimal recipes based on the user's conditions, ingredients, and emotions.

[1684] "Conditions" are user-selected constraints or requirements, including, for example, types of food and health restrictions.

[1685] "Ingredients" refer to the foods and ingredients used in a dish or recipe, and specifically include vegetables, meat, seasonings, etc.

[1686] "Quantity" is a numerical value indicating the quantity or weight of a material that the user has purchased or possesses.

[1687] A "database" is a collection of information that structures and stores user conditions, ingredients, and recipe information.

[1688] "Search" is the operation of searching a database for information that matches specified conditions.

[1689] A "prescription" is information that indicates a recipe or cooking method for a dish.

[1690] "Emotion" indicates the user's current psychological state, and is information such as "satisfied" or "dissatisfied," for example.

[1691] An "emotion engine" is an algorithm or system that selects the optimal prescription based on the user's emotions.

[1692] "Display" refers to the operation of visually showing prescription information and recommended recipes on the user's device.

[1693] "Preferences" indicate a user's tendency to prefer particular recipes or ingredients.

[1694] "Learning" is an information analysis process that uses user preferences and emotional data to reflect in future recipe suggestions.

[1695] A "system" is a set of mechanisms that combine multiple means and technologies to provide services to users.

[1696] MODE FOR CARRYING OUT THE INVENTION

[1697] This invention is a system that allows users to efficiently find recipes that suit their own conditions and preferences, and also learns their preferences and feelings and reflects them in future recipe suggestions.

[1698] System Overview

[1699] This system includes means for a user to select conditions and input and register purchased materials and their quantities, means for receiving the input data and searching a database for recipes that match the conditions, means for using an emotion engine to select a recipe according to emotions based on the received data and past data, means for displaying the searched recipes as recommendations to the user, means for saving a recipe selected by the user from the displayed recipes and learning the user's preferences and emotions, and means for reflecting the learned user preferences and emotions in the selection of recommended recipes from the next time onwards.

[1700] Hardware and Software Configuration

[1701] 1. Terminal: A device used by a user to access an application or web service, including a smartphone, tablet, or PC.

[1702] 2. Server: This is the central system that receives and processes input data from users. It includes a database server, machine learning engine, and emotion engine.

[1703] 3. Software:

[1704] User interface: A UI on an application or web browser that provides an interface for selecting conditions and inputting materials.

[1705] Database system: A database (e.g., SQL database) for storing and managing entered user and prescription data.

[1706] Emotion engine: An algorithm for analyzing user emotions and suggesting appropriate prescriptions based on them.

[1707] Machine learning algorithms: Recommendation systems that learn user preferences and history and reflect this in future recommendations.

[1708] Specific examples

[1709] For example, suppose User A launches the application, selects "baby food," and then enters "300g carrots," "200g chicken," and "satisfied." In this case, the server searches the database for baby food recipes that use "carrots" and "chicken," and selects a recipe that corresponds to the user's emotion of "satisfied." As a result, recommended recipes such as "carrot and chicken puree" and "chicken and carrot stew" are generated and sent to the device. When the user selects "carrot and chicken puree," details of the selection are displayed on the device. At the same time, the server saves the user's selection history and emotion data, and can reflect this in the next recipe suggestions. This allows the server to provide recipes that match the user's preferences and emotions each time the application is used.

[1710] Prompt Sentence Examples

[1711] By inputting the following prompt sentence into the generative AI model, a description of the above system can be generated in natural language.

[1712] "Users input conditions, ingredients, and emotions through an application or web service, and the AI ​​model uses a database and emotion engine to generate natural-sounding sentences that explain the system and suggest prescriptions that match the conditions and are appropriate for the emotions."

[1713] The prompts enable the generative AI model to generate detailed natural language descriptions of the system's functions and procedures.

[1714] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1715] Step 1:

[1716] Terminal: When a user launches an application or web service, the home screen appears.

[1717] Input: Application launch by user action

[1718] Output: Display of the home screen of the application or web service

[1719] Specific actions: Tap an icon on your smartphone to launch an app, or enter a URL in a web browser.

[1720] Step 2:

[1721] Terminal: A user interface (UI) for selecting conditions is displayed on the screen. The user is presented with options such as "baby food," "nursing care food," and "allergy-friendly food."

[1722] Input: The application initialization process calls the criteria selection UI

[1723] Output: Display of a screen where the user can select conditions

[1724] Specific operation: A screen will appear where you can select conditions using a drop-down menu or radio buttons.

[1725] Step 3:

[1726] User: Select a condition and click the Next button. For example, select "baby food."

[1727] Input: User selection of conditions

[1728] Output: Record of selected conditions and transition to the next input screen

[1729] Specific actions: Select with a mouse click or touch gesture and press the "Next" button.

[1730] Step 4:

[1731] Terminal: Displays a form that allows the user to input the ingredients and their quantities purchased, and also displays an interface for inputting or measuring the user's emotions.

[1732] Input: System response to condition selection

[1733] Output: Display of material and emotion input form

[1734] Specific operation: A section for entering ingredients and their quantities using text boxes or voice input, as well as a slider or button for entering emotions, will be displayed.

[1735] Step 5:

[1736] User: Enter the ingredients purchased (e.g., "300g carrots" and "200g chicken") and their current feelings (e.g., "Satisfied").

[1737] Input: User input of materials and emotions

[1738] Output: Display of input confirmation screen

[1739] Specific actions: Enter text or use voice recognition to enter material information, then drag the emotion slider to the appropriate value.

[1740] Step 6:

[1741] Terminal: A screen is displayed to confirm the input and the user is asked to click a confirmation button.

[1742] Input: Material and emotional input data

[1743] Output: Display confirmation screen

[1744] Specific operation: Displays the input data and displays a button to ask the user for confirmation.

[1745] Step 7:

[1746] User: Click the Verify button to verify that the data is correct.

[1747] Input: User clicks confirmation button

[1748] Output: Confirmed data transmission process

[1749] Specific operation: Press the confirmation button to confirm the input.

[1750] Step 8:

[1751] Terminal: Sends the user's input data (conditions, materials, emotions) to the server.

[1752] Input: Confirmed data

[1753] Output: Send data to the server

[1754] Specific operation: Executes an API call to send data to a server over the network.

[1755] Step 9:

[1756] Server: Receives input data sent by the user, searches the database for prescriptions that match the conditions, and uses an emotion engine to select a prescription that corresponds to the user's emotion.

[1757] Input: Input data sent from the terminal

[1758] Output: A list of prescriptions that match the criteria and are emotionally appropriate

[1759] Specific operation: Executes an SQL query to extract relevant prescriptions from the database and filters them using the emotion engine.

[1760] Step 10:

[1761] Server: Generates a list of recipes that match the conditions and are emotionally appropriate. For example, it might select "carrot and chicken puree" or "stewed chicken and carrots."

[1762] Input: Searched and filtered prescription data

[1763] Output: Generate a prescription list

[1764] Specific operation: Generate a list based on the filtered prescription data.

[1765] Step 11:

[1766] Server: Sends the generated prescription list to the user's terminal.

[1767] Input: Generated prescription list

[1768] Output: Send prescription list to terminal

[1769] Specific operation: Executes an API call to send a prescription list to the terminal via the network.

[1770] Step 12:

[1771] Device: Recommended recipes are displayed to the user.

[1772] Input: Prescription list sent from the server

[1773] Output: Display recommended recipes

[1774] Specific operation: Recipes appear on the screen in a list format using a design template.

[1775] Step 13:

[1776] User: Select a recipe from the suggested recipes. For example, select "Carrot and Chicken Puree."

[1777] Input: User selection of recipe

[1778] Output: Display detailed information about the selected recipe

[1779] Action: Tap or click to select a recipe from the list.

[1780] Step 14:

[1781] On your device: View detailed information about the selected recipe, including specific ingredients, cooking instructions, and cooking times.

[1782] Input: Recipe data selected by the user

[1783] Output: Display detailed recipe information

[1784] What Happens: A detailed view of the recipe appears, showing the ingredients list and steps in a scrollable format.

[1785] Step 15:

[1786] Server: Stores the data of the recipe selected by the user and the emotion data at that time.

[1787] Input: Recipe data and emotion data selected by the user

[1788] Output: Saved user data

[1789] Specific action: It is recorded as a new record in the database.

[1790] Step 16:

[1791] Server: Applies algorithms to learn user preferences and emotions, which analyzes user behavior patterns, preferences, and emotions.

[1792] Input: Stored user preference and emotion data

[1793] Output: Training data as analysis results

[1794] Specific actions: Run machine learning algorithms (e.g., recommendation systems) to analyze data.

[1795] Step 17:

[1796] Server: Updates the system to reflect the learning results in future recipe suggestions. This ensures that when the user uses the system again, it will suggest recipes that better match their preferences and emotions.

[1797] Input: Parsed training data

[1798] Output: Proposed features of the updated system

[1799] Specific operation: The proposed algorithm is updated based on the training data.

[1800] (Application example 2)

[1801] 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."

[1802] Conventional recipe suggestion systems were able to provide recipes that took into account the user's conditions and preferences, but they were unable to suggest recipes that reflected the user's emotions. As a result, suggestions that improved the user's emotional satisfaction and experience were insufficient. Furthermore, if a user's recipe preferences differed depending on a specific emotion, this was not recorded or learned, and could not be reflected in future suggestions. Therefore, the goal of this project is to further improve user satisfaction by providing a recipe suggestion system that also takes into account the user's emotions.

[1803] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1804] In this invention, the server includes a means for a user to select conditions and input and register purchased ingredients and their quantities, a means for receiving the input data and the user's emotional data, and a means for searching a database for recipes that match the conditions, and a means for displaying the searched recipes as recommendations to the user, thereby enabling recipe suggestions based on the user's emotions in addition to their conditions and preferences.

[1805] "User" means an individual or organization that uses the system.

[1806] "Conditions" are parameters that a user sets to search for a particular recipe.

[1807] "Ingredients" refers to the types and amounts of food used to prepare a recipe.

[1808] "Emotion data" is information that indicates the user's emotional state, and is data that the system receives to use in proposing recipes.

[1809] A "database" is a structured collection of information that stores recipe information and facilitates retrieval.

[1810] The "search means" is a software function that searches the database for recipes that meet the user's requirements.

[1811] The "displaying means" is an interface for displaying the selected recipe on the user's device.

[1812] The "storage means" is a system that records the user's selected recipes and emotional data for future reference and learning.

[1813] The "learning means" is an algorithm that analyzes stored user preference and emotion data and reflects that in future suggestions.

[1814] "Server" means a central management system for receiving, processing, and storing data.

[1815] This invention is a system that allows users to input ingredients and their quantities via a smartphone application or web interface, and suggests recipes that suit their preferences and conditions. This includes a means for users to select conditions, input purchased ingredients and emotional data, and provide recipes based on those.

[1816] System configuration and usage

[1817] 1. User selection of conditions and input of ingredients

[1818] The user launches the application and selects criteria such as "baby food," "caregiver food," and "allergy-friendly food" from their smartphone or computer terminal.

[1819] After selecting these conditions, the user inputs the type and quantity of ingredients purchased, as well as emotional data (such as "satisfied" or "sad").

[1820] 2. Data Receipt and Processing by the Server

[1821] The conditions, ingredients, and emotion data entered by the user are sent to the server, which receives this data and searches a database for recipes that match the ingredients and conditions.

[1822] The server uses an emotion engine, such as a TensorFlow-based emotion analysis model, to select recipes that match the user's emotional state based on the received emotion data.

[1823] 3. Creating and displaying recipes

[1824] The searched recipes are displayed as recommendations on the user's device. Recipe information includes the ingredients needed, cooking steps, cooking time, etc.

[1825] When the user selects a recipe from the ones presented, more detailed information about that recipe is displayed.

[1826] 4. Learning and storing user preference and emotion data

[1827] The server records the recipe selected by the user and their emotional state at the time. This data is used to make future recommendations.

[1828] It applies algorithms to learn user preferences and emotional data, analyzing user behavior patterns and preferences, so that future recipe suggestions are more tailored to the user's needs and emotions.

[1829] Hardware and software used

[1830] Hardware: Servers (e.g., Amazon EC2), user devices (smartphones, PCs, etc.)

[1831] Software: Flask (a web framework written in Python), SQLite (a local database), TensorFlow (a machine learning library for sentiment analysis)

[1832] Examples and prompts

[1833] For example, suppose User A starts an application to make baby food, selects "baby food," and then inputs "300g carrots," "200g chicken," and "satisfied." In this case, the server searches the database for baby food recipes that use "carrots" and "chicken," and selects a recipe that matches the user's emotion of "satisfied." Suggested recipes include "carrot and chicken puree" and "chicken and carrot stew."

[1834] Here is an example prompt:

[1835] Let's say a user selects "baby food" as a condition, and inputs "300g carrots," "200g chicken," and the emotion "satisfied." In this case, we'll suggest the following recipes:

[1836] 1. Carrot and chicken puree

[1837] 2. Chicken and carrot stew

[1838] By inputting this prompt into a generative AI model, recipes that match the user's conditions and emotions can be efficiently generated and suggested.

[1839] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1840] Step 1:

[1841] The user launches the application and selects conditions on a smartphone or computer. Specifically, options such as "baby food," "nursing care food," and "allergy-friendly food" are displayed, and the user selects one. The input data is sent to the server in the form of condition selection.

[1842] Step 2:

[1843] Based on the selected criteria, the user inputs the ingredients purchased, their quantities, and emotional data, such as "300g of carrots," "200g of chicken," and "satisfied." This data is also sent from the device to the server.

[1844] Step 3:

[1845] The server processes the received conditions, ingredient data, and emotion data. It then searches the database for recipes that match the conditions based on the type and amount of ingredients. It also takes into account the input emotion data and uses an emotion analysis model such as TensorFlow to select recipes that suit the emotion.

[1846] Step 4:

[1847] Based on the results of the search and sentiment analysis, the system generates recipe recommendations for the user. These recipes include, for example, "carrot and chicken puree" and "chicken and carrot stew." This list is sent to the user's device as recipe information and displayed on the screen.

[1848] Step 5:

[1849] The user selects a recipe from the list of recipes presented, and detailed information about the selected recipe (ingredients, cooking steps, cooking time, etc.) is displayed.

[1850] Step 6:

[1851] The server stores the recipe selected by the user and the emotion data at that time. The saved data is recorded along with the user ID and will be used for future recipe suggestions.

[1852] Step 7:

[1853] The server analyzes the stored data and applies algorithms that learn the user's preferences and emotions, allowing it to better tailor future recipe suggestions to the user's behavioral patterns, tastes, and emotions.

[1854] Specific explanation of processing operations

[1855] Step 1:

[1856] Input data: User selection of conditions (e.g., "baby food")

[1857] Output data: Criteria selection data sent to the server

[1858] How it works: A user launches the application and selects criteria on their smartphone or computer.

[1859] Step 2:

[1860] Input data: Food ingredient data and emotion data (e.g., "300g carrots," "200g chicken," "satisfied")

[1861] Output data: Ingredient data and emotion data sent to the server

[1862] How it works: Based on the selected criteria, the user inputs the ingredients purchased, their quantities, and emotional data.

[1863] Step 3:

[1864] Input data: condition data, ingredient data, emotion data

[1865] Output data: Recipe search results and sentiment analysis results

[1866] How it works: The server processes the received data, searches the database for recipes that match the criteria, and uses a sentiment analysis model to select an appropriate recipe.

[1867] Step 4:

[1868] Input data: Recipe search results and sentiment analysis results

[1869] Output data: A list of recipes recommended for the user

[1870] Operation: The server generates recommended recipes based on the search and analysis results, sends them to the user's device, and displays them on the screen.

[1871] Step 5:

[1872] Input data: User selected recipe

[1873] Output data: Detailed information about the selected recipe

[1874] How it works: The user selects a recipe from the ones presented and its details are displayed.

[1875] Step 6:

[1876] Input data: Selected recipes and sentiment data

[1877] Output data: Selection history and emotion data stored on the server

[1878] Operation: The server stores the recipe selected by the user and the emotion data at that time.

[1879] Step 7:

[1880] Input data: saved selection history and emotion data

[1881] Output data: Recipe suggestions for the next time and beyond that reflect the user's behavioral patterns, preferences, and emotions

[1882] How it works: The server analyzes the stored data and applies algorithms that learn the user's preferences and emotions to improve future recipe suggestions.

[1883] 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.

[1884] 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.

[1885] 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.

[1886] 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.

[1887] 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.

[1888] 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.

[1889] 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).

[1890] 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.

[1891] 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."

[1892] 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.

[1893] 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).

[1894] 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.

[1895] 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.

[1896] 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.

[1897] 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.

[1898] 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.

[1899] 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.

[1900] 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.

[1901] 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.

[1902] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1903] 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.

[1904] The following is further disclosed regarding the above embodiment.

[1905] (Claim 1)

[1906] A means for a user to select conditions and input and register purchased ingredients and their quantities;

[1907] means for receiving the input data and searching a database for recipes that meet the conditions;

[1908] means for displaying the searched recipes as recommendations to the user;

[1909] a means for saving a recipe selected by a user from the displayed recipes and learning the user's preferences;

[1910] A means for reflecting the learned user preferences in the selection of recommended recipes from the next time onwards;

[1911] A system including:

[1912] (Claim 2)

[1913] 10. The system of claim 1, further comprising: means for displaying an interface for confirming user input.

[1914] (Claim 3)

[1915] 2. The system according to claim 1, further comprising means for storing the purchased ingredients and their amounts in a database for use in subsequent recipe searches.

[1916] "Example 1"

[1917] (Claim 1)

[1918] A means for a user to select conditions and input and register purchased ingredients and their quantities;

[1919] means for receiving the input data and searching a database for recipes that meet the conditions;

[1920] means for displaying the searched recipes as recommendations to the user;

[1921] a means for saving a recipe selected by a user from the displayed recipes and learning the user's preferences;

[1922] A means for reflecting the learned user preferences in the selection of recommended recipes from the next time onwards;

[1923] means for displaying a corresponding interface when a user selects a condition;

[1924] A system including:

[1925] (Claim 2)

[1926] 10. The system of claim 1, further comprising: means for displaying an interface for confirming user input.

[1927] (Claim 3)

[1928] 2. The system according to claim 1, further comprising means for storing the purchased ingredients and their amounts in a database for use in subsequent recipe searches.

[1929] "Application Example 1"

[1930] (Claim 1)

[1931] A means for a user to select conditions and input and register purchased ingredients and their quantities;

[1932] means for receiving the input data and searching a database for recipes that meet the conditions;

[1933] means for displaying the searched recipes as recommendations to the user;

[1934] a means for saving a recipe selected by a user from the displayed recipes and learning the user's preferences;

[1935] A means for reflecting the learned user preferences in the selection of recommended recipes from the next time onwards;

[1936] means for generating a list of ingredients needed and ordering the ingredients;

[1937] A means of managing the delivery of ingredients;

[1938] A system including:

[1939] (Claim 2)

[1940] 10. The system of claim 1, further comprising: means for displaying an interface for confirming user input.

[1941] (Claim 3)

[1942] 2. The system according to claim 1, further comprising means for storing the purchased ingredients and their amounts in a database for use in subsequent recipe searches.

[1943] "Example 2: Combining Emotion Engines"

[1944] (Claim 1)

[1945] A means for a user to select conditions and input and register purchased materials and their quantities;

[1946] a means for receiving the input data and searching a database for a prescription that matches the conditions;

[1947] means for using an emotion engine to select an emotion-dependent prescription based on the received data and past data;

[1948] means for displaying the searched prescription as a recommendation to a user;

[1949] a means for storing a prescription selected by a user from the displayed prescriptions and learning the user's preferences and feelings;

[1950] A means for reflecting the learned user preferences and emotions in the selection of recommended prescriptions from the next time onwards;

[1951] A system including:

[1952] (Claim 2)

[1953] 10. The system of claim 1, further comprising: means for displaying an interface for confirming user input.

[1954] (Claim 3)

[1955] 2. The system according to claim 1, further comprising means for storing the purchased ingredients, their quantities and emotion data in a database and using the stored data for subsequent prescription searches.

[1956] "Application example 2 when combining emotion engines"

[1957] (Claim 1)

[1958] A means for a user to select conditions and input and register the ingredients and quantities purchased;

[1959] means for receiving the input data and user emotion data and searching a database for recipes that meet the conditions;

[1960] means for displaying the searched recipes as recommendations to the user;

[1961] a means for saving a recipe selected by a user from the displayed recipes and emotions, and learning the user's preferences and emotions;

[1962] A means for reflecting the learned user preferences and emotions in the selection of recommended recipes from the next time onwards;

[1963] A system including:

[1964] (Claim 2)

[1965] 10. The system of claim 1, further comprising: means for displaying an interface for confirming user input.

[1966] (Claim 3)

[1967] 2. The system according to claim 1, further comprising means for storing the purchased ingredients and their amounts in a database for use in subsequent recipe searches. [Explanation of symbols]

[1968] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for a user to select conditions and input and register purchased ingredients and their quantities; means for receiving the input data and searching a database for recipes that meet the conditions; means for displaying the searched recipes as recommendations to the user; a means for saving a recipe selected by a user from the displayed recipes and learning the user's preferences; A means for reflecting the learned user preferences in the selection of recommended recipes from the next time onwards; A system including:

2. 10. The system of claim 1, further comprising: means for displaying an interface for confirming user input.

3. 2. The system according to claim 1, further comprising means for storing the purchased ingredients and their amounts in a database for use in subsequent recipe searches.

Images