System

Abstract

To provide a system for quickly and surely proposing a suitable food or meal plan according to the meal restriction or nutrition condition of a user.SOLUTION: The specification processing unit 290 of the data processing apparatus 12 in the system acquires product information via a network, stores the product information in a database, constructs a generation model that performs learning based on the product information stored in the database, acquires dietary restrictions and nutritional conditions input by a user by causing the user to input the dietary restrictions and the nutritional conditions, generates a product and a dietary plan that match the dietary restrictions and the nutritional conditions using the generation model, and presents the generated product and dietary plan to the user.SELECTED DRAWING: Figure 2

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] Describe the "problem that the invention aims to solve" and the "means for solving the problem."

[0005] ---

[0006] Choosing commercially available foods can be extremely difficult for people with allergies, illnesses, dietary restrictions during pregnancy, or those who need to manage their nutrition for physical fitness. For those with multiple dietary restrictions, the time and effort required to individually check foods that meet each restriction can be a significant burden. To solve this problem, a system is needed that can quickly and reliably suggest foods and meal plans that match the user's dietary restrictions and nutritional requirements. [Means for solving the problem]

[0007] The present invention solves the above-mentioned problems by providing a system that includes means for acquiring product information via a network, means for storing the product information in a database, and means for constructing a generative model that learns based on the product information stored in the database. It also includes means for allowing a user to input dietary restrictions and nutritional conditions, and means for transmitting the dietary restrictions and nutritional conditions input by the user to a server. The system then includes means for using the generative model in the server to generate products and meal plans that conform to the dietary restrictions and nutritional conditions, and presenting the generated products and meal plans to the user.

[0008] ---

[0009] A "network" is a system in which multiple information devices are connected via communication to send and receive data.

[0010] "Product information" refers to detailed data about a product's characteristics and ingredients, such as the product's name, nutritional value, ingredient list, and allergen information.

[0011] A "database" is a collection of data constructed to efficiently search, store, and manage information.

[0012] A "server" is a computer that provides services to other computers on a network.

[0013] A "user" is an individual or organization that uses the system, and in the present invention is the entity that inputs dietary restrictions and nutritional conditions.

[0014] A "dietary restriction" is a restriction that prevents the intake of certain foods or ingredients for specific reasons such as allergies, illness, or pregnancy.

[0015] "Nutritional requirements" refer to the amount and type of nutrients required to maintain health or for a specific purpose (e.g., physical fitness, disease management).

[0016] A "generative model" is a mathematical model that uses machine learning algorithms to learn from data and make predictions or classifications on new data.

[0017] An "AI model" is synonymous with a "generative model," which is a model constructed using artificial intelligence techniques to perform a specific task.

[0018] "Meal Plan" means a combination or suggestion of appropriate meals based on specific nutritional requirements or dietary restrictions.

[0019] A "terminal" is a device that allows a user to input information and check results from the system, and includes smartphones and personal computers.

[0020] "Filtering" is the process of sorting data based on specific conditions and extracting only the necessary information.

[0021] "Learning" is the process by which generative and AI models use data to discover patterns and relationships that can be used for predictions and classifications. [Brief explanation of the drawings]

[0022] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6]FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] 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).

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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."

[0043] ---

[0044] The present invention is a system that allows people who have allergies, illnesses, dietary restrictions during pregnancy, or who need nutritional management for building a healthy body to easily select commercially available foods and boxed lunches. This system acquires product information via a network and provides products and meal plans that match the user's dietary restrictions and nutritional requirements. Specific embodiments of the system are described below.

[0045] Obtaining and storing product information

[0046] server

[0047] The server obtains product information from online supermarkets and bento shops via API or data files, including product names, nutritional information, ingredient lists, and allergen information.

[0048] The acquired product information is stored in a database.

[0049] Learning and Generative Model Building

[0050] server

[0051] Using product information stored in a database, a machine learning algorithm (e.g., deep learning) is used to build a generative model that learns detailed information about the product and can make predictions and classifications for new data.

[0052] Input from the user

[0053] User

[0054] Users use devices such as smartphones or computers to input their own dietary restrictions and nutritional requirements, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on their health status.

[0055] Sending and matching conditions

[0056] Terminal

[0057] The dietary restrictions and nutritional conditions entered by the user are sent from the terminal to the server.

[0058] server

[0059] The server uses the generative model to generate products, lunch boxes, and even daily meal plans that match the user's criteria, filtering the foods that match the criteria based on information stored in the database.

[0060] Proposals and Presentations

[0061] server

[0062] The server sends the generated product list and meal plan to the user's terminal.

[0063] Terminal

[0064] The device displays the suggestions sent from the server to the user, allowing the user to easily find foods and meal plans that fit their dietary restrictions and nutritional requirements.

[0065] User

[0066] The user can then review the suggested products and select the ones they wish to purchase. The selected products are added to the cart and the user can proceed with the purchase.

[0067] Specific examples

[0068] For example, if a user has conditions such as "egg allergy" and "avoid caffeine," they can input these conditions via their smartphone. The server uses the generative model to filter products and meal plans from the database that match these conditions and generate suggestions. Suggested foods include caffeine-free beverages and egg-free ingredients. Users can review these suggestions and safely select them, eliminating the need to go through the trouble of searching for foods that meet multiple conditions.

[0069] This system allows customers with multiple dietary restrictions to easily select foods that suit them, significantly reducing the burden of dietary management. It can also provide meal plans tailored to individual needs for users who need to manage diabetes or who are following specific diet plans.

[0070] ---

[0071] The processing flow will be explained below.

[0072] ---

[0073] Step 1:

[0074] server

[0075] Product information is obtained from online supermarkets and bento shops via API or data files.

[0076] Product information includes product name, nutritional information, ingredient list, and allergen information.

[0077] The obtained product information is saved in the database.

[0078] Step 2:

[0079] server

[0080] Based on the product information stored in the database, a generative model is constructed using machine learning algorithms (e.g., deep learning).

[0081] Generative models are trained with product information that can later be used for prediction and classification.

[0082] Step 3:

[0083] User

[0084] Users enter their dietary restrictions and nutritional requirements using a device such as a smartphone or computer.

[0085] For example, enter conditions such as "egg allergy" or "want to avoid caffeine."

[0086] Step 4:

[0087] Terminal

[0088] The dietary restrictions and nutritional conditions entered by the user are sent to the server.

[0089] Step 5:

[0090] server

[0091] The server receives the conditions sent by the user.

[0092] It uses a generative model to match product information in the database with the user's criteria and filter out matching products and meal plans.

[0093] Step 6:

[0094] server

[0095] Based on the filtered product information, proposals tailored to individual user conditions are generated.

[0096] Suggestions include a list of suitable products and a daily meal plan.

[0097] Step 7:

[0098] server

[0099] The generated proposal content is transmitted to the user's terminal.

[0100] Step 8:

[0101] Terminal

[0102] The terminal displays the proposal sent from the server to the user.

[0103] For example, it could be displayed in the format "Recommended breakfast: Decaffeinated coffee and eggless sandwich."

[0104] Step 9:

[0105] User

[0106] Check out suggested products and meal plans.

[0107] Select the product you want to purchase and add it to your cart.

[0108] Proceed with the purchase of items added to your cart.

[0109] ---

[0110] In this way, users can easily select products that fit their dietary restrictions and nutritional requirements. Furthermore, the recommendations provided are highly accurate thanks to the generative model.

[0111] Example 1

[0112] 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."

[0113] Currently, when selecting commercially available foods or bento boxes, it is difficult for users to find products that meet their allergies, illnesses, dietary restrictions during pregnancy, or nutritional management requirements for building a healthy body. This poses a problem in that it takes a great deal of time and effort for users to select foods that meet their requirements.

[0114] 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.

[0115] In this invention, the server includes means for acquiring product information via a network, means for storing the product information in a database, means for building a generative AI model that learns based on the product information stored in the database, means for the user to input dietary restrictions and nutritional requirements, means for transmitting the dietary restrictions and nutritional requirements input by the user to the server, means for the server to use the generative AI model to generate products and meal plans that meet the dietary restrictions and nutritional requirements, means for presenting the generated products and meal plans to the user, and means for adding products selected by the user from the presented products and meal plans to the purchasing process. This allows the user to easily select foods that meet their requirements and significantly reduces the burden of dietary management.

[0116] A "network" is a system in which multiple computers or devices are connected so that they can communicate with each other.

[0117] "Product information" refers to information about a product that includes data such as the product's name, nutritional value, ingredient list, and allergen information.

[0118] A "database" is a system for efficiently storing, retrieving, and managing organized data.

[0119] A "generative AI model" is a model that has been trained using machine learning algorithms to make new predictions or classifications based on data.

[0120] "User" refers to any individual or organization that uses the system or service.

[0121] A "dietary restriction" is a restriction that prevents the intake of certain foods or ingredients for health reasons.

[0122] "Nutritional requirements" are the nutrient requirements you need or want to avoid based on a specific health condition or goal.

[0123] A "server" is a computer system that provides services to clients over a network.

[0124] A "product list" is a list that refers to a collection of products selected based on specific conditions.

[0125] A "meal plan" refers to a suggestion or plan for meals over a day or period of time.

[0126] A "purchase process" refers to a series of procedures or steps a user takes to purchase a selected product.

[0127] The present invention provides a system that allows people who have allergies, illnesses, dietary restrictions during pregnancy, or who need nutritional management for building a healthy body to easily select commercially available foods and boxed lunches. This system acquires product information via a network and provides products and meal plans that match the user's dietary restrictions and nutritional requirements. Specific embodiments of the system are described below.

[0128] Obtaining and storing product information

[0129] server

[0130] The server collects product information from online supermarkets and bento shops via API or data files, including product names, nutritional information, ingredient lists, and allergen information.

[0131] The server stores the acquired product information in a database.

[0132] Specific examples

[0133] The server communicates with the online supermarket's API every day at midnight to retrieve new and updated product information, and then adds or updates this information to the database.

[0134] Example prompt sentence:

[0135] "Please use the Rakuten Market API to update all product information daily and store it in the database."

[0136] Learning and Generative Model Building

[0137] server

[0138] The server uses machine learning algorithms (e.g., deep learning) to train a generative AI model based on the product information stored in the database. The generative AI model learns detailed information about the product and makes predictions and classifications based on the user's criteria.

[0139] Specific examples

[0140] The server uses TensorFlow to train a new model each week based on the stored product information, which can then score each product taking into account allergen information and nutritional value.

[0141] Example prompt sentence:

[0142] "Use TensorFlow to build a model that learns all the product information in your database and classifies products that meet the user's criteria."

[0143] Input from the user

[0144] User

[0145] Users use devices such as smartphones or computers to input their own dietary restrictions and nutritional requirements, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on their health status.

[0146] Specific examples

[0147] The user launches the app and enters "egg allergy" and "caffeine avoidance" on the profile screen, which updates the user profile within the app.

[0148] Example prompt sentence:

[0149] "Enter any allergies or food ingredients you are avoiding. For example, egg allergy, caffeine avoidance."

[0150] Sending and matching conditions

[0151] Terminal

[0152] The dietary restrictions and nutritional conditions entered by the user are sent from the terminal to the server.

[0153] server

[0154] Once the server receives the user's criteria, it stores them in a database and then uses a deep learning model to filter products that match the criteria. Based on the filtered results, it generates a product list and a daily meal plan that meets the user's criteria.

[0155] Specific examples

[0156] The device sends the conditions "egg allergy" and "caffeine avoidance" to the server. The server receives this and uses the database and deep learning model to search for products that meet the conditions. For example, "egg-free bread" and "caffeine-free drinks" are matched.

[0157] Example prompt sentence:

[0158] "Match products based on input criteria and generate a daily meal plan using a generative model."

[0159] Proposals and Presentations

[0160] server

[0161] The server generates a product list and meal plan that meets the user's requirements and sends it to the user's terminal.

[0162] Terminal

[0163] The terminal displays the product list and meal plan sent from the server to the user.

[0164] User

[0165] Users can review the suggested products and meal plans and select the products they wish to purchase, which are then added to their cart and they can proceed with the checkout.

[0166] Specific examples

[0167] The server sends "egg-free bread" and "caffeine-free beverage" to the terminal. The user confirms this and adds the items they want to purchase to their cart. They then proceed with the purchase.

[0168] Example prompt sentence:

[0169] "Design a UI that suggests and displays products and meal plans that match the user's criteria."

[0170] This system allows users with allergies or dietary restrictions to easily select foods that suit them, significantly reducing the burden of dietary management. It also accommodates users following specific diet plans.

[0171] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0172] Step 1:

[0173] The server acquires the product information via the network.

[0174] Input: API request from online supermarket or bento shop

[0175] Specific operation: The server executes an API request every day at midnight to obtain new products and updated information.

[0176] Output: Product information returned from the API (product name, nutritional information, ingredient list, allergen information)

[0177] Step 2:

[0178] The server stores the acquired product information in a database.

[0179] Input: Product information obtained in Step 1

[0180] Specific operation: The server performs the process of adding or updating the product information in the database.

[0181] Output: Product information stored in the database

[0182] Step 3:

[0183] The server builds a generative AI model based on product information stored in the database.

[0184] Input: Product information stored in the database

[0185] Specific operation: The server uses TensorFlow to train a deep learning model and build a model based on product information.

[0186] Output: The generated deep learning model

[0187] Step 4:

[0188] Users input their dietary restrictions and nutritional requirements via their smartphone or computer.

[0189] Input: User's dietary restrictions or nutritional requirements (e.g., egg allergy, caffeine avoidance)

[0190] Specific operation: The user enters the conditions in the device app, which are then saved in the system.

[0191] Output: Entered dietary restrictions and nutritional conditions

[0192] Step 5:

[0193] The terminal transmits the conditions entered by the user to the server.

[0194] Input: Input data for dietary restrictions and nutritional conditions

[0195] Specific operation: The terminal executes a request to send the user's conditions to the server.

[0196] Output: User criteria sent to server

[0197] Step 6:

[0198] The server receives the user's requirements and uses the database and generative AI model to generate products and meal plans that meet the requirements.

[0199] Input: User conditions sent to the server, product information stored in the database, generated deep learning model

[0200] What it does: The server uses the user's criteria as filtering criteria to search and score products in the database and generate products and meal plans that best fit the criteria.

[0201] Output: A list of products and meal plans that match your criteria

[0202] Step 7:

[0203] The server transmits the generated product list and meal plan to the user's terminal.

[0204] Input: A list of products or meal plans that match your criteria

[0205] Specific operation: The server generates the proposal and executes a request to send it to the user's device.

[0206] Output: Product list and meal plan sent to the device

[0207] Step 8:

[0208] The terminal displays the product list and meal plan sent from the server to the user.

[0209] Input: Product list or meal plan sent from the server

[0210] Specific operation: The device displays the received product list and meal plan on the screen and notifies the user.

[0211] Output: Displayed product list and meal plan

[0212] Step 9:

[0213] The user reviews the suggested products and meal plans and selects the products they wish to purchase.

[0214] Input: Displayed product list or meal plan

[0215] Specific operation: The user selects the product they want to purchase on the screen and adds it to their cart.

[0216] Output: Items added to cart

[0217] Step 10:

[0218] The user then carries out the procedure to purchase the product added to the cart.

[0219] Input: Items added to cart

[0220] What happens: The user proceeds to the checkout screen, enters payment information, and completes the order.

[0221] Output: Completed order items

[0222] (Application example 1)

[0223] 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."

[0224] People who have dietary restrictions or nutritional needs have difficulty finding foods that do not contain allergens or specific ingredients when choosing commercially available foods or bento boxes. Furthermore, there are few ways to check this information in real time while shopping in physical stores, which places a significant burden on them when making appropriate product selections.

[0225] 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.

[0226] In this invention, the server includes: means for acquiring product information via a network; means for storing the product information in a database; means for constructing a generative model that learns based on the product information stored in the database; means for allowing a user to input dietary restrictions and nutritional requirements; means for transmitting the dietary restrictions and nutritional requirements input by the user to the server; means for the server to use the generative model to generate products and meal plans that meet the dietary restrictions and nutritional requirements; means for presenting the generated products and meal plans to the user; and means for scanning a barcode using a smartphone when a user selects a product in a physical store, comparing the scanned product information with the user's input conditions to determine whether the conditions are met, and presenting the result to the user. This enables users to easily find and select products that meet their conditions in real time while shopping in a physical store.

[0227] "Means for acquiring product information via a network" refers to a function for externally collecting information about various products, such as product names, nutritional value information, ingredient lists, and allergen information, via a network such as the Internet.

[0228] The "means for saving product information in a database" is a function for recording acquired product information in a database in a structured format for later retrieval and analysis.

[0229] The "means for constructing a generative model" is a function that uses a machine learning algorithm, such as deep learning, to create a model for generating products and meal plans based on product information stored in the database.

[0230] "Means for inputting dietary restrictions and nutritional requirements" is a function that provides an interface for users to input information about their allergies, ingredients they want to avoid, specific nutritional requirements, and so on.

[0231] The "means for transmitting dietary restrictions and nutritional conditions to the server" is a function for transferring information entered by the user to the server and processing it.

[0232] "Means for using a generative model to generate products and meal plans that meet dietary restrictions and nutritional requirements" is a function that uses the constructed generative model to calculate and generate products and meal plans that meet the user's requirements.

[0233] "Means for presenting generated products and meal plans to users" refers to a function that displays products and meal plans generated by the server on the user's device (such as a smartphone).

[0234] "A means of scanning barcodes using a smartphone when selecting products in a physical store...and presenting the results to the user" refers to a function that reads the barcode of a product with a smartphone when the user is shopping in a store, compares the product information with the user's conditions, and notifies the user in real time whether the product is a match.

[0235] The present invention provides a system that allows people who have allergies, illnesses, dietary restrictions during pregnancy, or who need nutritional management for building a healthy body to easily select commercially available foods and boxed lunches. This system acquires product information via a network and provides products and meal plans that match the user's dietary restrictions and nutritional requirements. Specific embodiments of the system are described below.

[0236] Obtaining and storing product information

[0237] The server obtains product information from online supermarkets and bento shops via API or data files. This product information includes the product name, nutritional value information, ingredient list, and allergen information. The obtained product information is stored in a database.

[0238] Learning and Generative Model Building

[0239] The server uses machine learning algorithms (e.g., deep learning) to build a generative model based on the product information stored in the database. This generative model learns detailed information about the product and can make predictions and classifications for new data.

[0240] Input from the user

[0241] Users use devices such as smartphones or computers to input their own dietary restrictions and nutritional requirements, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on their health status.

[0242] Sending and matching conditions

[0243] The user's dietary restrictions and nutritional requirements are sent from the device to the server, which uses a generative model to generate products, lunch boxes, and even daily meal plans that fit the user's requirements, filtering the foods that match the requirements based on information stored in the database.

[0244] Proposals and Presentations

[0245] The server sends the generated product list and meal plan to the user's device. The device displays the suggestions sent from the server to the user. This allows the user to easily check foods and meal plans that fit their dietary restrictions and nutritional requirements. The user reviews the suggested products and selects the products they wish to purchase. The selected products are added to the cart, and the user can proceed with the purchase.

[0246] Examples of applications in physical stores

[0247] When selecting a product in a physical store, a user can scan the product's barcode using their smartphone. The server uses the scanned barcode information to match product information with the user's input criteria. The matching results are presented to the user in real time, and the server determines whether the conditions are met and displays the results. For example, if a user has conditions such as "egg allergy" and "desire to avoid caffeine," the user enters these conditions via their smartphone. When a product is scanned in a physical store, the server uses a generative model to determine whether the product matches these conditions from the database and displays the results on the smartphone. Suggested foods include caffeine-free beverages and egg-free ingredients. Users can review these suggestions and make a safe selection, eliminating the need to search for foods that meet multiple conditions.

[0248] Prompt Sentence Examples

[0249] A concrete example of an input prompt for a generative AI model could be in the form of text like this:

[0250] Create a system that determines whether a user's dietary restrictions or allergies are met based on a scenario in which the user scans a product's barcode with their smartphone while shopping in a store. Product information is retrieved from an API and includes allergen information and ingredients. The user's conditions are egg allergy and caffeine avoidance. If the conditions are met, display a message saying "Conditions met." If not, display a message saying "Conditions not met." Please also provide specific code examples.

[0251] The above is a specific embodiment for carrying out the present invention, which enables a user to select appropriate products in real time while shopping in a physical store.

[0252] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0253] Step 1:

[0254] The server obtains product information via the network. Specifically, the server collects product information from online supermarkets and bento shops via API or data files. This product information includes the product name, nutritional value information, ingredient list, allergen information, etc. The input is data from an external API or file, and the output is the obtained product information. The server saves this information in a database.

[0255] Step 2:

[0256] The server learns from the product information stored in the database and builds a generative model. The server uses machine learning algorithms (e.g., deep learning) to learn detailed information about the products. The input is the product information stored in the database and the output is the generated model. This generative model is used to make predictions and classifications on new data.

[0257] Step 3:

[0258] Users use their smartphones or computers to input their own dietary restrictions and nutritional requirements. Specifically, they use the smartphone application screen to input allergy information, ingredients to avoid, specific nutritional requirements, etc. The user's condition information is input, and these conditions are sent to the server as output.

[0259] Step 4:

[0260] The server receives the user's dietary restrictions and nutritional requirements sent from the device. The server uses a generative model based on the received requirements to generate matching products and meal plans. The input is the user's requirements, and the output is a list of matching products and meal plans. The server filters the product information stored in the database to find foods that match the requirements.

[0261] Step 5:

[0262] The server sends the generated product list and meal plan to the user's device. The device displays the suggestions sent from the server to the user. The input is the generated product list and meal plan from the server, and the output is the suggestions displayed to the user on the device screen. The user can easily check foods and meal plans that fit their own dietary restrictions and nutritional requirements.

[0263] Step 6:

[0264] When a user selects a product in a physical store, they use their smartphone to scan the product's barcode. The terminal acquires the scanned barcode information and sends it to a server. The input is the barcode scanned by the smartphone, and the output is the barcode information sent to the server.

[0265] Step 7:

[0266] The server receives the scanned barcode information and retrieves the product information from the database. It then compares it with the user's input conditions. The server uses a generative model to match the scanned product information with the user's conditions and determine whether the conditions are met. The input is the barcode information and the user's conditions, and the output is the result of a judgment on whether the conditions are met.

[0267] Step 8:

[0268] The server sends the judgment result to the user's terminal. The terminal displays the result to the user. The input is the judgment result sent from the server, and the output is the matching result displayed on the terminal screen. The user can check the display and determine in real time whether the condition is met.

[0269] The above are the specific processing steps for carrying out the present invention, which enable users to easily find and select products that meet their requirements in real time while shopping in a physical store.

[0270] 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.

[0271] ---

[0272] This invention is a system that provides products and meal plans that match a user's dietary restrictions and nutritional requirements, and aims to provide more personalized suggestions to each user by combining it with an emotion engine that recognizes the user's emotions. This system obtains product information via a network and provides products and meal plans that match the user's requirements.

[0273] Obtaining and storing product information

[0274] server

[0275] Product information is obtained from online supermarkets and bento shops via API or data files, including product names, nutritional information, ingredient lists, and allergen information.

[0276] The obtained product information is saved in the database.

[0277] Learning and Generative Model Building

[0278] server

[0279] Based on the product information stored in the database, a machine learning algorithm (e.g., deep learning) is used to build a generative model. The generative model learns the product information and makes predictions and classifications for newly input data.

[0280] Input from the user

[0281] User

[0282] Users can use devices such as smartphones or computers to input their own dietary restrictions and nutritional requirements, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on their health status.

[0283] Sending and matching conditions

[0284] Terminal

[0285] The dietary restrictions and nutritional conditions entered by the user are sent to the server.

[0286] server

[0287] The server receives the conditions sent by the user and uses the generative model to match the product information in the database with the user's conditions and filter out matching products and meal plans.

[0288] Emotion recognition and suggestion adjustment

[0289] Terminal

[0290] The emotion engine uses the user's device's camera and microphone to recognize emotions from the user's facial expressions and voice. This feature is activated during initial setup or regular use.

[0291] server

[0292] Based on the emotional state recognized by the emotion engine, the server will tailor the recommendations, for example, if the user is feeling stressed, it will suggest foods and drinks that have a relaxing effect.

[0293] Proposals and Presentations

[0294] server

[0295] Based on the results of the filtering and sentiment engine, it generates product lists and daily meal plans tailored to individual user requirements.

[0296] server

[0297] The generated proposal content is transmitted to the user's terminal.

[0298] Terminal

[0299] The device displays the suggestions sent from the server to the user, allowing the user to easily check foods and meal plans that fit their dietary restrictions and nutritional requirements.

[0300] User

[0301] Users can review the suggested products and meal plans, select the products they want to purchase, and the selected products are added to their cart for further checkout.

[0302] Specific examples

[0303] For example, if a user inputs the conditions "I have an egg allergy" and "I want to avoid caffeine," the server uses the generative model to filter products and meal plans from the database that match these conditions. If the emotion engine uses the smartphone's camera and microphone to identify that the user is feeling "stressed," suggestions might include decaffeinated herbal teas and foods that help reduce stress.

[0304] The system allows users to select foods appropriate for their emotional state, as well as their dietary restrictions and nutritional requirements, for a more personalized service. It can also provide meal plans tailored to individual needs for users who need to manage diabetes or follow specific diet plans.

[0305] ---

[0306] The processing flow will be explained below.

[0307] ---

[0308] Step 1:

[0309] server

[0310] Product information is obtained from online supermarkets and bento shops via API or data files.

[0311] Product information includes product name, nutritional information, ingredient list, and allergen information.

[0312] The obtained product information is saved in the database.

[0313] Step 2:

[0314] server

[0315] Based on the product information stored in the database, a generative model is constructed using machine learning algorithms (e.g., deep learning).

[0316] The generative model learns product information and is given the ability to make predictions and classifications on newly input data.

[0317] Step 3:

[0318] User

[0319] Users enter their own dietary restrictions and nutritional requirements using a device such as a smartphone or computer.

[0320] Inputs include allergy information, avoidance of certain food ingredients, and nutritional requirements based on health conditions.

[0321] Step 4:

[0322] Terminal

[0323] The dietary restrictions and nutritional conditions entered by the user are sent to the server.

[0324] Step 5:

[0325] server

[0326] Receive dietary restrictions and nutritional requirements submitted by users.

[0327] It uses a generative model to match product information in a database with the user's criteria and filter out matching products and meal plans.

[0328] Step 6:

[0329] Terminal

[0330] The emotion engine uses the camera and microphone on the user's device to recognize emotions from the user's facial expressions and voice.

[0331] Emotion recognition is performed when the user inputs dietary restrictions and nutritional requirements.

[0332] Step 7:

[0333] server

[0334] The emotional state of the user recognized by the emotion engine is received and the suggestions are adjusted accordingly.

[0335] For example, if a user is feeling stressed, the app suggests foods and drinks that have a relaxing effect.

[0336] Step 8:

[0337] server

[0338] Based on the tailored suggestions, it generates a product list and daily meal plan tailored to the individual user's requirements.

[0339] Step 9:

[0340] server

[0341] The generated proposal content is transmitted to the user's terminal.

[0342] Step 10:

[0343] Terminal

[0344] The terminal displays the proposal sent from the server to the user.

[0345] For example, it could be displayed in the format "Recommended breakfast: Decaffeinated coffee and eggless sandwich."

[0346] Step 11:

[0347] User

[0348] Review the suggested products and meal plans and select the products you want to purchase.

[0349] The selected items will be added to your cart and you can proceed with the purchase.

[0350] ---

[0351] Through this specific processing step, users can easily select products and meal plans that fit their emotional state as well as their dietary restrictions and nutritional requirements.

[0352] Example 2

[0353] 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."

[0354] In modern society, users have a wide variety of dietary restrictions and nutritional requirements. Furthermore, users often want to make choices based on their emotional state. However, conventional systems have been inadequate in providing products and meal plans that take the user's emotional state into account, making it difficult to provide personalized recommendations. Furthermore, incorporating emotion recognition technology into a meal recommendation system would enable recommendations that are more tailored to individual users' needs, but no system has been able to achieve this.

[0355] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring product information via a network, means for storing the product information in a database, means for constructing a generative model that learns based on the product information stored in the database, means for analyzing the user's facial expressions and voice to recognize emotions, means for adjusting the generated products and meal plans based on the recognized emotions, and means for presenting the adjusted products and meal plans to the user. This enables the user to receive personalized products and meal plans that are tailored to their emotional state in addition to their dietary restrictions and nutritional requirements.

[0356] A "network" is a communications system that connects multiple computers or devices to send and receive data.

[0357] "Product information" refers to information about the product's characteristics and contents, such as the product's name, nutritional value information, ingredient list, and allergen information.

[0358] A "database" is a system or software that allows data to be efficiently stored, searched, and edited.

[0359] A "generative model" is a model built using machine learning algorithms to make predictions or classifications based on specific data.

[0360] A "user" is an individual or group that uses this system, and is the entity that provides input and instructions to the system.

[0361] "Dietary restrictions" refers to restricting the intake of certain foods or ingredients based on allergies, health conditions, religious beliefs, etc.

[0362] "Nutritional requirements" are requirements or conditions regarding a diet that a user follows with a focus on consuming specific nutrients.

[0363] A "server" is a computer system that provides data and services to other computers on a network.

[0364] "Emotion recognition" is a technology that analyzes and identifies a user's current emotional state from their facial expressions and voice.

[0365] "Personalized recommendations" refers to product and meal plan recommendations optimized for each individual user's dietary restrictions, nutritional requirements, and even emotional state.

[0366] The present invention is a system that provides products and meal plans that match a user's dietary restrictions and nutritional requirements, and aims to provide more personalized suggestions to each user by combining it with an emotion engine that recognizes the user's emotions. This system is implemented in the following steps.

[0367] Obtaining and storing product information

[0368] server

[0369] The server obtains product information via the network. Specifically, it collects product information from online supermarkets and bento shops via API or data files. This product information includes the product name, nutritional value information, ingredient list, and allergen information.

[0370] The acquired product information is stored in a database. MySQL or PostgreSQL are suitable database management systems. The table that stores product information contains columns for basic product information, nutritional value, and allergen information.

[0371] Learning and Generative Model Building

[0372] server

[0373] The server uses machine learning algorithms to build generative models based on product information stored in a database, using libraries such as TensorFlow and PyTorch.

[0374] Preprocess the data, handle missing values, normalize, etc. Then use the preprocessed data to train a model and build a generative model that classifies products that meet certain criteria.

[0375] The trained model is saved as a file and used for subsequent prediction processing.

[0376] Input from the user

[0377] User

[0378] Users use devices such as smartphones or PCs to input their own dietary restrictions and nutritional requirements. This input includes allergy information, avoidance of specific food ingredients, nutritional requirements based on health status, etc. The input information is sent to the server via the device's application.

[0379] Sending and matching conditions

[0380] Terminal

[0381] The device sends the dietary restrictions and nutritional requirements entered by the user to the server, for example, by sending serialized data in JSON format via an HTTP POST request.

[0382] server

[0383] The server uses the generative model to match product information based on the received user criteria, calculates a score for products that match the criteria, and filters out the top candidates.

[0384] The filtered product list is temporarily saved.

[0385] Emotion recognition and suggestion adjustment

[0386] Terminal

[0387] The device's emotion engine uses the camera and microphone to analyze the user's facial expressions and voice to recognize emotions. OpenCV and Emotion API are suitable software for this purpose.

[0388] The recognized emotion data is sent to the server in JSON format.

[0389] server

[0390] The server then adjusts its suggestions based on the received emotional data, for example, recommending foods and drinks that have a relaxing effect if the user is feeling stressed.

[0391] Proposals and Presentations

[0392] server

[0393] The server generates tailored recommendations and sends them to the user's device, which are presented as product lists and daily meal plans.

[0394] Terminal

[0395] The terminal analyzes the proposals sent from the server and displays them on a user interface, for example, using a tree view or list view to display product information.

[0396] User

[0397] Users can review the suggested products and meal plans, select the products they want to purchase, and the selected products are added to their cart for further checkout.

[0398] Specific examples

[0399] For example, if a user inputs the criteria "I have an egg allergy" and "I want to avoid caffeine," the server uses the generative model to filter products and meal plans from the database that fit those criteria. If the user's emotion engine recognizes "stress," suggestions might include decaffeinated herbal teas and foods that help reduce stress.

[0400] Prompt Sentence Examples

[0401] "I have an egg allergy and would like to avoid caffeine. Can you recommend any foods or drinks? I've also been feeling stressed lately."

[0402] In this way, the present invention can provide personalized products and meal plans tailored to a user's dietary restrictions, nutritional requirements, and emotional state, thereby enabling users to make better food choices and improve the quality of their diet.

[0403] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0404] Step 1: Retrieve and store product information

[0405] server

[0406] The server obtains product information via the network. Specifically, it collects product information from online supermarkets and bento shops via API or data files.

[0407] The server stores the retrieved product information in a database, including the product name, nutritional information, ingredient list, and allergen information.

[0408] Input: API endpoint URL of online supermarket or bento shop

[0409] Output: Product information stored in the database

[0410] Step 2: Building a training and generative model

[0411] server

[0412] The server reads product information from a database and builds a generative model using machine learning algorithms, such as TensorFlow and PyTorch.

[0413] Data preprocessing involves processing missing values ​​and normalization.

[0414] Train the model using the training data and save the model as a file.

[0415] Input: Product information retrieved from the database

[0416] Output: Trained generative model file

[0417] Step 3: User Input

[0418] User

[0419] Users can enter their dietary restrictions and nutritional requirements via smartphone or computer, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on health conditions.

[0420] Input: Information about dietary restrictions and nutritional requirements

[0421] Output: Input data saved on the device

[0422] Step 4: Sending and matching conditions

[0423] Terminal

[0424] The terminal converts the data entered by the user into JSON format and sends it to the server via an HTTP POST request.

[0425] Input: User's dietary restrictions and nutritional requirements

[0426] Output: JSON data sent to the server

[0427] server

[0428] The server analyzes the received user requirements, compares them with product information using a generative model, calculates a score for matching products, and filters out the top candidates.

[0429] Input: Received condition data in JSON format

[0430] Output: Filtered product list

[0431] Step 5: Recognize emotions and adjust suggestions

[0432] Terminal

[0433] The device's emotion engine uses the camera and microphone to analyze the user's facial expressions and voice to recognize emotions. OpenCV and Emotion API are suitable software for this purpose.

[0434] The recognized emotion data is sent to the server in JSON format.

[0435] Input: User's facial expressions and voice data

[0436] Output: Emotion data sent to the server

[0437] server

[0438] The server adjusts its suggestions based on the received emotional data. For example, if the user is feeling stressed, it will increase the number of products that have a relaxing effect.

[0439] Input: Received emotion data

[0440] Output: Tailored product list and meal plan

[0441] Step 6: Proposal and Presentation

[0442] server

[0443] The server generates the adjusted proposal and sends it to the user's device in JSON format.

[0444] Input: Tailored product list and meal plan

[0445] Output: JSON data sent to the terminal

[0446] Terminal

[0447] The terminal analyzes the proposals sent from the server and displays them in a user interface, for example, by displaying product information using a tree view or list view.

[0448] Input: JSON data received from the server

[0449] Output: Product information and meal plan presented to the user

[0450] Step 7: User Actions

[0451] User

[0452] Users can review the suggested products and meal plans, select the products they want to purchase, and the selected products are added to their cart for further checkout.

[0453] Input: User's choice

[0454] Output: List of items added to cart

[0455] (Application example 2)

[0456] 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."

[0457] Conventional meal plan suggestion systems can provide products and meal plans that meet a user's dietary restrictions and nutritional requirements, but they do not take into account the user's emotional state. As a result, they are unable to provide foods and meal plans that are optimal for the user's current emotional state, and further personalization is required.

[0458] 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.

[0459] In this invention, the server includes means for acquiring product information via a network, means for storing the product information in a database, means for constructing a generative model that learns based on the product information stored in the database, means for the user to input dietary restrictions and nutritional requirements, means for recognizing the user's emotions using a camera and a microphone, means for adjusting the content of suggestions based on the recognized emotions, and means for presenting the generated products and meal plans to the user. This makes it possible to provide highly personalized products and meal plans based on comprehensive data including the user's emotional state.

[0460] "Product information" refers to detailed product data that is acquired via a network and stored in a database, and includes nutritional values, ingredient lists, allergen information, and the like.

[0461] "Database" means an information system that stores product information and allows it to be accessed, searched, and updated.

[0462] A "generative model" is a model that is built using machine learning algorithms based on product information to generate products and meal plans that meet the user's requirements.

[0463] "Dietary restrictions and nutritional requirements" refers to dietary restrictions or requirements set by a user based on their own health condition, allergies, or requests to avoid certain ingredients.

[0464] The "camera and microphone" are visual and audio input devices for recognizing the user's facial expressions and voice, and are used in combination with the emotion engine.

[0465] "Means for recognizing emotions" refers to a system or algorithm that uses a camera and microphone to analyze the user's facial expressions and voice and determine the user's emotional state.

[0466] The "means for adjusting the proposal content" is a function for modifying or optimizing the content of the generated products or meal plans based on the user's emotional state recognized by the emotion engine.

[0467] The present invention is a system for proposing optimal products and meal plans based on a user's dietary restrictions, nutritional requirements, and emotional state. Specific embodiments of the system are described below.

[0468] Obtaining and storing product information

[0469] The server retrieves product information via the network and stores it in a database. Product information includes nutritional information, ingredient lists, and allergen information. This creates a foundation for quickly providing information that meets the user's requirements.

[0470] Learning and Generative Model Building

[0471] The server uses machine learning algorithms (e.g., deep learning) to build a generative model based on the product information stored in the database. The generative model learns the product information and makes predictions and classifications for newly input data.

[0472] Input from the user

[0473] Users use devices such as smartphones to input their own dietary restrictions and nutritional requirements, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on their health status.

[0474] Sending and matching conditions

[0475] The device sends the dietary restrictions and nutritional requirements entered by the user to the server, which then uses the generative model to match the user's requirements with product information in the database and filter out matching products and meal plans.

[0476] Emotion recognition and suggestion adjustment

[0477] The device uses a camera and microphone to recognize emotions from the user's facial expressions and voice. This function is activated during initial setup or regular use. The server then adjusts the suggestions based on the emotional state recognized by the emotion engine. For example, if the user is feeling stressed, it will suggest foods and drinks that have a relaxing effect.

[0478] Proposals and Presentations

[0479] Based on the results of the filtering and emotion engine, the server generates a product list and daily meal plan tailored to each user's individual requirements and sends it to the device. The device displays the suggestions sent from the server to the user, allowing the user to easily check foods and meal plans that suit their own dietary restrictions, nutritional requirements, and emotional state.

[0480] Users can review the suggested products and meal plans, select the products they want to purchase, and the selected products are added to their cart for further checkout.

[0481] Specific examples

[0482] For example, if a user inputs the conditions "I have an egg allergy" and "I want to avoid caffeine," the server uses the generative model to filter products and meal plans from the database that match these conditions. If the emotion engine uses the smartphone's camera and microphone to identify that the user is feeling "stressed," suggestions might include decaffeinated herbal teas and foods that help reduce stress.

[0483] Example prompt sentence:

[0484] "If a user inputs that they have an egg allergy and want to avoid caffeine, and the system detects through their smartphone's camera and microphone that they are feeling stressed, the system will suggest decaffeinated herbal teas and foods that help reduce stress."

[0485] In this way, it becomes possible to offer highly personalized products and meal plans based on comprehensive data, including the user's emotional state.

[0486] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0487] Step 1:

[0488] The server retrieves product information over the network. Inputs include API endpoints and data files, and outputs a product information dataset containing product names, nutritional information, ingredient lists, allergen information, etc. The data is received in JSON format and stored in an internal database.

[0489] Step 2:

[0490] The server uses deep learning algorithms to build a generative model based on product information stored in an internal database. The input includes product information from the database, and the output is a generative model for predicting products and meal plans that meet the user's criteria. Specifically, machine learning frameworks such as Keras and TensorFlow are used.

[0491] Step 3:

[0492] Users input their dietary restrictions and nutritional requirements using a device such as a smartphone. The input data includes allergy information, avoidance of specific food ingredients, and nutritional requirements based on health conditions. The device then transmits this data to a server.

[0493] Step 4:

[0494] The server receives the dietary restrictions and nutritional requirements sent by the user and performs filtering based on those requirements. The input includes the user's requirements data and product information in the database, and the output is a list of products and meal plans that match the requirements.

[0495] Step 5:

[0496] The device uses the user's camera and microphone to recognize emotions from the user's facial expressions and voice. Inputs include camera feed and audio input, and outputs provide data indicating the user's emotional state. An emotion engine analyzes information such as whether the user is feeling stressed.

[0497] Step 6:

[0498] The server adjusts the recommendations based on the user's perceived emotional state. The input includes the user's emotional data and the filtering results, and the output is a product list or meal plan that takes the user's emotional state into account. For example, if the user is feeling stressed, the server suggests foods and drinks that have a relaxing effect.

[0499] Step 7:

[0500] The server sends the generated products and meal plans to the device. The input includes the final product list and meal plan, and the output is the suggestions displayed on the user's device. The device displays the suggestions to the user, allowing the user to identify foods and meal plans that fit their dietary restrictions, nutritional requirements, and emotional state.

[0501] Step 8:

[0502] The user reviews the suggested products and meal plans and selects the products they want to purchase. The input includes product information selected from the suggestions, and the output is a list of products added to the cart. The user can then proceed with the purchase process based on this list.

[0503] 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.

[0504] 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.

[0505] 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.

[0506] [Second embodiment]

[0507] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0508] 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.

[0509] 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).

[0510] 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.

[0511] 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.

[0512] 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).

[0513] 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.

[0514] 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.

[0515] 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.

[0516] 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.

[0517] 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.

[0518] 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."

[0519] ---

[0520] The present invention is a system that allows people who have allergies, illnesses, dietary restrictions during pregnancy, or who need nutritional management for building a healthy body to easily select commercially available foods and boxed lunches. This system acquires product information via a network and provides products and meal plans that match the user's dietary restrictions and nutritional requirements. Specific embodiments of the system are described below.

[0521] Obtaining and storing product information

[0522] server

[0523] The server obtains product information from online supermarkets and bento shops via API or data files, including product names, nutritional information, ingredient lists, and allergen information.

[0524] The acquired product information is stored in a database.

[0525] Learning and Generative Model Building

[0526] server

[0527] Using product information stored in a database, a machine learning algorithm (e.g., deep learning) is used to build a generative model that learns detailed information about the product and can make predictions and classifications for new data.

[0528] Input from the user

[0529] User

[0530] Users use devices such as smartphones or computers to input their own dietary restrictions and nutritional requirements, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on their health status.

[0531] Sending and matching conditions

[0532] Terminal

[0533] The dietary restrictions and nutritional conditions entered by the user are sent from the terminal to the server.

[0534] server

[0535] The server uses the generative model to generate products, lunch boxes, and even daily meal plans that match the user's criteria, filtering the foods that match the criteria based on information stored in the database.

[0536] Proposals and Presentations

[0537] server

[0538] The server sends the generated product list and meal plan to the user's terminal.

[0539] Terminal

[0540] The device displays the suggestions sent from the server to the user, allowing the user to easily find foods and meal plans that fit their dietary restrictions and nutritional requirements.

[0541] User

[0542] The user can then review the suggested products and select the ones they wish to purchase. The selected products are added to the cart and the user can proceed with the purchase.

[0543] Specific examples

[0544] For example, if a user has conditions such as "egg allergy" and "avoid caffeine," they can input these conditions via their smartphone. The server uses the generative model to filter products and meal plans from the database that match these conditions and generate suggestions. Suggested foods include caffeine-free beverages and egg-free ingredients. Users can review these suggestions and safely select them, eliminating the need to go through the trouble of searching for foods that meet multiple conditions.

[0545] This system allows customers with multiple dietary restrictions to easily select foods that suit them, significantly reducing the burden of dietary management. It can also provide meal plans tailored to individual needs for users who need to manage diabetes or who are following specific diet plans.

[0546] ---

[0547] The processing flow will be explained below.

[0548] ---

[0549] Step 1:

[0550] server

[0551] Product information is obtained from online supermarkets and bento shops via API or data files.

[0552] Product information includes product name, nutritional information, ingredient list, and allergen information.

[0553] The obtained product information is saved in the database.

[0554] Step 2:

[0555] server

[0556] Based on the product information stored in the database, a generative model is constructed using machine learning algorithms (e.g., deep learning).

[0557] Generative models are trained with product information that can later be used for prediction and classification.

[0558] Step 3:

[0559] User

[0560] Users enter their dietary restrictions and nutritional requirements using a device such as a smartphone or computer.

[0561] For example, enter conditions such as "egg allergy" or "want to avoid caffeine."

[0562] Step 4:

[0563] Terminal

[0564] The dietary restrictions and nutritional conditions entered by the user are sent to the server.

[0565] Step 5:

[0566] server

[0567] The server receives the conditions sent by the user.

[0568] It uses a generative model to match product information in the database with the user's criteria and filter out matching products and meal plans.

[0569] Step 6:

[0570] server

[0571] Based on the filtered product information, proposals tailored to individual user conditions are generated.

[0572] Suggestions include a list of suitable products and a daily meal plan.

[0573] Step 7:

[0574] server

[0575] The generated proposal content is transmitted to the user's terminal.

[0576] Step 8:

[0577] Terminal

[0578] The terminal displays the proposal sent from the server to the user.

[0579] For example, it could be displayed in the format "Recommended breakfast: Decaffeinated coffee and eggless sandwich."

[0580] Step 9:

[0581] User

[0582] Check out suggested products and meal plans.

[0583] Select the product you want to purchase and add it to your cart.

[0584] Proceed with the purchase of items added to your cart.

[0585] ---

[0586] In this way, users can easily select products that fit their dietary restrictions and nutritional requirements. Furthermore, the recommendations provided are highly accurate thanks to the generative model.

[0587] Example 1

[0588] 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."

[0589] Currently, when selecting commercially available foods or bento boxes, it is difficult for users to find products that meet their allergies, illnesses, dietary restrictions during pregnancy, or nutritional management requirements for building a healthy body. This poses a problem in that it takes a great deal of time and effort for users to select foods that meet their requirements.

[0590] 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.

[0591] In this invention, the server includes means for acquiring product information via a network, means for storing the product information in a database, means for building a generative AI model that learns based on the product information stored in the database, means for the user to input dietary restrictions and nutritional requirements, means for transmitting the dietary restrictions and nutritional requirements input by the user to the server, means for the server to use the generative AI model to generate products and meal plans that meet the dietary restrictions and nutritional requirements, means for presenting the generated products and meal plans to the user, and means for adding products selected by the user from the presented products and meal plans to the purchasing process. This allows the user to easily select foods that meet their requirements and significantly reduces the burden of dietary management.

[0592] A "network" is a system in which multiple computers or devices are connected so that they can communicate with each other.

[0593] "Product information" refers to information about a product that includes data such as the product's name, nutritional value, ingredient list, and allergen information.

[0594] A "database" is a system for efficiently storing, retrieving, and managing organized data.

[0595] A "generative AI model" is a model that has been trained using machine learning algorithms to make new predictions or classifications based on data.

[0596] "User" refers to any individual or organization that uses the system or service.

[0597] A "dietary restriction" is a restriction that prevents the intake of certain foods or ingredients for health reasons.

[0598] "Nutritional requirements" are the nutrient requirements you need or want to avoid based on a specific health condition or goal.

[0599] A "server" is a computer system that provides services to clients over a network.

[0600] A "product list" is a list that refers to a collection of products selected based on specific conditions.

[0601] A "meal plan" refers to a suggestion or plan for meals over a day or period of time.

[0602] A "purchase process" refers to a series of procedures or steps a user takes to purchase a selected product.

[0603] The present invention provides a system that allows people who have allergies, illnesses, dietary restrictions during pregnancy, or who need nutritional management for building a healthy body to easily select commercially available foods and boxed lunches. This system acquires product information via a network and provides products and meal plans that match the user's dietary restrictions and nutritional requirements. Specific embodiments of the system are described below.

[0604] Obtaining and storing product information

[0605] server

[0606] The server collects product information from online supermarkets and bento shops via API or data files, including product names, nutritional information, ingredient lists, and allergen information.

[0607] The server stores the acquired product information in a database.

[0608] Specific examples

[0609] The server communicates with the online supermarket's API every day at midnight to retrieve new and updated product information, and then adds or updates this information to the database.

[0610] Example prompt sentence:

[0611] "Please use the Rakuten Market API to update all product information daily and store it in the database."

[0612] Learning and Generative Model Building

[0613] server

[0614] The server uses machine learning algorithms (e.g., deep learning) to train a generative AI model based on the product information stored in the database. The generative AI model learns detailed information about the product and makes predictions and classifications based on the user's criteria.

[0615] Specific examples

[0616] The server uses TensorFlow to train a new model each week based on the stored product information, which can then score each product taking into account allergen information and nutritional value.

[0617] Example prompt sentence:

[0618] "Use TensorFlow to build a model that learns all the product information in your database and classifies products that meet the user's criteria."

[0619] Input from the user

[0620] User

[0621] Users use devices such as smartphones or computers to input their own dietary restrictions and nutritional requirements, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on their health status.

[0622] Specific examples

[0623] The user launches the app and enters "egg allergy" and "caffeine avoidance" on the profile screen, which updates the user profile within the app.

[0624] Example prompt sentence:

[0625] "Enter any allergies or food ingredients you are avoiding. For example, egg allergy, caffeine avoidance."

[0626] Sending and matching conditions

[0627] Terminal

[0628] The dietary restrictions and nutritional conditions entered by the user are sent from the terminal to the server.

[0629] server

[0630] Once the server receives the user's criteria, it stores them in a database and then uses a deep learning model to filter products that match the criteria. Based on the filtered results, it generates a product list and a daily meal plan that meets the user's criteria.

[0631] Specific examples

[0632] The device sends the conditions "egg allergy" and "caffeine avoidance" to the server. The server receives this and uses the database and deep learning model to search for products that meet the conditions. For example, "egg-free bread" and "caffeine-free drinks" are matched.

[0633] Example prompt sentence:

[0634] "Match products based on input criteria and generate a daily meal plan using a generative model."

[0635] Proposals and Presentations

[0636] server

[0637] The server generates a product list and meal plan that meets the user's requirements and sends it to the user's terminal.

[0638] Terminal

[0639] The terminal displays the product list and meal plan sent from the server to the user.

[0640] User

[0641] Users can review the suggested products and meal plans and select the products they wish to purchase, which are then added to their cart and they can proceed with the checkout.

[0642] Specific examples

[0643] The server sends "egg-free bread" and "caffeine-free beverage" to the terminal. The user confirms this and adds the items they want to purchase to their cart. They then proceed with the purchase.

[0644] Example prompt sentence:

[0645] "Design a UI that suggests and displays products and meal plans that match the user's criteria."

[0646] This system allows users with allergies or dietary restrictions to easily select foods that suit them, significantly reducing the burden of dietary management. It also accommodates users following specific diet plans.

[0647] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0648] Step 1:

[0649] The server acquires the product information via the network.

[0650] Input: API request from online supermarket or bento shop

[0651] Specific operation: The server executes an API request every day at midnight to obtain new products and updated information.

[0652] Output: Product information returned from the API (product name, nutritional information, ingredient list, allergen information)

[0653] Step 2:

[0654] The server stores the acquired product information in a database.

[0655] Input: Product information obtained in Step 1

[0656] Specific operation: The server performs the process of adding or updating the product information in the database.

[0657] Output: Product information stored in the database

[0658] Step 3:

[0659] The server builds a generative AI model based on product information stored in the database.

[0660] Input: Product information stored in the database

[0661] Specific operation: The server uses TensorFlow to train a deep learning model and build a model based on product information.

[0662] Output: The generated deep learning model

[0663] Step 4:

[0664] Users input their dietary restrictions and nutritional requirements via their smartphone or computer.

[0665] Input: User's dietary restrictions or nutritional requirements (e.g., egg allergy, caffeine avoidance)

[0666] Specific operation: The user enters the conditions in the device app, which are then saved in the system.

[0667] Output: Entered dietary restrictions and nutritional conditions

[0668] Step 5:

[0669] The terminal transmits the conditions entered by the user to the server.

[0670] Input: Input data for dietary restrictions and nutritional conditions

[0671] Specific operation: The terminal executes a request to send the user's conditions to the server.

[0672] Output: User criteria sent to server

[0673] Step 6:

[0674] The server receives the user's requirements and uses the database and generative AI model to generate products and meal plans that meet the requirements.

[0675] Input: User conditions sent to the server, product information stored in the database, generated deep learning model

[0676] What it does: The server uses the user's criteria as filtering criteria to search and score products in the database and generate products and meal plans that best fit the criteria.

[0677] Output: A list of products and meal plans that match your criteria

[0678] Step 7:

[0679] The server transmits the generated product list and meal plan to the user's terminal.

[0680] Input: A list of products or meal plans that match your criteria

[0681] Specific operation: The server generates the proposal and executes a request to send it to the user's device.

[0682] Output: Product list and meal plan sent to the device

[0683] Step 8:

[0684] The terminal displays the product list and meal plan sent from the server to the user.

[0685] Input: Product list or meal plan sent from the server

[0686] Specific operation: The device displays the received product list and meal plan on the screen and notifies the user.

[0687] Output: Displayed product list and meal plan

[0688] Step 9:

[0689] The user reviews the suggested products and meal plans and selects the products they wish to purchase.

[0690] Input: Displayed product list or meal plan

[0691] Specific operation: The user selects the product they want to purchase on the screen and adds it to their cart.

[0692] Output: Items added to cart

[0693] Step 10:

[0694] The user then carries out the procedure to purchase the product added to the cart.

[0695] Input: Items added to cart

[0696] What happens: The user proceeds to the checkout screen, enters payment information, and completes the order.

[0697] Output: Completed order items

[0698] (Application example 1)

[0699] 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."

[0700] People who have dietary restrictions or nutritional needs have difficulty finding foods that do not contain allergens or specific ingredients when choosing commercially available foods or bento boxes. Furthermore, there are few ways to check this information in real time while shopping in physical stores, which places a significant burden on them when making appropriate product selections.

[0701] 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.

[0702] In this invention, the server includes: means for acquiring product information via a network; means for storing the product information in a database; means for constructing a generative model that learns based on the product information stored in the database; means for allowing a user to input dietary restrictions and nutritional requirements; means for transmitting the dietary restrictions and nutritional requirements input by the user to the server; means for the server to use the generative model to generate products and meal plans that meet the dietary restrictions and nutritional requirements; means for presenting the generated products and meal plans to the user; and means for scanning a barcode using a smartphone when a user selects a product in a physical store, comparing the scanned product information with the user's input conditions to determine whether the conditions are met, and presenting the result to the user. This enables users to easily find and select products that meet their conditions in real time while shopping in a physical store.

[0703] "Means for acquiring product information via a network" refers to a function for externally collecting information about various products, such as product names, nutritional value information, ingredient lists, and allergen information, via a network such as the Internet.

[0704] The "means for saving product information in a database" is a function for recording acquired product information in a database in a structured format for later retrieval and analysis.

[0705] The "means for constructing a generative model" is a function that uses a machine learning algorithm, such as deep learning, to create a model for generating products and meal plans based on product information stored in the database.

[0706] "Means for inputting dietary restrictions and nutritional requirements" is a function that provides an interface for users to input information about their allergies, ingredients they want to avoid, specific nutritional requirements, and so on.

[0707] The "means for transmitting dietary restrictions and nutritional conditions to the server" is a function for transferring information entered by the user to the server and processing it.

[0708] "Means for using a generative model to generate products and meal plans that meet dietary restrictions and nutritional requirements" is a function that uses the constructed generative model to calculate and generate products and meal plans that meet the user's requirements.

[0709] "Means for presenting generated products and meal plans to users" refers to a function that displays products and meal plans generated by the server on the user's device (such as a smartphone).

[0710] "A means of scanning barcodes using a smartphone when selecting products in a physical store...and presenting the results to the user" refers to a function that reads the barcode of a product with a smartphone when the user is shopping in a store, compares the product information with the user's conditions, and notifies the user in real time whether the product is a match.

[0711] The present invention provides a system that allows people who have allergies, illnesses, dietary restrictions during pregnancy, or who need nutritional management for building a healthy body to easily select commercially available foods and boxed lunches. This system acquires product information via a network and provides products and meal plans that match the user's dietary restrictions and nutritional requirements. Specific embodiments of the system are described below.

[0712] Obtaining and storing product information

[0713] The server obtains product information from online supermarkets and bento shops via API or data files. This product information includes the product name, nutritional value information, ingredient list, and allergen information. The obtained product information is stored in a database.

[0714] Learning and Generative Model Building

[0715] The server uses machine learning algorithms (e.g., deep learning) to build a generative model based on the product information stored in the database. This generative model learns detailed information about the product and can make predictions and classifications for new data.

[0716] Input from the user

[0717] Users use devices such as smartphones or computers to input their own dietary restrictions and nutritional requirements, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on their health status.

[0718] Sending and matching conditions

[0719] The user's dietary restrictions and nutritional requirements are sent from the device to the server, which uses a generative model to generate products, lunch boxes, and even daily meal plans that fit the user's requirements, filtering the foods that match the requirements based on information stored in the database.

[0720] Proposals and Presentations

[0721] The server sends the generated product list and meal plan to the user's device. The device displays the suggestions sent from the server to the user. This allows the user to easily check foods and meal plans that fit their dietary restrictions and nutritional requirements. The user reviews the suggested products and selects the products they wish to purchase. The selected products are added to the cart, and the user can proceed with the purchase.

[0722] Examples of applications in physical stores

[0723] When selecting a product in a physical store, a user can scan the product's barcode using their smartphone. The server uses the scanned barcode information to match product information with the user's input criteria. The matching results are presented to the user in real time, and the server determines whether the conditions are met and displays the results. For example, if a user has conditions such as "egg allergy" and "desire to avoid caffeine," the user enters these conditions via their smartphone. When a product is scanned in a physical store, the server uses a generative model to determine whether the product matches these conditions from the database and displays the results on the smartphone. Suggested foods include caffeine-free beverages and egg-free ingredients. Users can review these suggestions and make a safe selection, eliminating the need to search for foods that meet multiple conditions.

[0724] Prompt Sentence Examples

[0725] A concrete example of an input prompt for a generative AI model could be in the form of text like this:

[0726] Create a system that determines whether a user's dietary restrictions or allergies are met based on a scenario in which the user scans a product's barcode with their smartphone while shopping in a store. Product information is retrieved from an API and includes allergen information and ingredients. The user's conditions are egg allergy and caffeine avoidance. If the conditions are met, display a message saying "Conditions met." If not, display a message saying "Conditions not met." Please also provide specific code examples.

[0727] The above is a specific embodiment for carrying out the present invention, which enables a user to select appropriate products in real time while shopping in a physical store.

[0728] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0729] Step 1:

[0730] The server obtains product information via the network. Specifically, the server collects product information from online supermarkets and bento shops via API or data files. This product information includes the product name, nutritional value information, ingredient list, allergen information, etc. The input is data from an external API or file, and the output is the obtained product information. The server saves this information in a database.

[0731] Step 2:

[0732] The server learns from the product information stored in the database and builds a generative model. The server uses machine learning algorithms (e.g., deep learning) to learn detailed information about the products. The input is the product information stored in the database and the output is the generated model. This generative model is used to make predictions and classifications on new data.

[0733] Step 3:

[0734] Users use their smartphones or computers to input their own dietary restrictions and nutritional requirements. Specifically, they use the smartphone application screen to input allergy information, ingredients to avoid, specific nutritional requirements, etc. The user's condition information is input, and these conditions are sent to the server as output.

[0735] Step 4:

[0736] The server receives the user's dietary restrictions and nutritional requirements sent from the device. The server uses a generative model based on the received requirements to generate matching products and meal plans. The input is the user's requirements, and the output is a list of matching products and meal plans. The server filters the product information stored in the database to find foods that match the requirements.

[0737] Step 5:

[0738] The server sends the generated product list and meal plan to the user's device. The device displays the suggestions sent from the server to the user. The input is the generated product list and meal plan from the server, and the output is the suggestions displayed to the user on the device screen. The user can easily check foods and meal plans that fit their own dietary restrictions and nutritional requirements.

[0739] Step 6:

[0740] When a user selects a product in a physical store, they use their smartphone to scan the product's barcode. The terminal acquires the scanned barcode information and sends it to a server. The input is the barcode scanned by the smartphone, and the output is the barcode information sent to the server.

[0741] Step 7:

[0742] The server receives the scanned barcode information and retrieves the product information from the database. It then compares it with the user's input conditions. The server uses a generative model to match the scanned product information with the user's conditions and determine whether the conditions are met. The input is the barcode information and the user's conditions, and the output is the result of a judgment on whether the conditions are met.

[0743] Step 8:

[0744] The server sends the judgment result to the user's terminal. The terminal displays the result to the user. The input is the judgment result sent from the server, and the output is the matching result displayed on the terminal screen. The user can check the display and determine in real time whether the condition is met.

[0745] The above are the specific processing steps for carrying out the present invention, which enable users to easily find and select products that meet their requirements in real time while shopping in a physical store.

[0746] 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.

[0747] ---

[0748] This invention is a system that provides products and meal plans that match a user's dietary restrictions and nutritional requirements, and aims to provide more personalized suggestions to each user by combining it with an emotion engine that recognizes the user's emotions. This system obtains product information via a network and provides products and meal plans that match the user's requirements.

[0749] Obtaining and storing product information

[0750] server

[0751] Product information is obtained from online supermarkets and bento shops via API or data files. This information includes the product name, nutritional value, ingredient list, and allergen information.

[0752] The obtained product information is saved in the database.

[0753] Learning and Generative Model Building

[0754] server

[0755] Based on the product information stored in the database, a machine learning algorithm (e.g., deep learning) is used to build a generative model. The generative model learns the product information and makes predictions and classifications for newly input data.

[0756] Input from the user

[0757] User

[0758] Users can use devices such as smartphones or computers to input their own dietary restrictions and nutritional requirements, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on their health status.

[0759] Sending and matching conditions

[0760] Terminal

[0761] The dietary restrictions and nutritional conditions entered by the user are sent to the server.

[0762] server

[0763] The server receives the conditions sent by the user and uses a generative model to match the product information in the database with the user's conditions and filter out matching products and meal plans.

[0764] Emotion recognition and suggestion adjustment

[0765] Terminal

[0766] The emotion engine uses the user's device's camera and microphone to recognize emotions from the user's facial expressions and voice. This feature is activated during initial setup or regular use.

[0767] server

[0768] Based on the emotional state recognized by the emotion engine, the server will tailor the recommendations, for example, if the user is feeling stressed, it will suggest foods and drinks that have a relaxing effect.

[0769] Proposals and Presentations

[0770] server

[0771] Based on the results of the filtering and sentiment engine, it generates product lists and daily meal plans tailored to individual user requirements.

[0772] server

[0773] The generated proposal content is transmitted to the user's terminal.

[0774] Terminal

[0775] The device displays the suggestions sent from the server to the user, allowing the user to easily check foods and meal plans that fit their dietary restrictions and nutritional requirements.

[0776] User

[0777] Users can review the suggested products and meal plans, select the products they want to purchase, and the selected products are added to their cart to proceed with the purchase.

[0778] Specific examples

[0779] For example, if a user inputs the conditions "I have an egg allergy" and "I want to avoid caffeine," the server uses the generative model to filter products and meal plans from the database that match these conditions. If the emotion engine uses the smartphone's camera and microphone to identify that the user is feeling "stressed," suggestions might include decaffeinated herbal teas and foods that help reduce stress.

[0780] The system allows users to select foods appropriate for their emotional state, as well as their dietary restrictions and nutritional requirements, for a more personalized service. It can also provide meal plans tailored to individual needs for users who need to manage diabetes or follow specific diet plans.

[0781] ---

[0782] The processing flow will be explained below.

[0783] ---

[0784] Step 1:

[0785] server

[0786] Product information is obtained from online supermarkets and bento shops via API or data files.

[0787] Product information includes product name, nutritional information, ingredient list, and allergen information.

[0788] The obtained product information is saved in the database.

[0789] Step 2:

[0790] server

[0791] Based on the product information stored in the database, a generative model is constructed using machine learning algorithms (e.g., deep learning).

[0792] The generative model learns product information and is given the ability to make predictions and classifications on newly input data.

[0793] Step 3:

[0794] User

[0795] Users enter their own dietary restrictions and nutritional requirements using a device such as a smartphone or computer.

[0796] Inputs include allergy information, avoidance of certain food ingredients, and nutritional requirements based on health conditions.

[0797] Step 4:

[0798] Terminal

[0799] The dietary restrictions and nutritional conditions entered by the user are sent to the server.

[0800] Step 5:

[0801] server

[0802] Receive dietary restrictions and nutritional requirements submitted by users.

[0803] It uses a generative model to match product information in a database with the user's criteria and filter out matching products and meal plans.

[0804] Step 6:

[0805] Terminal

[0806] The emotion engine uses the camera and microphone on the user's device to recognize emotions from the user's facial expressions and voice.

[0807] Emotion recognition is performed when the user inputs dietary restrictions and nutritional requirements.

[0808] Step 7:

[0809] server

[0810] The emotional state of the user recognized by the emotion engine is received and the suggestions are adjusted accordingly.

[0811] For example, if a user is feeling stressed, the app suggests foods and drinks that have a relaxing effect.

[0812] Step 8:

[0813] server

[0814] Based on the tailored suggestions, it generates a product list and daily meal plan tailored to the individual user's requirements.

[0815] Step 9:

[0816] server

[0817] The generated proposal content is transmitted to the user's terminal.

[0818] Step 10:

[0819] Terminal

[0820] The terminal displays the proposal sent from the server to the user.

[0821] For example, it could be displayed in the format "Recommended breakfast: Decaffeinated coffee and eggless sandwich."

[0822] Step 11:

[0823] User

[0824] Review the suggested products and meal plans and select the products you want to purchase.

[0825] The selected items will be added to your cart and you can proceed with the purchase.

[0826] ---

[0827] Through this specific processing step, users can easily select products and meal plans that fit their emotional state as well as their dietary restrictions and nutritional requirements.

[0828] Example 2

[0829] 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."

[0830] In modern society, users have a wide variety of dietary restrictions and nutritional requirements. Furthermore, users often want to make choices based on their emotional state. However, conventional systems have been inadequate in providing products and meal plans that take the user's emotional state into account, making it difficult to provide personalized recommendations. Furthermore, incorporating emotion recognition technology into a meal recommendation system would enable recommendations that are more tailored to individual users' needs, but no system has been able to achieve this.

[0831] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring product information via a network, means for storing the product information in a database, means for constructing a generative model that learns based on the product information stored in the database, means for analyzing the user's facial expressions and voice to recognize emotions, means for adjusting the generated products and meal plans based on the recognized emotions, and means for presenting the adjusted products and meal plans to the user. This enables the user to receive personalized products and meal plans that are tailored to their emotional state in addition to their dietary restrictions and nutritional requirements.

[0832] A "network" is a communications system that connects multiple computers or devices to send and receive data.

[0833] "Product information" refers to information about the product's characteristics and contents, such as the product's name, nutritional value information, ingredient list, and allergen information.

[0834] A "database" is a system or software that allows data to be efficiently stored, searched, and edited.

[0835] A "generative model" is a model built using machine learning algorithms to make predictions or classifications based on specific data.

[0836] A "user" is an individual or group that uses this system, and is the entity that provides input and instructions to the system.

[0837] "Dietary restrictions" refers to restricting the intake of certain foods or ingredients based on allergies, health conditions, religious beliefs, etc.

[0838] "Nutritional requirements" are requirements or conditions regarding a diet that a user follows with a focus on consuming specific nutrients.

[0839] A "server" is a computer system that provides data and services to other computers on a network.

[0840] "Emotion recognition" is a technology that analyzes and identifies a user's current emotional state from their facial expressions and voice.

[0841] "Personalized recommendations" refers to product and meal plan recommendations optimized for each individual user's dietary restrictions, nutritional requirements, and even emotional state.

[0842] The present invention is a system that provides products and meal plans that match a user's dietary restrictions and nutritional requirements, and aims to provide more personalized suggestions to each user by combining it with an emotion engine that recognizes the user's emotions. This system is implemented in the following steps.

[0843] Obtaining and storing product information

[0844] server

[0845] The server obtains product information via the network. Specifically, it collects product information from online supermarkets and bento shops via API or data files. This product information includes the product name, nutritional value information, ingredient list, and allergen information.

[0846] The acquired product information is stored in a database. MySQL or PostgreSQL are suitable database management systems. The table that stores product information contains columns for basic product information, nutritional value, and allergen information.

[0847] Learning and Generative Model Building

[0848] server

[0849] The server uses machine learning algorithms to build generative models based on product information stored in a database, using libraries such as TensorFlow and PyTorch.

[0850] Preprocess the data, handle missing values, normalize, etc. Then use the preprocessed data to train a model and build a generative model that classifies products that meet certain criteria.

[0851] The trained model is saved as a file and used for subsequent prediction processing.

[0852] Input from the user

[0853] User

[0854] Users use devices such as smartphones or PCs to input their own dietary restrictions and nutritional requirements. This input includes allergy information, avoidance of specific food ingredients, nutritional requirements based on health status, etc. The input information is sent to the server via the device's application.

[0855] Sending and matching conditions

[0856] Terminal

[0857] The device sends the dietary restrictions and nutritional requirements entered by the user to the server, for example, by sending serialized data in JSON format via an HTTP POST request.

[0858] server

[0859] The server uses the generative model to match product information based on the received user criteria, calculates a score for products that match the criteria, and filters out the top candidates.

[0860] The filtered product list is temporarily saved.

[0861] Emotion recognition and suggestion adjustment

[0862] Terminal

[0863] The device's emotion engine uses the camera and microphone to analyze the user's facial expressions and voice to recognize emotions. OpenCV and Emotion API are suitable software for this purpose.

[0864] The recognized emotion data is sent to the server in JSON format.

[0865] server

[0866] The server then adjusts its suggestions based on the received emotional data, for example, recommending foods and drinks that have a relaxing effect if the user is feeling stressed.

[0867] Proposals and Presentations

[0868] server

[0869] The server generates tailored recommendations and sends them to the user's device, which are presented as product lists and daily meal plans.

[0870] Terminal

[0871] The terminal analyzes the proposals sent from the server and displays them on a user interface, for example, using a tree view or list view to display product information.

[0872] User

[0873] Users can review the suggested products and meal plans, select the products they want to purchase, and the selected products are added to their cart to proceed with the purchase.

[0874] Specific examples

[0875] For example, if a user inputs the criteria "I have an egg allergy" and "I want to avoid caffeine," the server uses the generative model to filter products and meal plans from the database that fit those criteria. If the user's emotion engine recognizes "stress," suggestions might include decaffeinated herbal teas and foods that help reduce stress.

[0876] Prompt Sentence Examples

[0877] "I have an egg allergy and would like to avoid caffeine. Can you recommend any foods or drinks? I've also been feeling stressed lately."

[0878] In this way, the present invention can provide personalized products and meal plans tailored to a user's dietary restrictions, nutritional requirements, and emotional state, thereby enabling users to make better food choices and improve the quality of their diet.

[0879] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0880] Step 1: Retrieve and store product information

[0881] server

[0882] The server obtains product information via the network. Specifically, it collects product information from online supermarkets and bento shops via API or data files.

[0883] The server stores the retrieved product information in a database, including the product name, nutritional information, ingredient list, and allergen information.

[0884] Input: API endpoint URL of online supermarket or bento shop

[0885] Output: Product information stored in the database

[0886] Step 2: Building a training and generative model

[0887] server

[0888] The server reads product information from a database and builds a generative model using machine learning algorithms, such as TensorFlow and PyTorch.

[0889] Data preprocessing involves processing missing values ​​and normalization.

[0890] Train the model using the training data and save the model as a file.

[0891] Input: Product information retrieved from the database

[0892] Output: Trained generative model file

[0893] Step 3: User Input

[0894] User

[0895] Users can input their dietary restrictions and nutritional requirements via smartphone or computer, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on health conditions.

[0896] Input: Information about dietary restrictions and nutritional requirements

[0897] Output: Input data saved on the device

[0898] Step 4: Sending and matching conditions

[0899] Terminal

[0900] The terminal converts the data entered by the user into JSON format and sends it to the server via an HTTP POST request.

[0901] Input: User's dietary restrictions and nutritional requirements

[0902] Output: JSON data sent to the server

[0903] server

[0904] The server analyzes the received user requirements, compares them with product information using a generative model, calculates a score for matching products, and filters the top candidates.

[0905] Input: Received condition data in JSON format

[0906] Output: Filtered product list

[0907] Step 5: Recognize emotions and adjust suggestions

[0908] Terminal

[0909] The device's emotion engine uses the camera and microphone to analyze the user's facial expressions and voice to recognize emotions. OpenCV and Emotion API are suitable software for this purpose.

[0910] The recognized emotion data is sent to the server in JSON format.

[0911] Input: User's facial expressions and voice data

[0912] Output: Emotion data sent to the server

[0913] server

[0914] The server adjusts its suggestions based on the received emotional data. For example, if the user is feeling stressed, it will increase the number of products that have a relaxing effect.

[0915] Input: Received emotion data

[0916] Output: Tailored product list and meal plan

[0917] Step 6: Proposal and Presentation

[0918] server

[0919] The server generates the adjusted proposal and sends it to the user's device in JSON format.

[0920] Input: Tailored product list and meal plan

[0921] Output: JSON data sent to the terminal

[0922] Terminal

[0923] The terminal analyzes the proposals sent from the server and displays them in a user interface, for example, by using a tree view or list view to display product information.

[0924] Input: JSON data received from the server

[0925] Output: Product information and meal plan presented to the user

[0926] Step 7: User Actions

[0927] User

[0928] Users can review the suggested products and meal plans, select the products they want to purchase, and the selected products are added to their cart to proceed with the purchase.

[0929] Input: User's choice

[0930] Output: List of items added to cart

[0931] (Application example 2)

[0932] 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."

[0933] Conventional meal plan suggestion systems can provide products and meal plans that meet a user's dietary restrictions and nutritional requirements, but they do not take into account the user's emotional state. As a result, they are unable to provide foods and meal plans that are optimal for the user's current emotional state, and further personalization is required.

[0934] 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.

[0935] In this invention, the server includes means for acquiring product information via a network, means for storing the product information in a database, means for constructing a generative model that learns based on the product information stored in the database, means for the user to input dietary restrictions and nutritional requirements, means for recognizing the user's emotions using a camera and a microphone, means for adjusting the content of suggestions based on the recognized emotions, and means for presenting the generated products and meal plans to the user. This makes it possible to provide highly personalized products and meal plans based on comprehensive data including the user's emotional state.

[0936] "Product information" refers to detailed product data that is acquired via a network and stored in a database, and includes nutritional values, ingredient lists, allergen information, and the like.

[0937] "Database" means an information system that stores product information and allows it to be accessed, searched, and updated.

[0938] A "generative model" is a model that is built using machine learning algorithms based on product information to generate products and meal plans that meet the user's requirements.

[0939] "Dietary restrictions and nutritional requirements" refers to dietary restrictions or requirements set by a user based on their own health condition, allergies, or requests to avoid certain ingredients.

[0940] The "camera and microphone" are visual and audio input devices for recognizing the user's facial expressions and voice, and are used in combination with the emotion engine.

[0941] "Means for recognizing emotions" refers to a system or algorithm that uses a camera and microphone to analyze the user's facial expressions and voice and determine the user's emotional state.

[0942] The "means for adjusting the proposal content" is a function for modifying or optimizing the content of the generated products or meal plans based on the user's emotional state recognized by the emotion engine.

[0943] The present invention is a system for proposing optimal products and meal plans based on a user's dietary restrictions, nutritional requirements, and emotional state. Specific embodiments of the system are described below.

[0944] Obtaining and storing product information

[0945] The server retrieves product information via the network and stores it in a database. Product information includes nutritional information, ingredient lists, and allergen information. This creates a foundation for quickly providing information that meets the user's requirements.

[0946] Learning and Generative Model Building

[0947] The server uses machine learning algorithms (e.g., deep learning) to build a generative model based on the product information stored in the database. The generative model learns the product information and makes predictions and classifications for newly input data.

[0948] Input from the user

[0949] Users use devices such as smartphones to input their own dietary restrictions and nutritional requirements, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on their health status.

[0950] Sending and matching conditions

[0951] The device sends the dietary restrictions and nutritional requirements entered by the user to the server, which then uses the generative model to match the user's requirements with product information in the database and filter out matching products and meal plans.

[0952] Emotion recognition and suggestion adjustment

[0953] The device uses a camera and microphone to recognize emotions from the user's facial expressions and voice. This function is activated during initial setup or regular use. The server then adjusts the suggestions based on the emotional state recognized by the emotion engine. For example, if the user is feeling stressed, it will suggest foods and drinks that have a relaxing effect.

[0954] Proposals and Presentations

[0955] Based on the results of the filtering and emotion engine, the server generates a product list and daily meal plan tailored to each user's individual requirements and sends it to the device. The device displays the suggestions sent from the server to the user, allowing the user to easily check foods and meal plans that suit their own dietary restrictions, nutritional requirements, and emotional state.

[0956] Users can review the suggested products and meal plans, select the products they want to purchase, and the selected products are added to their cart to proceed with the purchase.

[0957] Specific examples

[0958] For example, if a user inputs the conditions "I have an egg allergy" and "I want to avoid caffeine," the server uses the generative model to filter products and meal plans from the database that match these conditions. If the emotion engine uses the smartphone's camera and microphone to identify that the user is feeling "stressed," suggestions might include decaffeinated herbal teas and foods that help reduce stress.

[0959] Example prompt sentence:

[0960] "If a user inputs that they have an egg allergy and want to avoid caffeine, and the system detects through their smartphone's camera and microphone that they are feeling stressed, the system will suggest decaffeinated herbal teas and foods that help reduce stress."

[0961] In this way, it becomes possible to offer highly personalized products and meal plans based on comprehensive data, including the user's emotional state.

[0962] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0963] Step 1:

[0964] The server retrieves product information over the network. Inputs include API endpoints and data files, and outputs a product information dataset containing product names, nutritional information, ingredient lists, allergen information, etc. The data is received in JSON format and stored in an internal database.

[0965] Step 2:

[0966] The server uses deep learning algorithms to build a generative model based on product information stored in an internal database. The input includes product information from the database, and the output is a generative model for predicting products and meal plans that meet the user's criteria. Specifically, machine learning frameworks such as Keras and TensorFlow are used.

[0967] Step 3:

[0968] Users input their dietary restrictions and nutritional requirements using a device such as a smartphone. The input data includes allergy information, avoidance of specific food ingredients, and nutritional requirements based on health conditions. The device then transmits this data to a server.

[0969] Step 4:

[0970] The server receives the dietary restrictions and nutritional requirements sent by the user and performs filtering based on those requirements. The input includes the user's requirements data and product information in the database, and the output is a list of products and meal plans that match the requirements.

[0971] Step 5:

[0972] The device uses the user's camera and microphone to recognize emotions from the user's facial expressions and voice. Inputs include camera feed and audio input, and outputs provide data indicating the user's emotional state. An emotion engine analyzes information such as whether the user is feeling stressed.

[0973] Step 6:

[0974] The server adjusts the recommendations based on the user's perceived emotional state. The input includes the user's emotional data and the filtering results, and the output is a product list or meal plan that takes the user's emotional state into account. For example, if the user is feeling stressed, the server suggests foods and drinks that have a relaxing effect.

[0975] Step 7:

[0976] The server sends the generated products and meal plans to the device. The input includes the final product list and meal plan, and the output is the suggestions displayed on the user's device. The device displays the suggestions to the user, allowing the user to identify foods and meal plans that fit their dietary restrictions, nutritional requirements, and emotional state.

[0977] Step 8:

[0978] The user reviews the suggested products and meal plans and selects the products they want to purchase. The input includes product information selected from the suggestions, and the output is a list of products added to the cart. The user can then proceed with the purchase process based on this list.

[0979] 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.

[0980] 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.

[0981] 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.

[0982] [Third embodiment]

[0983] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0984] 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.

[0985] 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).

[0986] 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.

[0987] 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.

[0988] 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).

[0989] 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.

[0990] 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.

[0991] 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.

[0992] 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.

[0993] 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.

[0994] 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."

[0995] ---

[0996] The present invention is a system that allows people who have allergies, illnesses, dietary restrictions during pregnancy, or who need nutritional management for building a healthy body to easily select commercially available foods and boxed lunches. This system acquires product information via a network and provides products and meal plans that match the user's dietary restrictions and nutritional requirements. Specific embodiments of the system are described below.

[0997] Obtaining and storing product information

[0998] server

[0999] The server obtains product information from online supermarkets and bento shops via API or data files, including product names, nutritional information, ingredient lists, and allergen information.

[1000] The acquired product information is stored in a database.

[1001] Learning and Generative Model Building

[1002] server

[1003] Using product information stored in a database, a machine learning algorithm (e.g., deep learning) is used to build a generative model that learns detailed information about the product and can make predictions and classifications for new data.

[1004] Input from the user

[1005] User

[1006] Users use devices such as smartphones or computers to input their own dietary restrictions and nutritional requirements, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on their health status.

[1007] Sending and matching conditions

[1008] Terminal

[1009] The dietary restrictions and nutritional conditions entered by the user are sent from the terminal to the server.

[1010] server

[1011] The server uses the generative model to generate products, lunch boxes, and even daily meal plans that match the user's criteria, filtering the foods that match the criteria based on information stored in the database.

[1012] Proposals and Presentations

[1013] server

[1014] The server sends the generated product list and meal plan to the user's terminal.

[1015] Terminal

[1016] The device displays the suggestions sent from the server to the user, allowing the user to easily find foods and meal plans that fit their dietary restrictions and nutritional requirements.

[1017] User

[1018] The user can then review the suggested products and select the ones they wish to purchase. The selected products are added to the cart and the user can proceed with the purchase.

[1019] Specific examples

[1020] For example, if a user has conditions such as "egg allergy" and "avoid caffeine," they can input these conditions via their smartphone. The server uses the generative model to filter products and meal plans from the database that match these conditions and generate suggestions. Suggested foods include caffeine-free beverages and egg-free ingredients. Users can review these suggestions and safely select them, eliminating the need to go through the trouble of searching for foods that meet multiple conditions.

[1021] This system allows customers with multiple dietary restrictions to easily select foods that suit them, significantly reducing the burden of dietary management. It can also provide meal plans tailored to individual needs for users who need to manage diabetes or who are following specific diet plans.

[1022] ---

[1023] The processing flow will be explained below.

[1024] ---

[1025] Step 1:

[1026] server

[1027] Product information is obtained from online supermarkets and bento shops via API or data files.

[1028] Product information includes product name, nutritional information, ingredient list, and allergen information.

[1029] The obtained product information is saved in the database.

[1030] Step 2:

[1031] server

[1032] Based on the product information stored in the database, a generative model is constructed using machine learning algorithms (e.g., deep learning).

[1033] Generative models are trained with product information that can later be used for prediction and classification.

[1034] Step 3:

[1035] User

[1036] Users enter their dietary restrictions and nutritional requirements using a device such as a smartphone or computer.

[1037] For example, enter conditions such as "egg allergy" or "want to avoid caffeine."

[1038] Step 4:

[1039] Terminal

[1040] The dietary restrictions and nutritional conditions entered by the user are sent to the server.

[1041] Step 5:

[1042] server

[1043] The server receives the conditions sent by the user.

[1044] It uses a generative model to match product information in the database with the user's criteria and filter out matching products and meal plans.

[1045] Step 6:

[1046] server

[1047] Based on the filtered product information, proposals tailored to individual user conditions are generated.

[1048] Suggestions include a list of suitable products and a daily meal plan.

[1049] Step 7:

[1050] server

[1051] The generated proposal content is transmitted to the user's terminal.

[1052] Step 8:

[1053] Terminal

[1054] The terminal displays the proposal sent from the server to the user.

[1055] For example, it could be displayed in the format "Recommended breakfast: Decaffeinated coffee and eggless sandwich."

[1056] Step 9:

[1057] User

[1058] Check out suggested products and meal plans.

[1059] Select the product you want to purchase and add it to your cart.

[1060] Proceed with the purchase of items added to your cart.

[1061] ---

[1062] In this way, users can easily select products that fit their dietary restrictions and nutritional requirements. Furthermore, the recommendations provided are highly accurate thanks to the generative model.

[1063] Example 1

[1064] 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."

[1065] Currently, when selecting commercially available foods or bento boxes, it is difficult for users to find products that meet their allergies, illnesses, dietary restrictions during pregnancy, or nutritional management requirements for building a healthy body. This poses a problem in that it takes a great deal of time and effort for users to select foods that meet their requirements.

[1066] 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.

[1067] In this invention, the server includes means for acquiring product information via a network, means for storing the product information in a database, means for building a generative AI model that learns based on the product information stored in the database, means for the user to input dietary restrictions and nutritional requirements, means for transmitting the dietary restrictions and nutritional requirements input by the user to the server, means for the server to use the generative AI model to generate products and meal plans that meet the dietary restrictions and nutritional requirements, means for presenting the generated products and meal plans to the user, and means for adding products selected by the user from the presented products and meal plans to the purchasing process. This allows the user to easily select foods that meet their requirements and significantly reduces the burden of dietary management.

[1068] A "network" is a system in which multiple computers or devices are connected so that they can communicate with each other.

[1069] "Product information" refers to information about a product that includes data such as the product's name, nutritional value, ingredient list, and allergen information.

[1070] A "database" is a system for efficiently storing, retrieving, and managing organized data.

[1071] A "generative AI model" is a model that has been trained using machine learning algorithms to make new predictions or classifications based on data.

[1072] "User" refers to any individual or organization that uses the system or service.

[1073] A "dietary restriction" is a restriction that prevents the intake of certain foods or ingredients for health reasons.

[1074] "Nutritional requirements" are the nutrient requirements you need or want to avoid based on a specific health condition or goal.

[1075] A "server" is a computer system that provides services to clients over a network.

[1076] A "product list" is a list that refers to a collection of products selected based on specific conditions.

[1077] A "meal plan" refers to a suggestion or plan for meals over a day or period of time.

[1078] A "purchase process" refers to a series of procedures or steps a user takes to purchase a selected product.

[1079] The present invention provides a system that allows people who have allergies, illnesses, dietary restrictions during pregnancy, or who need nutritional management for building a healthy body to easily select commercially available foods and boxed lunches. This system acquires product information via a network and provides products and meal plans that match the user's dietary restrictions and nutritional requirements. Specific embodiments of the system are described below.

[1080] Obtaining and storing product information

[1081] server

[1082] The server collects product information from online supermarkets and bento shops via API or data files, including product names, nutritional information, ingredient lists, and allergen information.

[1083] The server stores the acquired product information in a database.

[1084] Specific examples

[1085] The server communicates with the online supermarket's API every day at midnight to retrieve new and updated product information, and then adds or updates this information to the database.

[1086] Example prompt sentence:

[1087] "Please use the Rakuten Market API to update all product information daily and store it in the database."

[1088] Learning and Generative Model Building

[1089] server

[1090] The server uses machine learning algorithms (e.g., deep learning) to train a generative AI model based on the product information stored in the database. The generative AI model learns detailed information about the product and makes predictions and classifications based on the user's criteria.

[1091] Specific examples

[1092] The server uses TensorFlow to train a new model each week based on the stored product information, which can then score each product taking into account allergen information and nutritional value.

[1093] Example prompt sentence:

[1094] "Use TensorFlow to build a model that learns all the product information in your database and classifies products that meet the user's criteria."

[1095] Input from the user

[1096] User

[1097] Users use devices such as smartphones or computers to input their own dietary restrictions and nutritional requirements, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on their health status.

[1098] Specific examples

[1099] The user launches the app and enters "egg allergy" and "caffeine avoidance" on the profile screen, which updates the user profile within the app.

[1100] Example prompt sentence:

[1101] "Enter any allergies or food ingredients you are avoiding. For example, egg allergy, caffeine avoidance."

[1102] Sending and matching conditions

[1103] Terminal

[1104] The dietary restrictions and nutritional conditions entered by the user are sent from the terminal to the server.

[1105] server

[1106] Once the server receives the user's criteria, it stores them in a database and then uses a deep learning model to filter products that match the criteria. Based on the filtered results, it generates a product list and a daily meal plan that meets the user's criteria.

[1107] Specific examples

[1108] The device sends the conditions "egg allergy" and "caffeine avoidance" to the server. The server receives this and uses the database and deep learning model to search for products that meet the conditions. For example, "egg-free bread" and "caffeine-free drinks" are matched.

[1109] Example prompt sentence:

[1110] "Match products based on input criteria and generate a daily meal plan using a generative model."

[1111] Proposals and Presentations

[1112] server

[1113] The server generates a product list and meal plan that meets the user's requirements and sends it to the user's terminal.

[1114] Terminal

[1115] The terminal displays the product list and meal plan sent from the server to the user.

[1116] User

[1117] Users can review the suggested products and meal plans and select the products they wish to purchase, which are then added to their cart and they can proceed with the checkout.

[1118] Specific examples

[1119] The server sends "egg-free bread" and "caffeine-free beverage" to the terminal. The user confirms this and adds the items they want to purchase to their cart. They then proceed with the purchase.

[1120] Example prompt sentence:

[1121] "Design a UI that suggests and displays products and meal plans that match the user's criteria."

[1122] This system allows users with allergies or dietary restrictions to easily select foods that suit them, significantly reducing the burden of dietary management. It also accommodates users following specific diet plans.

[1123] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1124] Step 1:

[1125] The server acquires the product information via the network.

[1126] Input: API request from online supermarket or bento shop

[1127] Specific operation: The server executes an API request every day at midnight to obtain new products and updated information.

[1128] Output: Product information returned from the API (product name, nutritional information, ingredient list, allergen information)

[1129] Step 2:

[1130] The server stores the acquired product information in a database.

[1131] Input: Product information obtained in Step 1

[1132] Specific operation: The server performs the process of adding or updating the product information in the database.

[1133] Output: Product information stored in the database

[1134] Step 3:

[1135] The server builds a generative AI model based on product information stored in the database.

[1136] Input: Product information stored in the database

[1137] Specific operation: The server uses TensorFlow to train a deep learning model and build a model based on product information.

[1138] Output: The generated deep learning model

[1139] Step 4:

[1140] Users input their dietary restrictions and nutritional requirements via their smartphone or computer.

[1141] Input: User's dietary restrictions or nutritional requirements (e.g., egg allergy, caffeine avoidance)

[1142] Specific operation: The user enters the conditions in the device app, which are then saved in the system.

[1143] Output: Entered dietary restrictions and nutritional conditions

[1144] Step 5:

[1145] The terminal transmits the conditions entered by the user to the server.

[1146] Input: Input data for dietary restrictions and nutritional conditions

[1147] Specific operation: The terminal executes a request to send the user's conditions to the server.

[1148] Output: User criteria sent to server

[1149] Step 6:

[1150] The server receives the user's requirements and uses the database and generative AI model to generate products and meal plans that meet the requirements.

[1151] Input: User conditions sent to the server, product information stored in the database, generated deep learning model

[1152] What it does: The server uses the user's criteria as filtering criteria to search and score products in the database and generate products and meal plans that best fit the criteria.

[1153] Output: A list of products and meal plans that match your criteria

[1154] Step 7:

[1155] The server transmits the generated product list and meal plan to the user's terminal.

[1156] Input: A list of products or meal plans that match your criteria

[1157] Specific operation: The server generates the proposal and executes a request to send it to the user's device.

[1158] Output: Product list and meal plan sent to the device

[1159] Step 8:

[1160] The terminal displays the product list and meal plan sent from the server to the user.

[1161] Input: Product list or meal plan sent from the server

[1162] Specific operation: The device displays the received product list and meal plan on the screen and notifies the user.

[1163] Output: Displayed product list and meal plan

[1164] Step 9:

[1165] The user reviews the suggested products and meal plans and selects the products they wish to purchase.

[1166] Input: Displayed product list or meal plan

[1167] Specific operation: The user selects the product they want to purchase on the screen and adds it to their cart.

[1168] Output: Items added to cart

[1169] Step 10:

[1170] The user then carries out the procedure to purchase the product added to the cart.

[1171] Input: Items added to cart

[1172] What happens: The user proceeds to the checkout screen, enters payment information, and completes the order.

[1173] Output: Completed order items

[1174] (Application example 1)

[1175] 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."

[1176] People who have dietary restrictions or nutritional needs have difficulty finding foods that do not contain allergens or specific ingredients when choosing commercially available foods or bento boxes. Furthermore, there are few ways to check this information in real time while shopping in physical stores, which places a significant burden on them when making appropriate product selections.

[1177] 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.

[1178] In this invention, the server includes: means for acquiring product information via a network; means for storing the product information in a database; means for constructing a generative model that learns based on the product information stored in the database; means for allowing a user to input dietary restrictions and nutritional requirements; means for transmitting the dietary restrictions and nutritional requirements input by the user to the server; means for the server to use the generative model to generate products and meal plans that meet the dietary restrictions and nutritional requirements; means for presenting the generated products and meal plans to the user; and means for scanning a barcode using a smartphone when a user selects a product in a physical store, comparing the scanned product information with the user's input conditions to determine whether the conditions are met, and presenting the result to the user. This enables users to easily find and select products that meet their conditions in real time while shopping in a physical store.

[1179] "Means for acquiring product information via a network" refers to a function for externally collecting information about various products, such as product names, nutritional value information, ingredient lists, and allergen information, via a network such as the Internet.

[1180] The "means for saving product information in a database" is a function for recording acquired product information in a database in a structured format for later retrieval and analysis.

[1181] The "means for constructing a generative model" is a function that uses a machine learning algorithm, such as deep learning, to create a model for generating products and meal plans based on product information stored in the database.

[1182] "Means for inputting dietary restrictions and nutritional requirements" is a function that provides an interface for users to input information about their allergies, ingredients they want to avoid, specific nutritional requirements, and so on.

[1183] The "means for transmitting dietary restrictions and nutritional conditions to the server" is a function for transferring information entered by the user to the server and processing it.

[1184] "Means for using a generative model to generate products and meal plans that meet dietary restrictions and nutritional requirements" is a function that uses the constructed generative model to calculate and generate products and meal plans that meet the user's requirements.

[1185] "Means for presenting generated products and meal plans to users" refers to a function that displays products and meal plans generated by the server on the user's device (such as a smartphone).

[1186] "A means of scanning barcodes using a smartphone when selecting products in a physical store...and presenting the results to the user" refers to a function that reads the barcode of a product with a smartphone when the user is shopping in a store, compares the product information with the user's conditions, and notifies the user in real time whether the product is a match.

[1187] The present invention provides a system that allows people who have allergies, illnesses, dietary restrictions during pregnancy, or who need nutritional management for building a healthy body to easily select commercially available foods and boxed lunches. This system acquires product information via a network and provides products and meal plans that match the user's dietary restrictions and nutritional requirements. Specific embodiments of the system are described below.

[1188] Obtaining and storing product information

[1189] The server obtains product information from online supermarkets and bento shops via API or data files. This product information includes the product name, nutritional value information, ingredient list, and allergen information. The obtained product information is stored in a database.

[1190] Learning and Generative Model Building

[1191] The server uses machine learning algorithms (e.g., deep learning) to build a generative model based on the product information stored in the database. This generative model learns detailed information about the product and can make predictions and classifications for new data.

[1192] Input from the user

[1193] Users use devices such as smartphones or computers to input their own dietary restrictions and nutritional requirements, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on their health status.

[1194] Sending and matching conditions

[1195] The user's dietary restrictions and nutritional requirements are sent from the device to the server, which uses a generative model to generate products, lunch boxes, and even daily meal plans that fit the user's requirements, filtering the foods that match the requirements based on information stored in the database.

[1196] Proposals and Presentations

[1197] The server sends the generated product list and meal plan to the user's device. The device displays the suggestions sent from the server to the user. This allows the user to easily check foods and meal plans that fit their dietary restrictions and nutritional requirements. The user reviews the suggested products and selects the products they wish to purchase. The selected products are added to the cart, and the user can proceed with the purchase.

[1198] Examples of applications in physical stores

[1199] When selecting a product in a physical store, a user can scan the product's barcode using their smartphone. The server uses the scanned barcode information to match product information with the user's input criteria. The matching results are presented to the user in real time, and the server determines whether the conditions are met and displays the results. For example, if a user has conditions such as "egg allergy" and "desire to avoid caffeine," the user enters these conditions via their smartphone. When a product is scanned in a physical store, the server uses a generative model to determine whether the product matches these conditions from the database and displays the results on the smartphone. Suggested foods include caffeine-free beverages and egg-free ingredients. Users can review these suggestions and make a safe selection, eliminating the need to search for foods that meet multiple conditions.

[1200] Prompt Sentence Examples

[1201] A concrete example of an input prompt for a generative AI model could be in the form of text like this:

[1202] Create a system that determines whether a user's dietary restrictions or allergies are met based on a scenario in which the user scans a product's barcode with their smartphone while shopping in a store. Product information is retrieved from an API and includes allergen information and ingredients. The user's conditions are egg allergy and caffeine avoidance. If the conditions are met, display a message saying "Conditions met." If not, display a message saying "Conditions not met." Please also provide specific code examples.

[1203] The above is a specific embodiment for carrying out the present invention, which enables a user to select appropriate products in real time while shopping in a physical store.

[1204] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1205] Step 1:

[1206] The server obtains product information via the network. Specifically, the server collects product information from online supermarkets and bento shops via API or data files. This product information includes the product name, nutritional value information, ingredient list, allergen information, etc. The input is data from an external API or file, and the output is the obtained product information. The server saves this information in a database.

[1207] Step 2:

[1208] The server learns from the product information stored in the database and builds a generative model. The server uses machine learning algorithms (e.g., deep learning) to learn detailed information about the products. The input is the product information stored in the database and the output is the generated model. This generative model is used to make predictions and classifications on new data.

[1209] Step 3:

[1210] Users use their smartphones or computers to input their own dietary restrictions and nutritional requirements. Specifically, they use the smartphone application screen to input allergy information, ingredients to avoid, specific nutritional requirements, etc. The user's condition information is input, and these conditions are sent to the server as output.

[1211] Step 4:

[1212] The server receives the user's dietary restrictions and nutritional requirements sent from the device. The server uses a generative model based on the received requirements to generate matching products and meal plans. The input is the user's requirements, and the output is a list of matching products and meal plans. The server filters the product information stored in the database to find foods that match the requirements.

[1213] Step 5:

[1214] The server sends the generated product list and meal plan to the user's device. The device displays the suggestions sent from the server to the user. The input is the generated product list and meal plan from the server, and the output is the suggestions displayed to the user on the device screen. The user can easily check foods and meal plans that fit their own dietary restrictions and nutritional requirements.

[1215] Step 6:

[1216] When a user selects a product in a physical store, they use their smartphone to scan the product's barcode. The terminal acquires the scanned barcode information and sends it to a server. The input is the barcode scanned by the smartphone, and the output is the barcode information sent to the server.

[1217] Step 7:

[1218] The server receives the scanned barcode information and retrieves the product information from the database. It then compares it with the user's input conditions. The server uses a generative model to match the scanned product information with the user's conditions and determine whether the conditions are met. The input is the barcode information and the user's conditions, and the output is the result of a judgment on whether the conditions are met.

[1219] Step 8:

[1220] The server sends the judgment result to the user's terminal. The terminal displays the result to the user. The input is the judgment result sent from the server, and the output is the matching result displayed on the terminal screen. The user can check the display and determine in real time whether the condition is met.

[1221] The above are the specific processing steps for carrying out the present invention, which enable users to easily find and select products that meet their requirements in real time while shopping in a physical store.

[1222] 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.

[1223] ---

[1224] This invention is a system that provides products and meal plans that match a user's dietary restrictions and nutritional requirements, and aims to provide more personalized suggestions to each user by combining it with an emotion engine that recognizes the user's emotions. This system obtains product information via a network and provides products and meal plans that match the user's requirements.

[1225] Obtaining and storing product information

[1226] server

[1227] Product information is obtained from online supermarkets and bento shops via API or data files. This information includes the product name, nutritional value, ingredient list, and allergen information.

[1228] The obtained product information is saved in the database.

[1229] Learning and Generative Model Building

[1230] server

[1231] Based on the product information stored in the database, a machine learning algorithm (e.g., deep learning) is used to build a generative model. The generative model learns the product information and makes predictions and classifications for newly input data.

[1232] Input from the user

[1233] User

[1234] Users can use devices such as smartphones or computers to input their own dietary restrictions and nutritional requirements, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on their health status.

[1235] Sending and matching conditions

[1236] Terminal

[1237] The dietary restrictions and nutritional conditions entered by the user are sent to the server.

[1238] server

[1239] The server receives the conditions sent by the user and uses a generative model to match the product information in the database with the user's conditions and filter out matching products and meal plans.

[1240] Emotion recognition and suggestion adjustment

[1241] Terminal

[1242] The emotion engine uses the user's device's camera and microphone to recognize emotions from the user's facial expressions and voice. This feature is activated during initial setup or regular use.

[1243] server

[1244] Based on the emotional state recognized by the emotion engine, the server will tailor the recommendations, for example, if the user is feeling stressed, it will suggest foods and drinks that have a relaxing effect.

[1245] Proposals and Presentations

[1246] server

[1247] Based on the results of the filtering and sentiment engine, it generates product lists and daily meal plans tailored to individual user requirements.

[1248] server

[1249] The generated proposal content is transmitted to the user's terminal.

[1250] Terminal

[1251] The device displays the suggestions sent from the server to the user, allowing the user to easily check foods and meal plans that fit their dietary restrictions and nutritional requirements.

[1252] User

[1253] Users can review the suggested products and meal plans, select the products they want to purchase, and the selected products are added to their cart to proceed with the purchase.

[1254] Specific examples

[1255] For example, if a user inputs the conditions "I have an egg allergy" and "I want to avoid caffeine," the server uses the generative model to filter products and meal plans from the database that match these conditions. If the emotion engine uses the smartphone's camera and microphone to identify that the user is feeling "stressed," suggestions might include decaffeinated herbal teas and foods that help reduce stress.

[1256] The system allows users to select foods appropriate for their emotional state, as well as their dietary restrictions and nutritional requirements, for a more personalized service. It can also provide meal plans tailored to individual needs for users who need to manage diabetes or follow specific diet plans.

[1257] ---

[1258] The processing flow will be explained below.

[1259] ---

[1260] Step 1:

[1261] server

[1262] Product information is obtained from online supermarkets and bento shops via API or data files.

[1263] Product information includes product name, nutritional information, ingredient list, and allergen information.

[1264] The obtained product information is saved in the database.

[1265] Step 2:

[1266] server

[1267] Based on the product information stored in the database, a generative model is constructed using machine learning algorithms (e.g., deep learning).

[1268] The generative model learns product information and is given the ability to make predictions and classifications on newly input data.

[1269] Step 3:

[1270] User

[1271] Users enter their own dietary restrictions and nutritional requirements using a device such as a smartphone or computer.

[1272] Inputs include allergy information, avoidance of certain food ingredients, and nutritional requirements based on health conditions.

[1273] Step 4:

[1274] Terminal

[1275] The dietary restrictions and nutritional conditions entered by the user are sent to the server.

[1276] Step 5:

[1277] server

[1278] Receive dietary restrictions and nutritional requirements submitted by users.

[1279] It uses a generative model to match product information in a database with the user's criteria and filter out matching products and meal plans.

[1280] Step 6:

[1281] Terminal

[1282] The emotion engine uses the camera and microphone on the user's device to recognize emotions from the user's facial expressions and voice.

[1283] Emotion recognition is performed when the user inputs dietary restrictions and nutritional requirements.

[1284] Step 7:

[1285] server

[1286] The emotional state of the user recognized by the emotion engine is received and the suggestions are adjusted accordingly.

[1287] For example, if a user is feeling stressed, the app suggests foods and drinks that have a relaxing effect.

[1288] Step 8:

[1289] server

[1290] Based on the tailored suggestions, it generates a product list and daily meal plan tailored to the individual user's requirements.

[1291] Step 9:

[1292] server

[1293] The generated proposal content is transmitted to the user's terminal.

[1294] Step 10:

[1295] Terminal

[1296] The terminal displays the proposal sent from the server to the user.

[1297] For example, it could be displayed in the format "Recommended breakfast: Decaffeinated coffee and eggless sandwich."

[1298] Step 11:

[1299] User

[1300] Review the suggested products and meal plans and select the products you want to purchase.

[1301] The selected items will be added to your cart and you can proceed with the purchase.

[1302] ---

[1303] Through this specific processing step, users can easily select products and meal plans that fit their emotional state as well as their dietary restrictions and nutritional requirements.

[1304] Example 2

[1305] 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."

[1306] In modern society, users have a wide variety of dietary restrictions and nutritional requirements. Furthermore, users often want to make choices based on their emotional state. However, conventional systems have been inadequate in providing products and meal plans that take the user's emotional state into account, making it difficult to provide personalized recommendations. Furthermore, incorporating emotion recognition technology into a meal recommendation system would enable recommendations that are more tailored to individual users' needs, but no system has been able to achieve this.

[1307] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring product information via a network, means for storing the product information in a database, means for constructing a generative model that learns based on the product information stored in the database, means for analyzing the user's facial expressions and voice to recognize emotions, means for adjusting the generated products and meal plans based on the recognized emotions, and means for presenting the adjusted products and meal plans to the user. This enables the user to receive personalized products and meal plans that are tailored to their emotional state in addition to their dietary restrictions and nutritional requirements.

[1308] A "network" is a communications system that connects multiple computers or devices to send and receive data.

[1309] "Product information" refers to information about the product's characteristics and contents, such as the product's name, nutritional value information, ingredient list, and allergen information.

[1310] A "database" is a system or software that allows data to be efficiently stored, searched, and edited.

[1311] A "generative model" is a model built using machine learning algorithms to make predictions or classifications based on specific data.

[1312] A "user" is an individual or group that uses this system, and is the entity that provides input and instructions to the system.

[1313] "Dietary restrictions" refers to restricting the intake of certain foods or ingredients based on allergies, health conditions, religious beliefs, etc.

[1314] "Nutritional requirements" are requirements or conditions regarding a diet that a user follows with a focus on consuming specific nutrients.

[1315] A "server" is a computer system that provides data and services to other computers on a network.

[1316] "Emotion recognition" is a technology that analyzes and identifies a user's current emotional state from their facial expressions and voice.

[1317] "Personalized recommendations" refers to product and meal plan recommendations optimized for each individual user's dietary restrictions, nutritional requirements, and even emotional state.

[1318] The present invention is a system that provides products and meal plans that match a user's dietary restrictions and nutritional requirements, and aims to provide more personalized suggestions to each user by combining it with an emotion engine that recognizes the user's emotions. This system is implemented in the following steps.

[1319] Obtaining and storing product information

[1320] server

[1321] The server obtains product information via the network. Specifically, it collects product information from online supermarkets and bento shops via API or data files. This product information includes the product name, nutritional value information, ingredient list, and allergen information.

[1322] The acquired product information is stored in a database. MySQL or PostgreSQL are suitable database management systems. The table that stores product information contains columns for basic product information, nutritional value, and allergen information.

[1323] Learning and Generative Model Building

[1324] server

[1325] The server uses machine learning algorithms to build generative models based on product information stored in a database, using libraries such as TensorFlow and PyTorch.

[1326] Preprocess the data, handle missing values, normalize, etc. Then use the preprocessed data to train a model and build a generative model that classifies products that meet certain criteria.

[1327] The trained model is saved as a file and used for subsequent prediction processing.

[1328] Input from the user

[1329] User

[1330] Users use devices such as smartphones or PCs to input their own dietary restrictions and nutritional requirements. This input includes allergy information, avoidance of specific food ingredients, nutritional requirements based on health status, etc. The input information is sent to the server via the device's application.

[1331] Sending and matching conditions

[1332] Terminal

[1333] The device sends the dietary restrictions and nutritional requirements entered by the user to the server, for example, by sending serialized data in JSON format via an HTTP POST request.

[1334] server

[1335] The server uses the generative model to match product information based on the received user criteria, calculates a score for products that match the criteria, and filters out the top candidates.

[1336] The filtered product list is temporarily saved.

[1337] Emotion recognition and suggestion adjustment

[1338] Terminal

[1339] The device's emotion engine uses the camera and microphone to analyze the user's facial expressions and voice to recognize emotions. OpenCV and Emotion API are suitable software for this purpose.

[1340] The recognized emotion data is sent to the server in JSON format.

[1341] server

[1342] The server then adjusts its suggestions based on the received emotional data, for example, recommending foods and drinks that have a relaxing effect if the user is feeling stressed.

[1343] Proposals and Presentations

[1344] server

[1345] The server generates tailored recommendations and sends them to the user's device, which are presented as product lists and daily meal plans.

[1346] Terminal

[1347] The terminal analyzes the proposals sent from the server and displays them on a user interface, for example, using a tree view or list view to display product information.

[1348] User

[1349] Users can review the suggested products and meal plans, select the products they want to purchase, and the selected products are added to their cart to proceed with the purchase.

[1350] Specific examples

[1351] For example, if a user inputs the criteria "I have an egg allergy" and "I want to avoid caffeine," the server uses the generative model to filter products and meal plans from the database that fit those criteria. If the user's emotion engine recognizes "stress," suggestions might include decaffeinated herbal teas and foods that help reduce stress.

[1352] Prompt Sentence Examples

[1353] "I have an egg allergy and would like to avoid caffeine. Can you recommend any foods or drinks? I've also been feeling stressed lately."

[1354] In this way, the present invention can provide personalized products and meal plans tailored to a user's dietary restrictions, nutritional requirements, and emotional state, thereby enabling users to make better food choices and improve the quality of their diet.

[1355] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1356] Step 1: Retrieve and store product information

[1357] server

[1358] The server obtains product information via the network. Specifically, it collects product information from online supermarkets and bento shops via API or data files.

[1359] The server stores the retrieved product information in a database, including the product name, nutritional information, ingredient list, and allergen information.

[1360] Input: API endpoint URL of online supermarket or bento shop

[1361] Output: Product information stored in the database

[1362] Step 2: Building a training and generative model

[1363] server

[1364] The server reads product information from a database and builds a generative model using machine learning algorithms, such as TensorFlow and PyTorch.

[1365] Data preprocessing involves processing missing values ​​and normalization.

[1366] Train the model using the training data and save the model as a file.

[1367] Input: Product information retrieved from the database

[1368] Output: Trained generative model file

[1369] Step 3: User Input

[1370] User

[1371] Users can input their dietary restrictions and nutritional requirements via smartphone or computer, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on health conditions.

[1372] Input: Information about dietary restrictions and nutritional requirements

[1373] Output: Input data saved on the device

[1374] Step 4: Sending and matching conditions

[1375] Terminal

[1376] The terminal converts the data entered by the user into JSON format and sends it to the server via an HTTP POST request.

[1377] Input: User's dietary restrictions and nutritional requirements

[1378] Output: JSON data sent to the server

[1379] server

[1380] The server analyzes the received user requirements, compares them with product information using a generative model, calculates a score for matching products, and filters the top candidates.

[1381] Input: Received condition data in JSON format

[1382] Output: Filtered product list

[1383] Step 5: Recognize emotions and adjust suggestions

[1384] Terminal

[1385] The device's emotion engine uses the camera and microphone to analyze the user's facial expressions and voice to recognize emotions. OpenCV and Emotion API are suitable software for this purpose.

[1386] The recognized emotion data is sent to the server in JSON format.

[1387] Input: User's facial expressions and voice data

[1388] Output: Emotion data sent to the server

[1389] server

[1390] The server adjusts its suggestions based on the received emotional data. For example, if the user is feeling stressed, it will increase the number of products that have a relaxing effect.

[1391] Input: Received emotion data

[1392] Output: Tailored product list and meal plan

[1393] Step 6: Proposal and Presentation

[1394] server

[1395] The server generates the adjusted proposal and sends it to the user's device in JSON format.

[1396] Input: Tailored product list and meal plan

[1397] Output: JSON data sent to the terminal

[1398] Terminal

[1399] The terminal analyzes the proposals sent from the server and displays them in a user interface, for example, by using a tree view or list view to display product information.

[1400] Input: JSON data received from the server

[1401] Output: Product information and meal plan presented to the user

[1402] Step 7: User Actions

[1403] User

[1404] Users can review the suggested products and meal plans, select the products they want to purchase, and the selected products are added to their cart to proceed with the purchase.

[1405] Input: User's choice

[1406] Output: List of items added to cart

[1407] (Application example 2)

[1408] 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."

[1409] Conventional meal plan suggestion systems can provide products and meal plans that meet a user's dietary restrictions and nutritional requirements, but they do not take into account the user's emotional state. As a result, they are unable to provide foods and meal plans that are optimal for the user's current emotional state, and further personalization is required.

[1410] 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.

[1411] In this invention, the server includes means for acquiring product information via a network, means for storing the product information in a database, means for constructing a generative model that learns based on the product information stored in the database, means for the user to input dietary restrictions and nutritional requirements, means for recognizing the user's emotions using a camera and a microphone, means for adjusting the content of suggestions based on the recognized emotions, and means for presenting the generated products and meal plans to the user. This makes it possible to provide highly personalized products and meal plans based on comprehensive data including the user's emotional state.

[1412] "Product information" refers to detailed product data that is acquired via a network and stored in a database, and includes nutritional values, ingredient lists, allergen information, and the like.

[1413] "Database" means an information system that stores product information and allows it to be accessed, searched, and updated.

[1414] A "generative model" is a model that is built using machine learning algorithms based on product information to generate products and meal plans that meet the user's requirements.

[1415] "Dietary restrictions and nutritional requirements" refers to dietary restrictions or requirements set by a user based on their own health condition, allergies, or requests to avoid certain ingredients.

[1416] The "camera and microphone" are visual and audio input devices for recognizing the user's facial expressions and voice, and are used in combination with the emotion engine.

[1417] "Means for recognizing emotions" refers to a system or algorithm that uses a camera and microphone to analyze the user's facial expressions and voice and determine the user's emotional state.

[1418] The "means for adjusting the proposal content" is a function for modifying or optimizing the content of the generated products or meal plans based on the user's emotional state recognized by the emotion engine.

[1419] The present invention is a system for proposing optimal products and meal plans based on a user's dietary restrictions, nutritional requirements, and emotional state. Specific embodiments of the system are described below.

[1420] Obtaining and storing product information

[1421] The server retrieves product information via the network and stores it in a database. Product information includes nutritional information, ingredient lists, and allergen information. This creates a foundation for quickly providing information that meets the user's requirements.

[1422] Learning and Generative Model Building

[1423] The server uses machine learning algorithms (e.g., deep learning) to build a generative model based on the product information stored in the database. The generative model learns the product information and makes predictions and classifications for newly input data.

[1424] Input from the user

[1425] Users use devices such as smartphones to input their own dietary restrictions and nutritional requirements, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on their health status.

[1426] Sending and matching conditions

[1427] The device sends the dietary restrictions and nutritional requirements entered by the user to the server, which then uses the generative model to match the user's requirements with product information in the database and filter out matching products and meal plans.

[1428] Emotion recognition and suggestion adjustment

[1429] The device uses a camera and microphone to recognize emotions from the user's facial expressions and voice. This function is activated during initial setup or regular use. The server then adjusts the suggestions based on the emotional state recognized by the emotion engine. For example, if the user is feeling stressed, it will suggest foods and drinks that have a relaxing effect.

[1430] Proposals and Presentations

[1431] Based on the results of the filtering and emotion engine, the server generates a product list and daily meal plan tailored to each user's individual requirements and sends it to the device. The device displays the suggestions sent from the server to the user, allowing the user to easily check foods and meal plans that suit their own dietary restrictions, nutritional requirements, and emotional state.

[1432] Users can review the suggested products and meal plans, select the products they want to purchase, and the selected products are added to their cart to proceed with the purchase.

[1433] Specific examples

[1434] For example, if a user inputs the conditions "I have an egg allergy" and "I want to avoid caffeine," the server uses the generative model to filter products and meal plans from the database that match these conditions. If the emotion engine uses the smartphone's camera and microphone to identify that the user is feeling "stressed," suggestions might include decaffeinated herbal teas and foods that help reduce stress.

[1435] Example prompt sentence:

[1436] "If a user inputs that they have an egg allergy and want to avoid caffeine, and the system detects through their smartphone's camera and microphone that they are feeling stressed, the system will suggest decaffeinated herbal teas and foods that help reduce stress."

[1437] In this way, it becomes possible to offer highly personalized products and meal plans based on comprehensive data, including the user's emotional state.

[1438] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1439] Step 1:

[1440] The server retrieves product information over the network. Inputs include API endpoints and data files, and outputs a product information dataset containing product names, nutritional information, ingredient lists, allergen information, etc. The data is received in JSON format and stored in an internal database.

[1441] Step 2:

[1442] The server uses deep learning algorithms to build a generative model based on product information stored in an internal database. The input includes product information from the database, and the output is a generative model for predicting products and meal plans that meet the user's criteria. Specifically, machine learning frameworks such as Keras and TensorFlow are used.

[1443] Step 3:

[1444] Users input their dietary restrictions and nutritional requirements using a device such as a smartphone. The input data includes allergy information, avoidance of specific food ingredients, and nutritional requirements based on health conditions. The device then transmits this data to a server.

[1445] Step 4:

[1446] The server receives the dietary restrictions and nutritional requirements sent by the user and performs filtering based on those requirements. The input includes the user's requirements data and product information in the database, and the output is a list of products and meal plans that match the requirements.

[1447] Step 5:

[1448] The device uses the user's camera and microphone to recognize emotions from the user's facial expressions and voice. Inputs include camera feed and audio input, and outputs provide data indicating the user's emotional state. An emotion engine analyzes information such as whether the user is feeling stressed.

[1449] Step 6:

[1450] The server adjusts the recommendations based on the user's perceived emotional state. The input includes the user's emotional data and the filtering results, and the output is a product list or meal plan that takes the user's emotional state into account. For example, if the user is feeling stressed, the server suggests foods and drinks that have a relaxing effect.

[1451] Step 7:

[1452] The server sends the generated products and meal plans to the device. The input includes the final product list and meal plan, and the output is the suggestions displayed on the user's device. The device displays the suggestions to the user, allowing the user to identify foods and meal plans that fit their dietary restrictions, nutritional requirements, and emotional state.

[1453] Step 8:

[1454] The user reviews the suggested products and meal plans and selects the products they want to purchase. The input includes product information selected from the suggestions, and the output is a list of products added to the cart. The user can then proceed with the purchase process based on this list.

[1455] 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.

[1456] 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.

[1457] 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.

[1458] [Fourth embodiment]

[1459] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1460] 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.

[1461] 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).

[1462] 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.

[1463] 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.

[1464] 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).

[1465] 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.

[1466] 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.

[1467] 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.

[1468] 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.

[1469] 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.

[1470] 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.

[1471] 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."

[1472] ---

[1473] The present invention is a system that allows people who have allergies, illnesses, dietary restrictions during pregnancy, or who need nutritional management for building a healthy body to easily select commercially available foods and boxed lunches. This system acquires product information via a network and provides products and meal plans that match the user's dietary restrictions and nutritional requirements. Specific embodiments of the system are described below.

[1474] Obtaining and storing product information

[1475] server

[1476] The server obtains product information from online supermarkets and bento shops via API or data files, including product names, nutritional information, ingredient lists, and allergen information.

[1477] The acquired product information is stored in a database.

[1478] Learning and Generative Model Building

[1479] server

[1480] Using product information stored in a database, a machine learning algorithm (e.g., deep learning) is used to build a generative model that learns detailed information about the product and can make predictions and classifications for new data.

[1481] Input from the user

[1482] User

[1483] Users use devices such as smartphones or computers to input their own dietary restrictions and nutritional requirements, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on their health status.

[1484] Sending and matching conditions

[1485] Terminal

[1486] The dietary restrictions and nutritional conditions entered by the user are sent from the terminal to the server.

[1487] server

[1488] The server uses the generative model to generate products, lunch boxes, and even daily meal plans that match the user's criteria, filtering the foods that match the criteria based on information stored in the database.

[1489] Proposals and Presentations

[1490] server

[1491] The server sends the generated product list and meal plan to the user's terminal.

[1492] Terminal

[1493] The device displays the suggestions sent from the server to the user, allowing the user to easily find foods and meal plans that fit their dietary restrictions and nutritional requirements.

[1494] User

[1495] The user can then review the suggested products and select the ones they wish to purchase. The selected products are added to the cart and the user can proceed with the purchase.

[1496] Specific examples

[1497] For example, if a user has conditions such as "egg allergy" and "avoid caffeine," they can input these conditions via their smartphone. The server uses the generative model to filter products and meal plans from the database that match these conditions and generate suggestions. Suggested foods include caffeine-free beverages and egg-free ingredients. Users can review these suggestions and safely select them, eliminating the need to go through the trouble of searching for foods that meet multiple conditions.

[1498] This system allows customers with multiple dietary restrictions to easily select foods that suit them, significantly reducing the burden of dietary management. It can also provide meal plans tailored to individual needs for users who need to manage diabetes or who are following specific diet plans.

[1499] ---

[1500] The processing flow will be explained below.

[1501] ---

[1502] Step 1:

[1503] server

[1504] Product information is obtained from online supermarkets and bento shops via API or data files.

[1505] Product information includes product name, nutritional information, ingredient list, and allergen information.

[1506] The obtained product information is saved in the database.

[1507] Step 2:

[1508] server

[1509] Based on the product information stored in the database, a generative model is constructed using machine learning algorithms (e.g., deep learning).

[1510] Generative models are trained with product information that can later be used for prediction and classification.

[1511] Step 3:

[1512] User

[1513] Users enter their dietary restrictions and nutritional requirements using a device such as a smartphone or computer.

[1514] For example, enter conditions such as "egg allergy" or "want to avoid caffeine."

[1515] Step 4:

[1516] Terminal

[1517] The dietary restrictions and nutritional conditions entered by the user are sent to the server.

[1518] Step 5:

[1519] server

[1520] The server receives the conditions sent by the user.

[1521] It uses a generative model to match product information in the database with the user's criteria and filter out matching products and meal plans.

[1522] Step 6:

[1523] server

[1524] Based on the filtered product information, proposals tailored to individual user conditions are generated.

[1525] Suggestions include a list of suitable products and a daily meal plan.

[1526] Step 7:

[1527] server

[1528] The generated proposal content is transmitted to the user's terminal.

[1529] Step 8:

[1530] Terminal

[1531] The terminal displays the proposal sent from the server to the user.

[1532] For example, it could be displayed in the format "Recommended breakfast: Decaffeinated coffee and eggless sandwich."

[1533] Step 9:

[1534] User

[1535] Check out suggested products and meal plans.

[1536] Select the product you want to purchase and add it to your cart.

[1537] Proceed with the purchase of items added to your cart.

[1538] ---

[1539] In this way, users can easily select products that fit their dietary restrictions and nutritional requirements. Furthermore, the recommendations provided are highly accurate thanks to the generative model.

[1540] Example 1

[1541] 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."

[1542] Currently, when selecting commercially available foods or bento boxes, it is difficult for users to find products that meet their allergies, illnesses, dietary restrictions during pregnancy, or nutritional management requirements for building a healthy body. This poses a problem in that it takes a great deal of time and effort for users to select foods that meet their requirements.

[1543] 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.

[1544] In this invention, the server includes means for acquiring product information via a network, means for storing the product information in a database, means for building a generative AI model that learns based on the product information stored in the database, means for the user to input dietary restrictions and nutritional requirements, means for transmitting the dietary restrictions and nutritional requirements input by the user to the server, means for the server to use the generative AI model to generate products and meal plans that meet the dietary restrictions and nutritional requirements, means for presenting the generated products and meal plans to the user, and means for adding products selected by the user from the presented products and meal plans to the purchasing process. This allows the user to easily select foods that meet their requirements and significantly reduces the burden of dietary management.

[1545] A "network" is a system in which multiple computers or devices are connected so that they can communicate with each other.

[1546] "Product information" refers to information about a product that includes data such as the product's name, nutritional value, ingredient list, and allergen information.

[1547] A "database" is a system for efficiently storing, retrieving, and managing organized data.

[1548] A "generative AI model" is a model that has been trained using machine learning algorithms to make new predictions or classifications based on data.

[1549] "User" refers to any individual or organization that uses the system or service.

[1550] A "dietary restriction" is a restriction that prevents the intake of certain foods or ingredients for health reasons.

[1551] "Nutritional requirements" are the nutrient requirements you need or want to avoid based on a specific health condition or goal.

[1552] A "server" is a computer system that provides services to clients over a network.

[1553] A "product list" is a list that refers to a collection of products selected based on specific conditions.

[1554] A "meal plan" refers to a suggestion or plan for meals over a day or period of time.

[1555] A "purchase process" refers to a series of procedures or steps a user takes to purchase a selected product.

[1556] The present invention provides a system that allows people who have allergies, illnesses, dietary restrictions during pregnancy, or who need nutritional management for building a healthy body to easily select commercially available foods and boxed lunches. This system acquires product information via a network and provides products and meal plans that match the user's dietary restrictions and nutritional requirements. Specific embodiments of the system are described below.

[1557] Obtaining and storing product information

[1558] server

[1559] The server collects product information from online supermarkets and bento shops via API or data files, including product names, nutritional information, ingredient lists, and allergen information.

[1560] The server stores the acquired product information in a database.

[1561] Specific examples

[1562] The server communicates with the online supermarket's API every day at midnight to retrieve new and updated product information, and then adds or updates this information to the database.

[1563] Example prompt sentence:

[1564] "Please use the Rakuten Market API to update all product information daily and store it in the database."

[1565] Learning and Generative Model Building

[1566] server

[1567] The server uses machine learning algorithms (e.g., deep learning) to train a generative AI model based on the product information stored in the database. The generative AI model learns detailed information about the product and makes predictions and classifications based on the user's criteria.

[1568] Specific examples

[1569] The server uses TensorFlow to train a new model each week based on the stored product information, which can then score each product taking into account allergen information and nutritional value.

[1570] Example prompt sentence:

[1571] "Use TensorFlow to build a model that learns all the product information in your database and classifies products that meet the user's criteria."

[1572] Input from the user

[1573] User

[1574] Users use devices such as smartphones or computers to input their own dietary restrictions and nutritional requirements, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on their health status.

[1575] Specific examples

[1576] The user launches the app and enters "egg allergy" and "caffeine avoidance" on the profile screen, which updates the user profile within the app.

[1577] Example prompt sentence:

[1578] "Enter any allergies or food ingredients you are avoiding. For example, egg allergy, caffeine avoidance."

[1579] Sending and matching conditions

[1580] Terminal

[1581] The dietary restrictions and nutritional conditions entered by the user are sent from the terminal to the server.

[1582] server

[1583] Once the server receives the user's criteria, it stores them in a database and then uses a deep learning model to filter products that match the criteria. Based on the filtered results, it generates a product list and a daily meal plan that meets the user's criteria.

[1584] Specific examples

[1585] The device sends the conditions "egg allergy" and "caffeine avoidance" to the server. The server receives this and uses the database and deep learning model to search for products that meet the conditions. For example, "egg-free bread" and "caffeine-free drinks" are matched.

[1586] Example prompt sentence:

[1587] "Match products based on input criteria and generate a daily meal plan using a generative model."

[1588] Proposals and Presentations

[1589] server

[1590] The server generates a product list and meal plan that meets the user's requirements and sends it to the user's terminal.

[1591] Terminal

[1592] The terminal displays the product list and meal plan sent from the server to the user.

[1593] User

[1594] Users can review the suggested products and meal plans and select the products they wish to purchase, which are then added to their cart and they can proceed with the checkout.

[1595] Specific examples

[1596] The server sends "egg-free bread" and "caffeine-free beverage" to the terminal. The user confirms this and adds the items they want to purchase to their cart. They then proceed with the purchase.

[1597] Example prompt sentence:

[1598] "Design a UI that suggests and displays products and meal plans that match the user's criteria."

[1599] This system allows users with allergies or dietary restrictions to easily select foods that suit them, significantly reducing the burden of dietary management. It also accommodates users following specific diet plans.

[1600] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1601] Step 1:

[1602] The server acquires the product information via the network.

[1603] Input: API request from online supermarket or bento shop

[1604] Specific operation: The server executes an API request every day at midnight to obtain new products and updated information.

[1605] Output: Product information returned from the API (product name, nutritional information, ingredient list, allergen information)

[1606] Step 2:

[1607] The server stores the acquired product information in a database.

[1608] Input: Product information obtained in Step 1

[1609] Specific operation: The server performs the process of adding or updating the product information in the database.

[1610] Output: Product information stored in the database

[1611] Step 3:

[1612] The server builds a generative AI model based on product information stored in the database.

[1613] Input: Product information stored in the database

[1614] Specific operation: The server uses TensorFlow to train a deep learning model and build a model based on product information.

[1615] Output: The generated deep learning model

[1616] Step 4:

[1617] Users input their dietary restrictions and nutritional requirements via their smartphone or computer.

[1618] Input: User's dietary restrictions or nutritional requirements (e.g., egg allergy, caffeine avoidance)

[1619] Specific operation: The user enters the conditions in the device app, which are then saved in the system.

[1620] Output: Entered dietary restrictions and nutritional conditions

[1621] Step 5:

[1622] The terminal transmits the conditions entered by the user to the server.

[1623] Input: Input data for dietary restrictions and nutritional conditions

[1624] Specific operation: The terminal executes a request to send the user's conditions to the server.

[1625] Output: User criteria sent to server

[1626] Step 6:

[1627] The server receives the user's requirements and uses the database and generative AI model to generate products and meal plans that meet the requirements.

[1628] Input: User conditions sent to the server, product information stored in the database, generated deep learning model

[1629] What it does: The server uses the user's criteria as filtering criteria to search and score products in the database and generate products and meal plans that best fit the criteria.

[1630] Output: A list of products and meal plans that match your criteria

[1631] Step 7:

[1632] The server transmits the generated product list and meal plan to the user's terminal.

[1633] Input: A list of products or meal plans that match your criteria

[1634] Specific operation: The server generates the proposal and executes a request to send it to the user's device.

[1635] Output: Product list and meal plan sent to the device

[1636] Step 8:

[1637] The terminal displays the product list and meal plan sent from the server to the user.

[1638] Input: Product list or meal plan sent from the server

[1639] Specific operation: The device displays the received product list and meal plan on the screen and notifies the user.

[1640] Output: Displayed product list and meal plan

[1641] Step 9:

[1642] The user reviews the suggested products and meal plans and selects the products they wish to purchase.

[1643] Input: Displayed product list or meal plan

[1644] Specific operation: The user selects the product they want to purchase on the screen and adds it to their cart.

[1645] Output: Items added to cart

[1646] Step 10:

[1647] The user then carries out the procedure to purchase the product added to the cart.

[1648] Input: Items added to cart

[1649] What happens: The user proceeds to the checkout screen, enters payment information, and completes the order.

[1650] Output: Completed order items

[1651] (Application example 1)

[1652] 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."

[1653] People who have dietary restrictions or nutritional needs have difficulty finding foods that do not contain allergens or specific ingredients when choosing commercially available foods or bento boxes. Furthermore, there are few ways to check this information in real time while shopping in physical stores, which places a significant burden on them when making appropriate product selections.

[1654] 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.

[1655] In this invention, the server includes: means for acquiring product information via a network; means for storing the product information in a database; means for constructing a generative model that learns based on the product information stored in the database; means for allowing a user to input dietary restrictions and nutritional requirements; means for transmitting the dietary restrictions and nutritional requirements input by the user to the server; means for the server to use the generative model to generate products and meal plans that meet the dietary restrictions and nutritional requirements; means for presenting the generated products and meal plans to the user; and means for scanning a barcode using a smartphone when a user selects a product in a physical store, comparing the scanned product information with the user's input conditions to determine whether the conditions are met, and presenting the result to the user. This enables users to easily find and select products that meet their conditions in real time while shopping in a physical store.

[1656] "Means for acquiring product information via a network" refers to a function for externally collecting information about various products, such as product names, nutritional value information, ingredient lists, and allergen information, via a network such as the Internet.

[1657] The "means for saving product information in a database" is a function for recording acquired product information in a database in a structured format for later retrieval and analysis.

[1658] The "means for constructing a generative model" is a function that uses a machine learning algorithm, such as deep learning, to create a model for generating products and meal plans based on product information stored in the database.

[1659] "Means for inputting dietary restrictions and nutritional requirements" is a function that provides an interface for users to input information about their allergies, ingredients they want to avoid, specific nutritional requirements, and so on.

[1660] The "means for transmitting dietary restrictions and nutritional conditions to the server" is a function for transferring information entered by the user to the server and processing it.

[1661] "Means for using a generative model to generate products and meal plans that meet dietary restrictions and nutritional requirements" is a function that uses the constructed generative model to calculate and generate products and meal plans that meet the user's requirements.

[1662] "Means for presenting generated products and meal plans to users" refers to a function that displays products and meal plans generated by the server on the user's device (such as a smartphone).

[1663] "A means of scanning barcodes using a smartphone when selecting products in a physical store...and presenting the results to the user" refers to a function that reads the barcode of a product with a smartphone when the user is shopping in a store, compares the product information with the user's conditions, and notifies the user in real time whether the product is a match.

[1664] The present invention provides a system that allows people who have allergies, illnesses, dietary restrictions during pregnancy, or who need nutritional management for building a healthy body to easily select commercially available foods and boxed lunches. This system acquires product information via a network and provides products and meal plans that match the user's dietary restrictions and nutritional requirements. Specific embodiments of the system are described below.

[1665] Obtaining and storing product information

[1666] The server obtains product information from online supermarkets and bento shops via API or data files. This product information includes the product name, nutritional value information, ingredient list, and allergen information. The obtained product information is stored in a database.

[1667] Learning and Generative Model Building

[1668] The server uses machine learning algorithms (e.g., deep learning) to build a generative model based on the product information stored in the database. This generative model learns detailed information about the product and can make predictions and classifications for new data.

[1669] Input from the user

[1670] Users use devices such as smartphones or computers to input their own dietary restrictions and nutritional requirements, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on their health status.

[1671] Sending and matching conditions

[1672] The user's dietary restrictions and nutritional requirements are sent from the device to the server, which uses a generative model to generate products, lunch boxes, and even daily meal plans that fit the user's requirements, filtering the foods that match the requirements based on information stored in the database.

[1673] Proposals and Presentations

[1674] The server sends the generated product list and meal plan to the user's device. The device displays the suggestions sent from the server to the user. This allows the user to easily check foods and meal plans that fit their dietary restrictions and nutritional requirements. The user reviews the suggested products and selects the products they wish to purchase. The selected products are added to the cart, and the user can proceed with the purchase.

[1675] Examples of applications in physical stores

[1676] When selecting a product in a physical store, a user can scan the product's barcode using their smartphone. The server uses the scanned barcode information to match product information with the user's input criteria. The matching results are presented to the user in real time, and the server determines whether the conditions are met and displays the results. For example, if a user has conditions such as "egg allergy" and "desire to avoid caffeine," the user enters these conditions via their smartphone. When a product is scanned in a physical store, the server uses a generative model to determine whether the product matches these conditions from the database and displays the results on the smartphone. Suggested foods include caffeine-free beverages and egg-free ingredients. Users can review these suggestions and make a safe selection, eliminating the need to search for foods that meet multiple conditions.

[1677] Prompt Sentence Examples

[1678] A concrete example of an input prompt for a generative AI model could be in the form of text like this:

[1679] Create a system that determines whether a user's dietary restrictions or allergies are met based on a scenario in which the user scans a product's barcode with their smartphone while shopping in a store. Product information is retrieved from an API and includes allergen information and ingredients. The user's conditions are egg allergy and caffeine avoidance. If the conditions are met, display a message saying "Conditions met." If not, display a message saying "Conditions not met." Please also provide specific code examples.

[1680] The above is a specific embodiment for carrying out the present invention, which enables a user to select appropriate products in real time while shopping in a physical store.

[1681] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1682] Step 1:

[1683] The server obtains product information via the network. Specifically, the server collects product information from online supermarkets and bento shops via API or data files. This product information includes the product name, nutritional value information, ingredient list, allergen information, etc. The input is data from an external API or file, and the output is the obtained product information. The server saves this information in a database.

[1684] Step 2:

[1685] The server learns from the product information stored in the database and builds a generative model. The server uses machine learning algorithms (e.g., deep learning) to learn detailed information about the products. The input is the product information stored in the database and the output is the generated model. This generative model is used to make predictions and classifications on new data.

[1686] Step 3:

[1687] Users use their smartphones or computers to input their own dietary restrictions and nutritional requirements. Specifically, they use the smartphone application screen to input allergy information, ingredients to avoid, specific nutritional requirements, etc. The user's condition information is input, and these conditions are sent to the server as output.

[1688] Step 4:

[1689] The server receives the user's dietary restrictions and nutritional requirements sent from the device. The server uses a generative model based on the received requirements to generate matching products and meal plans. The input is the user's requirements, and the output is a list of matching products and meal plans. The server filters the product information stored in the database to find foods that match the requirements.

[1690] Step 5:

[1691] The server sends the generated product list and meal plan to the user's device. The device displays the suggestions sent from the server to the user. The input is the generated product list and meal plan from the server, and the output is the suggestions displayed to the user on the device screen. The user can easily check foods and meal plans that fit their own dietary restrictions and nutritional requirements.

[1692] Step 6:

[1693] When a user selects a product in a physical store, they use their smartphone to scan the product's barcode. The terminal acquires the scanned barcode information and sends it to a server. The input is the barcode scanned by the smartphone, and the output is the barcode information sent to the server.

[1694] Step 7:

[1695] The server receives the scanned barcode information and retrieves the product information from the database. It then compares it with the user's input conditions. The server uses a generative model to match the scanned product information with the user's conditions and determine whether the conditions are met. The input is the barcode information and the user's conditions, and the output is the result of a judgment on whether the conditions are met.

[1696] Step 8:

[1697] The server sends the judgment result to the user's terminal. The terminal displays the result to the user. The input is the judgment result sent from the server, and the output is the matching result displayed on the terminal screen. The user can check the display and determine in real time whether the condition is met.

[1698] The above are the specific processing steps for carrying out the present invention, which enable users to easily find and select products that meet their requirements in real time while shopping in a physical store.

[1699] 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.

[1700] ---

[1701] This invention is a system that provides products and meal plans that match a user's dietary restrictions and nutritional requirements, and aims to provide more personalized suggestions to each user by combining it with an emotion engine that recognizes the user's emotions. This system obtains product information via a network and provides products and meal plans that match the user's requirements.

[1702] Obtaining and storing product information

[1703] server

[1704] Product information is obtained from online supermarkets and bento shops via API or data files. This information includes the product name, nutritional value, ingredient list, and allergen information.

[1705] The obtained product information is saved in the database.

[1706] Learning and Generative Model Building

[1707] server

[1708] Based on the product information stored in the database, a machine learning algorithm (e.g., deep learning) is used to build a generative model. The generative model learns the product information and makes predictions and classifications for newly input data.

[1709] Input from the user

[1710] User

[1711] Users can use devices such as smartphones or computers to input their own dietary restrictions and nutritional requirements, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on their health status.

[1712] Sending and matching conditions

[1713] Terminal

[1714] The dietary restrictions and nutritional conditions entered by the user are sent to the server.

[1715] server

[1716] The server receives the conditions sent by the user and uses a generative model to match the product information in the database with the user's conditions and filter out matching products and meal plans.

[1717] Emotion recognition and suggestion adjustment

[1718] Terminal

[1719] The emotion engine uses the user's device's camera and microphone to recognize emotions from the user's facial expressions and voice. This feature is activated during initial setup or regular use.

[1720] server

[1721] Based on the emotional state recognized by the emotion engine, the server will tailor the recommendations, for example, if the user is feeling stressed, it will suggest foods and drinks that have a relaxing effect.

[1722] Proposals and Presentations

[1723] server

[1724] Based on the results of the filtering and sentiment engine, it generates product lists and daily meal plans tailored to individual user requirements.

[1725] server

[1726] The generated proposal content is transmitted to the user's terminal.

[1727] Terminal

[1728] The device displays the suggestions sent from the server to the user, allowing the user to easily check foods and meal plans that fit their dietary restrictions and nutritional requirements.

[1729] User

[1730] Users can review the suggested products and meal plans, select the products they want to purchase, and the selected products are added to their cart to proceed with the purchase.

[1731] Specific examples

[1732] For example, if a user inputs the conditions "I have an egg allergy" and "I want to avoid caffeine," the server uses the generative model to filter products and meal plans from the database that match these conditions. If the emotion engine uses the smartphone's camera and microphone to identify that the user is feeling "stressed," suggestions might include decaffeinated herbal teas and foods that help reduce stress.

[1733] The system allows users to select foods appropriate for their emotional state, as well as their dietary restrictions and nutritional requirements, for a more personalized service. It can also provide meal plans tailored to individual needs for users who need to manage diabetes or follow specific diet plans.

[1734] ---

[1735] The processing flow will be explained below.

[1736] ---

[1737] Step 1:

[1738] server

[1739] Product information is obtained from online supermarkets and bento shops via API or data files.

[1740] Product information includes product name, nutritional information, ingredient list, and allergen information.

[1741] The obtained product information is saved in the database.

[1742] Step 2:

[1743] server

[1744] Based on the product information stored in the database, a generative model is constructed using machine learning algorithms (e.g., deep learning).

[1745] The generative model learns product information and is given the ability to make predictions and classifications on newly input data.

[1746] Step 3:

[1747] User

[1748] Users enter their own dietary restrictions and nutritional requirements using a device such as a smartphone or computer.

[1749] Inputs include allergy information, avoidance of certain food ingredients, and nutritional requirements based on health conditions.

[1750] Step 4:

[1751] Terminal

[1752] The dietary restrictions and nutritional conditions entered by the user are sent to the server.

[1753] Step 5:

[1754] server

[1755] Receive dietary restrictions and nutritional requirements submitted by users.

[1756] It uses a generative model to match product information in a database with the user's criteria and filter out matching products and meal plans.

[1757] Step 6:

[1758] Terminal

[1759] The emotion engine uses the camera and microphone on the user's device to recognize emotions from the user's facial expressions and voice.

[1760] Emotion recognition is performed when the user inputs dietary restrictions and nutritional requirements.

[1761] Step 7:

[1762] server

[1763] The emotional state of the user recognized by the emotion engine is received and the suggestions are adjusted accordingly.

[1764] For example, if a user is feeling stressed, the app suggests foods and drinks that have a relaxing effect.

[1765] Step 8:

[1766] server

[1767] Based on the tailored suggestions, it generates a product list and daily meal plan tailored to the individual user's requirements.

[1768] Step 9:

[1769] server

[1770] The generated proposal content is transmitted to the user's terminal.

[1771] Step 10:

[1772] Terminal

[1773] The terminal displays the proposal sent from the server to the user.

[1774] For example, it could be displayed in the format "Recommended breakfast: Decaffeinated coffee and eggless sandwich."

[1775] Step 11:

[1776] User

[1777] Review the suggested products and meal plans and select the products you want to purchase.

[1778] The selected items will be added to your cart and you can proceed with the purchase.

[1779] ---

[1780] Through this specific processing step, users can easily select products and meal plans that fit their emotional state as well as their dietary restrictions and nutritional requirements.

[1781] Example 2

[1782] 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."

[1783] In modern society, users have a wide variety of dietary restrictions and nutritional requirements. Furthermore, users often want to make choices based on their emotional state. However, conventional systems have been inadequate in providing products and meal plans that take the user's emotional state into account, making it difficult to provide personalized recommendations. Furthermore, incorporating emotion recognition technology into a meal recommendation system would enable recommendations that are more tailored to individual users' needs, but no system has been able to achieve this.

[1784] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring product information via a network, means for storing the product information in a database, means for constructing a generative model that learns based on the product information stored in the database, means for analyzing the user's facial expressions and voice to recognize emotions, means for adjusting the generated products and meal plans based on the recognized emotions, and means for presenting the adjusted products and meal plans to the user. This enables the user to receive personalized products and meal plans that are tailored to their emotional state in addition to their dietary restrictions and nutritional requirements.

[1785] A "network" is a communications system that connects multiple computers or devices to send and receive data.

[1786] "Product information" refers to information about the product's characteristics and contents, such as the product's name, nutritional value information, ingredient list, and allergen information.

[1787] A "database" is a system or software that allows data to be efficiently stored, searched, and edited.

[1788] A "generative model" is a model built using machine learning algorithms to make predictions or classifications based on specific data.

[1789] A "user" is an individual or group that uses this system, and is the entity that provides input and instructions to the system.

[1790] "Dietary restrictions" refers to restricting the intake of certain foods or ingredients based on allergies, health conditions, religious beliefs, etc.

[1791] "Nutritional requirements" are requirements or conditions regarding a diet that a user follows with a focus on consuming specific nutrients.

[1792] A "server" is a computer system that provides data and services to other computers on a network.

[1793] "Emotion recognition" is a technology that analyzes and identifies a user's current emotional state from their facial expressions and voice.

[1794] "Personalized recommendations" refers to product and meal plan recommendations optimized for each individual user's dietary restrictions, nutritional requirements, and even emotional state.

[1795] The present invention is a system that provides products and meal plans that match a user's dietary restrictions and nutritional requirements, and aims to provide more personalized suggestions to each user by combining it with an emotion engine that recognizes the user's emotions. This system is implemented in the following steps.

[1796] Obtaining and storing product information

[1797] server

[1798] The server obtains product information via the network. Specifically, it collects product information from online supermarkets and bento shops via API or data files. This product information includes the product name, nutritional value information, ingredient list, and allergen information.

[1799] The acquired product information is stored in a database. MySQL or PostgreSQL are suitable database management systems. The table that stores product information contains columns for basic product information, nutritional value, and allergen information.

[1800] Learning and Generative Model Building

[1801] server

[1802] The server uses machine learning algorithms to build generative models based on product information stored in a database, using libraries such as TensorFlow and PyTorch.

[1803] Preprocess the data, handle missing values, normalize, etc. Then use the preprocessed data to train a model and build a generative model that classifies products that meet certain criteria.

[1804] The trained model is saved as a file and used for subsequent prediction processing.

[1805] Input from the user

[1806] User

[1807] Users use devices such as smartphones or PCs to input their own dietary restrictions and nutritional requirements. This input includes allergy information, avoidance of specific food ingredients, nutritional requirements based on health status, etc. The input information is sent to the server via the device's application.

[1808] Sending and matching conditions

[1809] Terminal

[1810] The device sends the dietary restrictions and nutritional requirements entered by the user to the server, for example, by sending serialized data in JSON format via an HTTP POST request.

[1811] server

[1812] The server uses the generative model to match product information based on the received user criteria, calculates a score for products that match the criteria, and filters out the top candidates.

[1813] The filtered product list is temporarily saved.

[1814] Emotion recognition and suggestion adjustment

[1815] Terminal

[1816] The device's emotion engine uses the camera and microphone to analyze the user's facial expressions and voice to recognize emotions. OpenCV and Emotion API are suitable software for this purpose.

[1817] The recognized emotion data is sent to the server in JSON format.

[1818] server

[1819] The server then adjusts its suggestions based on the received emotional data, for example, recommending foods and drinks that have a relaxing effect if the user is feeling stressed.

[1820] Proposals and Presentations

[1821] server

[1822] The server generates tailored recommendations and sends them to the user's device, which are presented as product lists and daily meal plans.

[1823] Terminal

[1824] The terminal analyzes the proposals sent from the server and displays them on a user interface, for example, using a tree view or list view to display product information.

[1825] User

[1826] Users can review the suggested products and meal plans, select the products they want to purchase, and the selected products are added to their cart to proceed with the purchase.

[1827] Specific examples

[1828] For example, if a user inputs the criteria "I have an egg allergy" and "I want to avoid caffeine," the server uses the generative model to filter products and meal plans from the database that fit those criteria. If the user's emotion engine recognizes "stress," suggestions might include decaffeinated herbal teas and foods that help reduce stress.

[1829] Prompt Sentence Examples

[1830] "I have an egg allergy and would like to avoid caffeine. Can you recommend any foods or drinks? I've also been feeling stressed lately."

[1831] In this way, the present invention can provide personalized products and meal plans tailored to a user's dietary restrictions, nutritional requirements, and emotional state, thereby enabling users to make better food choices and improve the quality of their diet.

[1832] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1833] Step 1: Retrieve and store product information

[1834] server

[1835] The server obtains product information via the network. Specifically, it collects product information from online supermarkets and bento shops via API or data files.

[1836] The server stores the retrieved product information in a database, including the product name, nutritional information, ingredient list, and allergen information.

[1837] Input: API endpoint URL of online supermarket or bento shop

[1838] Output: Product information stored in the database

[1839] Step 2: Building a training and generative model

[1840] server

[1841] The server reads product information from a database and builds a generative model using machine learning algorithms, such as TensorFlow and PyTorch.

[1842] Data preprocessing involves processing missing values ​​and normalization.

[1843] Train the model using the training data and save the model as a file.

[1844] Input: Product information retrieved from the database

[1845] Output: Trained generative model file

[1846] Step 3: User Input

[1847] User

[1848] Users can input their dietary restrictions and nutritional requirements via smartphone or computer, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on health conditions.

[1849] Input: Information about dietary restrictions and nutritional requirements

[1850] Output: Input data saved on the device

[1851] Step 4: Sending and matching conditions

[1852] Terminal

[1853] The terminal converts the data entered by the user into JSON format and sends it to the server via an HTTP POST request.

[1854] Input: User's dietary restrictions and nutritional requirements

[1855] Output: JSON data sent to the server

[1856] server

[1857] The server analyzes the received user requirements, compares them with product information using a generative model, calculates a score for matching products, and filters the top candidates.

[1858] Input: Received condition data in JSON format

[1859] Output: Filtered product list

[1860] Step 5: Recognize emotions and adjust suggestions

[1861] Terminal

[1862] The device's emotion engine uses the camera and microphone to analyze the user's facial expressions and voice to recognize emotions. OpenCV and Emotion API are suitable software for this purpose.

[1863] The recognized emotion data is sent to the server in JSON format.

[1864] Input: User's facial expressions and voice data

[1865] Output: Emotion data sent to the server

[1866] server

[1867] The server adjusts its suggestions based on the received emotional data. For example, if the user is feeling stressed, it will increase the number of products that have a relaxing effect.

[1868] Input: Received emotion data

[1869] Output: Tailored product list and meal plan

[1870] Step 6: Proposal and Presentation

[1871] server

[1872] The server generates the adjusted proposal and sends it to the user's device in JSON format.

[1873] Input: Tailored product list and meal plan

[1874] Output: JSON data sent to the terminal

[1875] Terminal

[1876] The terminal analyzes the proposals sent from the server and displays them in a user interface, for example, by using a tree view or list view to display product information.

[1877] Input: JSON data received from the server

[1878] Output: Product information and meal plan presented to the user

[1879] Step 7: User Actions

[1880] User

[1881] Users can review the suggested products and meal plans, select the products they want to purchase, and the selected products are added to their cart to proceed with the purchase.

[1882] Input: User's choice

[1883] Output: List of items added to cart

[1884] (Application example 2)

[1885] 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."

[1886] Conventional meal plan suggestion systems can provide products and meal plans that meet a user's dietary restrictions and nutritional requirements, but they do not take into account the user's emotional state. As a result, they are unable to provide foods and meal plans that are optimal for the user's current emotional state, and further personalization is required.

[1887] 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.

[1888] In this invention, the server includes means for acquiring product information via a network, means for storing the product information in a database, means for constructing a generative model that learns based on the product information stored in the database, means for the user to input dietary restrictions and nutritional requirements, means for recognizing the user's emotions using a camera and a microphone, means for adjusting the content of suggestions based on the recognized emotions, and means for presenting the generated products and meal plans to the user. This makes it possible to provide highly personalized products and meal plans based on comprehensive data including the user's emotional state.

[1889] "Product information" refers to detailed product data that is acquired via a network and stored in a database, and includes nutritional values, ingredient lists, allergen information, and the like.

[1890] "Database" means an information system that stores product information and allows it to be accessed, searched, and updated.

[1891] A "generative model" is a model that is built using machine learning algorithms based on product information to generate products and meal plans that meet the user's requirements.

[1892] "Dietary restrictions and nutritional requirements" refers to dietary restrictions or requirements set by a user based on their own health condition, allergies, or requests to avoid certain ingredients.

[1893] The "camera and microphone" are visual and audio input devices for recognizing the user's facial expressions and voice, and are used in combination with the emotion engine.

[1894] "Means for recognizing emotions" refers to a system or algorithm that uses a camera and microphone to analyze the user's facial expressions and voice and determine the user's emotional state.

[1895] The "means for adjusting the proposal content" is a function for modifying or optimizing the content of the generated products or meal plans based on the user's emotional state recognized by the emotion engine.

[1896] The present invention is a system for proposing optimal products and meal plans based on a user's dietary restrictions, nutritional requirements, and emotional state. Specific embodiments of the system are described below.

[1897] Obtaining and storing product information

[1898] The server retrieves product information via the network and stores it in a database. Product information includes nutritional information, ingredient lists, and allergen information. This creates a foundation for quickly providing information that meets the user's requirements.

[1899] Learning and Generative Model Building

[1900] The server uses machine learning algorithms (e.g., deep learning) to build a generative model based on the product information stored in the database. The generative model learns the product information and makes predictions and classifications for newly input data.

[1901] Input from the user

[1902] Users use devices such as smartphones to input their own dietary restrictions and nutritional requirements, including allergy information, avoidance of certain food ingredients, and nutritional requirements based on their health status.

[1903] Sending and matching conditions

[1904] The device sends the dietary restrictions and nutritional requirements entered by the user to the server, which then uses the generative model to match the user's requirements with product information in the database and filter out matching products and meal plans.

[1905] Emotion recognition and suggestion adjustment

[1906] The device uses a camera and microphone to recognize emotions from the user's facial expressions and voice. This function is activated during initial setup or regular use. The server then adjusts the suggestions based on the emotional state recognized by the emotion engine. For example, if the user is feeling stressed, it will suggest foods and drinks that have a relaxing effect.

[1907] Proposals and Presentations

[1908] Based on the results of the filtering and emotion engine, the server generates a product list and daily meal plan tailored to each user's individual requirements and sends it to the device. The device displays the suggestions sent from the server to the user, allowing the user to easily check foods and meal plans that suit their own dietary restrictions, nutritional requirements, and emotional state.

[1909] Users can review the suggested products and meal plans, select the products they want to purchase, and the selected products are added to their cart to proceed with the purchase.

[1910] Specific examples

[1911] For example, if a user inputs the conditions "I have an egg allergy" and "I want to avoid caffeine," the server uses the generative model to filter products and meal plans from the database that match these conditions. If the emotion engine uses the smartphone's camera and microphone to identify that the user is feeling "stressed," suggestions might include decaffeinated herbal teas and foods that help reduce stress.

[1912] Example prompt sentence:

[1913] "If a user inputs that they have an egg allergy and want to avoid caffeine, and the system detects through their smartphone's camera and microphone that they are feeling stressed, the system will suggest decaffeinated herbal teas and foods that help reduce stress."

[1914] In this way, it becomes possible to offer highly personalized products and meal plans based on comprehensive data, including the user's emotional state.

[1915] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1916] Step 1:

[1917] The server retrieves product information over the network. Inputs include API endpoints and data files, and outputs a product information dataset containing product names, nutritional information, ingredient lists, allergen information, etc. The data is received in JSON format and stored in an internal database.

[1918] Step 2:

[1919] The server uses deep learning algorithms to build a generative model based on product information stored in an internal database. The input includes product information from the database, and the output is a generative model for predicting products and meal plans that meet the user's criteria. Specifically, machine learning frameworks such as Keras and TensorFlow are used.

[1920] Step 3:

[1921] Users input their dietary restrictions and nutritional requirements using a device such as a smartphone. The input data includes allergy information, avoidance of specific food ingredients, and nutritional requirements based on health conditions. The device then transmits this data to a server.

[1922] Step 4:

[1923] The server receives the dietary restrictions and nutritional requirements sent by the user and performs filtering based on those requirements. The input includes the user's requirements data and product information in the database, and the output is a list of products and meal plans that match the requirements.

[1924] Step 5:

[1925] The device uses the user's camera and microphone to recognize emotions from the user's facial expressions and voice. Inputs include camera feed and audio input, and outputs provide data indicating the user's emotional state. An emotion engine analyzes information such as whether the user is feeling stressed.

[1926] Step 6:

[1927] The server adjusts the recommendations based on the user's perceived emotional state. The input includes the user's emotional data and the filtering results, and the output is a product list or meal plan that takes the user's emotional state into account. For example, if the user is feeling stressed, the server suggests foods and drinks that have a relaxing effect.

[1928] Step 7:

[1929] The server sends the generated products and meal plans to the device. The input includes the final product list and meal plan, and the output is the suggestions displayed on the user's device. The device displays the suggestions to the user, allowing the user to identify foods and meal plans that fit their dietary restrictions, nutritional requirements, and emotional state.

[1930] Step 8:

[1931] The user reviews the suggested products and meal plans and selects the products they want to purchase. The input includes product information selected from the suggestions, and the output is a list of products added to the cart. The user can then proceed with the purchase process based on this list.

[1932] 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.

[1933] 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.

[1934] 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.

[1935] 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.

[1936] 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.

[1937] 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.

[1938] 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).

[1939] 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.

[1940] 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."

[1941] 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.

[1942] 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).

[1943] 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.

[1944] 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.

[1945] 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.

[1946] 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.

[1947] 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.

[1948] 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.

[1949] 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.

[1950] 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.

[1951] 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.

[1952] 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.

[1953] The following is further disclosed regarding the above embodiment.

[1954] ---

[1955] (Claim 1)

[1956] A means for acquiring product information via a network;

[1957] means for storing the product information in a database;

[1958] means for constructing a generative model that learns based on the product information stored in the database;

[1959] a means for allowing a user to input dietary restrictions and nutritional requirements;

[1960] means for transmitting the dietary restrictions and nutritional conditions input by the user to a server;

[1961] A means for generating products and meal plans that conform to the dietary restrictions and nutritional requirements by utilizing the generative model in the server;

[1962] means for presenting the generated products and meal plans to the user;

[1963] A system including:

[1964] (Claim 2)

[1965] 10. The system of claim 1, wherein the product information includes nutritional value information, an ingredient list, and allergen information.

[1966] (Claim 3)

[1967] 10. The system of claim 1, wherein the generative model is constructed using a deep learning algorithm.

[1968] (Claim 4)

[1969] 2. The system according to claim 1, wherein the presenting means transmits a notification to a user terminal.

[1970] (Claim 5)

[1971] 2. The system according to claim 1, further comprising means for proposing a daily meal plan based on the user's input.

[1972] ---

[1973] This draft was written as a claim in the patent application, appropriately incorporating the characteristic parts of the invention.

[1974] "Example 1"

[1975] (Claim 1)

[1976] A means for acquiring product information via a network;

[1977] means for storing the product information in a database;

[1978] A means for constructing a generative AI model that learns based on the product information stored in the database;

[1979] a means for allowing a user to input dietary restrictions and nutritional requirements;

[1980] means for transmitting the dietary restrictions and nutritional conditions input by the user to a server;

[1981] A means for generating products and meal plans that conform to the dietary restrictions and nutritional requirements by utilizing the generative AI model on the server;

[1982] means for presenting the generated products and meal plans to the user;

[1983] means for adding user-selected items from the presented items and meal plans to a purchasing process;

[1984] A system including:

[1985] (Claim 2)

[1986] 10. The system of claim 1, wherein the product information includes nutritional value information, an ingredient list, and allergen information.

[1987] (Claim 3)

[1988] 10. The system of claim 1, wherein the generative AI model is constructed using a deep learning algorithm.

[1989] "Application Example 1"

[1990] (Claim 1)

[1991] A means for acquiring product information via a network;

[1992] means for storing the product information in a database;

[1993] means for constructing a generative model that learns based on the product information stored in the database;

[1994] a means for allowing a user to input dietary restrictions and nutritional requirements;

[1995] means for transmitting the dietary restrictions and nutritional conditions input by the user to a server;

[1996] A means for generating products and meal plans that conform to the dietary restrictions and nutritional requirements by utilizing the generative model in the server;

[1997] means for presenting the generated products and meal plans to the user;

[1998] A means for allowing a user to scan a barcode using a smartphone when selecting a product in a physical store, and for determining whether the scanned product meets the conditions by comparing the information on the scanned product with the conditions entered by the user, and presenting the results to the user;

[1999] A system including:

[2000] (Claim 2)

[2001] 10. The system of claim 1, wherein the product information includes nutritional value information, an ingredient list, and allergen information.

[2002] (Claim 3)

[2003] 10. The system of claim 1, wherein the generative model is constructed using a deep learning algorithm.

[2004] "Example 2: Combining Emotion Engines"

[2005] (Claim 1)

[2006] A means for acquiring product information via a network;

[2007] means for storing the product information in a database;

[2008] means for constructing a generative model that learns based on the product information stored in the database;

[2009] a means for allowing a user to input dietary restrictions and nutritional requirements;

[2010] means for transmitting the dietary restrictions and nutritional conditions input by the user to a server;

[2011] A means for generating products and meal plans that conform to the dietary restrictions and nutritional requirements by utilizing the generative model in the server;

[2012] A means for recognizing emotions by analyzing the user's facial expressions and voice;

[2013] means for adjusting the generated product or meal plan based on the recognized emotion;

[2014] means for presenting the tailored product or meal plan to the user;

[2015] A system including:

[2016] (Claim 2)

[2017] 10. The system of claim 1, wherein the product information includes nutritional value information, an ingredient list, and allergen information.

[2018] (Claim 3)

[2019] 10. The system of claim 1, wherein the generative model is constructed using a deep learning algorithm.

[2020] "Application example 2 when combining emotion engines"

[2021] (Claim 1)

[2022] A means for acquiring product information via a network;

[2023] means for storing the product information in a database;

[2024] means for constructing a generative model that learns based on the product information stored in the database;

[2025] a means for allowing a user to input dietary restrictions and nutritional requirements;

[2026] means for transmitting the dietary restrictions and nutritional conditions input by the user to a server;

[2027] A means for generating products and meal plans that conform to the dietary restrictions and nutritional requirements by utilizing the generative model in the server;

[2028] means for presenting the generated products and meal plans to the user;

[2029] means for recognizing a user's emotion using a camera and a microphone;

[2030] means for adjusting suggestions based on the recognized emotion;

[2031] A system including:

[2032] (Claim 2)

[2033] 10. The system of claim 1, wherein the product information includes nutritional value information, an ingredient list, and allergen information.

[2034] (Claim 3)

[2035] 10. The system of claim 1, wherein the generative model is constructed using a deep learning algorithm. [Explanation of symbols]

[2036] 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 acquiring product information via a network; means for storing the product information in a database; means for constructing a generative model that learns based on the product information stored in the database; a means for allowing a user to input dietary restrictions and nutritional requirements; means for transmitting the dietary restrictions and nutritional conditions input by the user to a server; A means for generating products and meal plans that conform to the dietary restrictions and nutritional requirements by utilizing the generative model in the server; means for presenting the generated products and meal plans to the user; A system including:

2. 10. The system of claim 1, wherein the product information includes nutritional value information, an ingredient list, and allergen information.

3. 10. The system of claim 1, wherein the generative model is constructed using a deep learning algorithm.

4. 2. The system according to claim 1, wherein the presenting means transmits a notification to a user terminal.

5. 2. The system according to claim 1, further comprising means for proposing a daily meal plan based on the user's input.

Images