System

Abstract

To provide a system capable of efficiently matching user preference information with product ingredient information.SOLUTION: A system includes: means for receiving and storing user preference data; means for collecting and analyzing product ingredient data; means for identifying the user's emotional state using an emotion engine; means for generating a prompt sentence that instructs the generation of a product suggestion list that matches the user's preference and emotional state based on the user's preference data, the product ingredient data, and the user's emotional state; means for generating a product suggestion list that matches the user's preferences using the generated prompt sentence and a generative AI model; means for presenting the generated suggestion list to the user; and means for enabling operations related to a purchase procedure when suggested products are on sale.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] There is a demand for a system that can efficiently suggest the best products for each user and make the process of purchasing smooth. In addition, a mechanism is also needed that allows privately owned shops and other stores with little influence to gain the chance to acquire new customers. [Means for solving the problem]

[0005] This invention utilizes AI for various evaluations such as product ingredient analysis, monitor evaluations, and product design, and matches the preferences of pre-registered users with the results of the evaluations. It provides a system that suggests products based on the matching results, and allows users to purchase the suggested products if they are on sale. This allows users to easily find the best products, and also gives stores the chance to acquire new customers. [Brief description of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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. 2 is a sequence diagram showing a process flow of the data processing system in the first embodiment of the first form example. [Figure 12] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the application example 1 of the first embodiment. [Figure 13] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the second embodiment of the second embodiment. [Figure 14] FIG. 13 is a sequence diagram showing a process flow of the data processing system in application example 2 of embodiment 2. [Figure 15]FIG. 13 is a sequence diagram showing a process flow of a data processing system in a third embodiment of the present invention. [Figure 16] FIG. 13 is a sequence diagram showing a process flow of the data processing system in the third application example of the third embodiment. [Figure 17] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0011] 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.

[0012] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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 wide area network (WAN) and / or a local area network (LAN).

[0018] 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.

[0019] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. 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.

[0020] 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 (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0022] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0023] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

[0024] 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.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] In one embodiment of the present invention, a user registers their preferences in the system. These preferences include various information related to food, such as favorite ingredients, allergy information, and preferred seasonings. The system then uses AI to evaluate and judge the product's ingredients, monitor evaluations, product design, and other aspects. This evaluation takes into account various information related to the product, such as the product's nutritional content, allergens, appearance, and taste. The system then matches the user's preferences with the results of the evaluation and judgement, and suggests the most suitable product for the user. If the suggested product is on sale, the user can purchase it on the spot.

[0029] "Example 2"

[0030] As a specific example, let's say a user registers preferences such as "I like fish," "I don't like spicy food," and "I have no allergies." The system uses AI to analyze the ingredients of products and evaluates products that "have fish as a main ingredient" and "don't contain spicy ingredients." The system then matches this information and suggests products to the user that "have fish as a main ingredient and don't contain spicy ingredients." If the suggested products are on sale, the user can purchase them on the spot.

[0031] The process flow of each embodiment will be described below.

[0032] "Example 1"

[0033] Step 1: The user registers their preferences in the system. These preferences include various information about food, such as favorite ingredients, allergy information, and preferred seasonings.

[0034] Step 2: The system uses AI to evaluate and judge the product's ingredients, monitor evaluation, product design, etc. This evaluation takes into account various information about the product, such as the product's nutritional content, allergens, appearance, taste, etc.

[0035] Step 3: The system matches the user's preferences with the evaluation results and suggests the most suitable products for the user.

[0036] Step 4: If the suggested product is available, the user can purchase it on the spot.

[0037] "Example 2"

[0038] Step 1: The user registers their preferences, such as "I like fish," "I don't like spicy food," or "I have no allergies."

[0039] Step 2: The system uses AI to analyze the product's ingredients and evaluates the product as "containing fish as the main ingredient" and "not containing spicy ingredients."

[0040] Step 3: The system matches this information and suggests products to the user that are "fish-based and do not contain spicy ingredients."

[0041] Step 4: If the suggested product is available, the user can purchase it on the spot.

[0042] Example 1

[0043] Next, a description will be given of Example 1 of the embodiment 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".

[0044] Conventional systems have difficulty in proposing optimal products based on users' preferences, and also do not adequately consider product ingredients and allergy information. As a result, it is difficult for users to find products that suit their preferences and health conditions.

[0045] 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.

[0046] In this invention, the server includes a means for a user to input his / her preference information, a means for collecting product ingredient data, a means for performing ingredient analysis and evaluation using AI based on the collected ingredient data, a means for matching the user's preference information with the product evaluation results, a means for suggesting products based on the matching results, and a means for allowing the user to purchase the suggested products if they are on sale. This makes it possible to suggest and purchase the most suitable products that match the user's preferences and health condition.

[0047] "User" refers to an individual who uses the system to input their own preference information and receive suggestions of the most suitable products.

[0048] "Preference information" refers to food-related information entered by the user, such as favorite ingredients, allergy information, and preferred seasonings.

[0049] "Ingredient data" refers to detailed information about a product, such as its nutritional content, allergens, appearance, and taste.

[0050] "AI" refers to artificial intelligence, and more specifically, technology that uses machine learning frameworks such as TENSORFLOW (registered trademark) and PyTorch to perform component analysis and evaluation.

[0051] "Ingredient analysis" refers to the process of evaluating nutritional components, allergens, etc. based on a product's ingredient data.

[0052] "Evaluation results" refers to the results of ingredient analysis conducted by AI, and include evaluations of the product's nutritional content, allergens, appearance, taste, etc.

[0053] "Matching" refers to the process of comparing user preference information with product evaluation results and selecting the most suitable product.

[0054] "Suggestion" refers to the act of notifying the user of the most suitable product based on the matching results.

[0055] "Purchase Means" refers to the mechanism by which a User purchases a proposed Product if the Product is on sale.

[0056] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0057] This invention is a system that uses AI to analyze and evaluate the ingredients of products based on user preference information and proposes optimal products. A specific embodiment of this system will be described below.

[0058] Input of user preferences

[0059] Users use a dedicated device or smartphone app to input their own preference information, which includes favorite ingredients, allergy information, preferred seasonings, etc. For example, a user might input "I like tomatoes," "I'm allergic to nuts," and "I like spicy food."

[0060] Collect product data

[0061] The server collects product data through a database or external API. The collected data includes the product's nutritional content, allergens, appearance, taste, etc. For example, the server obtains "ingredients information for product X."

[0062] Product composition analysis and evaluation

[0063] The server uses AI to analyze ingredients and evaluate products based on the collected product data. This AI is built using machine learning frameworks such as TensorFlow and PyTorch. For example, the server might evaluate "Product X contains tomatoes, does not contain nuts, and is spicy."

[0064] Matching user preferences

[0065] The server matches the user's preference information with the evaluation results of the product. For example, the server "compares the preference information of user A with the evaluation results of product X and calculates a matching score."

[0066] Optimal product proposals

[0067] The server proposes products with high matching scores to users. The proposals are made through a dedicated terminal or smartphone app. For example, the server proposes "Product X to User A."

[0068] Purchase of products

[0069] Users can purchase the suggested products through a dedicated device or smartphone app. For example, User A "purchases Product X using a smartphone app."

[0070] Examples

[0071] Example 1: Registering user preferences

[0072] User A registers in the system his favorite food ingredient "tomato," his allergy information "nut allergy," and his favorite seasoning "spicy food."

[0073] Example 2: Product composition analysis and evaluation

[0074] The server analyzes the ingredients of product X. Product X contains "tomatoes" and no nuts. It also has a spicy flavor. The server uses TensorFlow to evaluate this information and decides whether it matches the preferences of user A.

[0075] Example 3: Matching and Suggestions

[0076] The server matches the preference information of User A with the evaluation result of Product X and proposes Product X to User A. User A can purchase Product X through a smartphone app.

[0077] Examples of prompt statements

[0078] "Please explain the system that uses AI to analyze and evaluate the ingredients of products based on user preference information and recommend the most suitable products. Please also specify the names of specific hardware and software."

[0079] By feeding this prompt into a generative AI model, a detailed explanation of the system can be obtained.

[0080] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0081] Step 1:

[0082] Users input their own preference information using a dedicated device or smartphone app. The input preference information includes favorite ingredients, allergy information, and preferred seasonings. For example, a user might input "I like tomatoes," "I'm allergic to nuts," and "I like spicy food." The input data is sent to the server and saved in a database.

[0083] Step 2:

[0084] The server collects product data through a database or external API. The collected data includes the product's nutritional content, allergens, appearance, and taste. For example, the server obtains "ingredients information for product X." The obtained data is stored in a database.

[0085] Step 3:

[0086] The server uses AI to analyze ingredients and perform evaluation based on the collected product data. This AI is built using machine learning frameworks such as TensorFlow and PyTorch. For example, the server evaluates "Product X contains tomatoes and no nuts. It is seasoned with hot sauce." The input is the product data, and the output is the evaluation result.

[0087] Step 4:

[0088] The server matches the user's preference information with the product evaluation results. For example, the server "compares the preference information of user A with the evaluation results of product X and calculates a matching score." The input is the user's preference information and the product evaluation results, and the output is the matching score.

[0089] Step 5:

[0090] The server proposes products with high matching scores to users. Suggestions are made through dedicated terminals or smartphone apps. For example, the server "proposes product X to user A." The input is the matching score, and the output is information about the proposed product.

[0091] Step 6:

[0092] The user can purchase the suggested product through a dedicated terminal or smartphone app. For example, user A "purchases product X using a smartphone app." The input is the information about the suggested product, and the output is a notification of purchase completion.

[0093] (Application example 1)

[0094] Next, a description will be given of Application Example 1 of Form 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."

[0095] Conventional food delivery services have had the problem that it is difficult to suggest optimal dishes that take into account the user's preferences and allergy information. In addition, users have to check many menus to find a dish that suits them, which is time-consuming and labor-intensive.

[0096] The identification process by the identification processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means. In this invention, the server includes a means for utilizing AI for various evaluations and judgments such as component analysis of products, monitor evaluations, and product design, a means for matching the results of the evaluations and judgments with the user's preferences registered in advance, a means for suggesting products based on the matching results, a system including a mechanism for allowing the user to purchase the suggested products if they are on sale, a means for registering user preference information, analyzing the menu of a food delivery service, and suggesting the most suitable dish, and a means for ordering the suggested dish on the spot. This makes it possible to suggest the most suitable dish taking into account the user's preferences and allergy information, and allows the user to easily find and order the dish that suits him or her.

[0097] "Product ingredient analysis" refers to obtaining and analyzing information about a product's nutritional components, allergens, etc.

[0098] "Monitor evaluation" refers to the collection and analysis of product evaluations by users and experts.

[0099] "Product design" refers to evaluating the product's appearance and packaging design.

[0100] "Means of utilizing AI" refers to the use of artificial intelligence to analyze data and make evaluations and judgments.

[0101] "My preferences" refers to information such as favorite ingredients, disliked ingredients, allergy information, and preferred seasonings that are registered in advance by the user.

[0102] The "evaluation result" refers to the evaluation conducted by AI based on the product's ingredient analysis, monitor evaluation, product design, etc.

[0103] A "matching means" is a means of comparing the user's preferences with the results of the evaluation judgment and selecting the most suitable product.

[0104] The "means for suggesting products" refers to a means for presenting the most suitable products to the user based on the matching results.

[0105] A "mechanism for enabling purchase" is a mechanism that allows users to purchase a suggested product on the spot if the product is on sale.

[0106] "User preference information" refers to information registered by the user, such as favorite ingredients, disliked ingredients, allergy information, and preferred seasonings.

[0107] A "food delivery service menu" is a list of dishes offered by a food delivery service.

[0108] The "means for suggesting the most suitable dish" refers to a means for analyzing a user's preference information and the menu of a food delivery service, and selecting and suggesting the most suitable dish to the user.

[0109] An "instant ordering solution" is a solution that allows a user to instantly order a suggested dish.

[0110] The system for implementing this invention registers user preference information, analyzes the menu of food delivery services, and suggests the most suitable dishes. The system is realized using the following hardware and software.

[0111] Hardware

[0112] Smartphone: A device that allows users to register their preferences and view and order suggested dishes.

[0113] Server: A device for running AI models and analyzing data.

[0114] software

[0115] Python: A programming language used for data analysis and running AI models.

[0116] scikit-learn: A machine learning library for data vectorization and similarity calculations.

[0117] requests: An HTTP library for retrieving menu information from food delivery service APIs.

[0118] Processing flow

[0119] 1. Registration of user preferences

[0120] Users register their preferences (favorite ingredients, disliked ingredients, allergy information, preferred seasonings, etc.) through a smartphone application. This information is sent to the server and stored in a database.

[0121] 2. Get menu information

[0122] The server uses the requests library to retrieve the latest menu information from the food delivery service's API, including product descriptions and ingredient information.

[0123] 3. Component analysis and evaluation

[0124] The server uses scikit-learn to convert the menu descriptions into TF-IDF vectors, compare them with the user's preference information, and calculate the cosine similarity, thereby identifying the dish that best matches the user's preference.

[0125] 4. Food suggestions

[0126] The server then suggests the best dishes to the user based on the calculated similarity, and the suggested dishes are notified to the user via a smartphone application.

[0127] 5. Order Execution

[0128] Users can review the suggested dishes and place their order on the spot, and the order information is sent to a food delivery service, which then delivers the food to the user.

[0129] Examples

[0130] For example, if a user registered the following preferences:

[0131] User Preferences:

[0132] Favorite ingredients: Chicken, Tomato

[0133] Disliked food: Peanuts

[0134] Allergies: Nuts

[0135] Favorite seasoning: Spicy

[0136] If a food delivery service's menu includes the following:

[0137] Food delivery service menu:

[0138] 1. Chicken Curry: Spicy chicken curry in a tomato-based sauce.

[0139] 2. Peanut Sauce Salad: Salad made with peanut sauce.

[0140] 3. Tomato pasta: Pasta with tomato sauce.

[0141] The system will analyze the user's preferences and menu information and make the following suggestions:

[0142] Recommended dishes:

[0143] 1. Chicken Curry: Spicy chicken curry in a tomato-based sauce.

[0144] 2. Tomato pasta: Pasta with tomato sauce.

[0145] In this way, users can easily find and order dishes that suit their tastes.

[0146] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0147] Step 1:

[0148] The user inputs his / her preference information (favorite ingredients, disliked ingredients, allergy information, preferred seasoning, etc.) through a smartphone application. The input preference information is sent from the smartphone to the server and stored in a database. The input for this step is the user's preference information, and the output is the preference information stored on the server.

[0149] Step 2:

[0150] The server uses the requests library to get the latest menu information from the food delivery service's API. The menu information includes product descriptions and ingredient information. The input of this step is the API request, and the output is the menu information.

[0151] Step 3:

[0152] The server uses scikit-learn to vectorize the menu descriptions using TF-IDF. Specifically, each menu description is converted into a numerical vector based on the frequency of occurrence of words. The input for this step is the menu description, and the output is the vectorized menu information.

[0153] Step 4:

[0154] The server vectorizes the user's preference information and compares it with the menu information to calculate the cosine similarity. Specifically, the user's preference information is expressed as a vector, and the cosine similarity is calculated between the vector of each menu. The input of this step is the vectorized user's preference information and menu information, and the output is the similarity score with each menu.

[0155] Step 5:

[0156] The server selects the best dishes for the user based on the calculated similarity score, taking into account allergy information and excluding dishes that contain allergens. The inputs of this step are the similarity score and allergy information, and the output is a list of dishes to suggest to the user.

[0157] Step 6:

[0158] The server sends the list of suggested dishes to the smartphone application, through which the user can review the suggested dishes. The input of this step is the list of suggested dishes, and the output is the list of dishes displayed in the smartphone application.

[0159] Step 7:

[0160] The user can review the proposed dishes and place an order on the spot. The order information is sent from the smartphone to the server, which then forwards it to the food delivery service. The input of this step is the user's order information, and the output is the order information sent to the food delivery service.

[0161] In this way, users can easily find and order dishes that suit their tastes.

[0162] Example 2

[0163] Next, a second embodiment of the second embodiment will be described. 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."

[0164] In conventional systems, it was difficult to efficiently match user preference information with product ingredient information, and it was not possible to suggest the most suitable products to users. In addition, there was a lack of means to analyze product ingredient information in detail and find products that match the user's preferences. Furthermore, there was an insufficient mechanism to check whether the suggested products were on sale and to smoothly carry out the purchasing procedure.

[0165] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0166] In this invention, the server includes a means for a user to input preference information using a terminal, a means for transmitting the input preference information to the server and storing it in a database, a means for collecting product ingredient information and analyzing the ingredient information using a generative AI model, a means for matching the user's preference information with the product ingredient information, a means for suggesting products based on the matching results, and a means for allowing the user to purchase the suggested products if they are on sale. This makes it possible to efficiently find products that match the user's preferences and smoothly carry out the purchase procedure if the suggested products are on sale.

[0167] "User" means an individual or group that uses the system to input preference information and receive product suggestions.

[0168] A "terminal" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[0169] "Preference information" is personal data entered by the user, such as their preferences or allergy information.

[0170] A "server" is a computer system that receives preference information sent by a user, stores it in a database, and analyzes product ingredient information.

[0171] A "database" is a data management system in which a server stores preference information and product ingredient information.

[0172] "Product ingredient information" is detailed information about a product, such as its nutritional components and allergens.

[0173] A "generative AI model" is an artificial intelligence model used to analyze product ingredient information and match it with user preference information.

[0174] "Matching" is the process of comparing a user's preference information with product ingredient information to find products that meet the conditions.

[0175] "Suggestion" refers to the act of presenting products suitable for the user based on the matching results.

[0176] A "checkout" is a series of operations and processes that a user performs to purchase a suggested product.

[0177] The present invention is a system for suggesting optimal products based on user preference information and supporting the purchase procedure. A specific embodiment of this system will be described below.

[0178] First, the user inputs preference information using a terminal. The terminal is an electronic device such as a smartphone, tablet, or computer. The user starts a dedicated application and inputs preference information. For example, the user inputs information such as "I like fish," "I don't like spicy food," and "I have no allergies."

[0179] Next, the terminal transmits the input preference information to a server. The server stores the received preference information in a database. The database is a data management system for managing preference information and product ingredient information. For example, a database such as MySQL (registered trademark) can be used.

[0180] The server collects product ingredient information. The product ingredient information is detailed information such as the product's nutritional content and allergens. The server provides an API for scanning product barcodes. The user scans the product's barcode using the device's camera, and the device sends the scanned barcode information to the server. The server obtains the product's ingredient information based on the barcode information.

[0181] Next, the server uses a generative AI model to analyze the collected product ingredient information. The generative AI model uses, for example, "OpenAI's GPT-4 (registered trademark)". The server sends the following prompt sentence to the generative AI model:

[0182] Product ingredient information: Contains fish as the main ingredient and does not contain any spicy ingredients.

[0183] Rate this product and decide whether to recommend it to your users.

[0184] The generative AI model analyzes the ingredient information and returns the evaluation results to the server. The server matches the user's preference information with the product's ingredient information based on the evaluation results from the generative AI model. For example, it lists products that match conditions such as "I like fish" or "I don't like spicy food."

[0185] The server generates a list of matching products and sends it to the terminal, which displays the suggestions to the user, for example, displaying a message such as "We found a product that is fish-based and does not contain spicy ingredients."

[0186] The user uses the terminal to check the proposed products. If he / she wishes to purchase the product, he / she clicks the "Purchase" button on the terminal. The server provides an interface to support the purchase procedure and processes the payment. For example, it displays a form for entering credit card information.

[0187] In this way, products that match the user's preferences can be efficiently found, and if the suggested product is on sale, the user can smoothly complete the purchase procedure.

[0188] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0189] Step 1:

[0190] The user inputs preference information using the terminal.

[0191] Specific operations: The user launches a dedicated application and enters information such as "I like fish," "I don't like spicy food," and "I have no allergies" into a preference input form.

[0192] Input: User preference information

[0193] Output: Preference information entered into the device

[0194] Step 2:

[0195] The terminal transmits the input preference information to the server.

[0196] Specific operation: When the user clicks the "Send" button, the device sends the preference information to the server in JSON format.

[0197] Input: Preference information entered into the device

[0198] Output: Preference information sent to the server

[0199] Step 3:

[0200] The server stores the received preference information in a database.

[0201] Specific operation: The server parses the received JSON data and stores the preference information in a database, for example, a MySQL database.

[0202] Input: Preference information sent to the server

[0203] Output: Preference information stored in a database

[0204] Step 4:

[0205] The server collects information on ingredients of the product.

[0206] Specific operation: The user uses the device's camera to scan the barcode of the product, and the device sends the scanned barcode information to the server. The server obtains the product's ingredient information based on the barcode information.

[0207] Input: Barcode information of scanned item

[0208] Output: Product ingredient information collected on the server

[0209] Step 5:

[0210] The server uses a generative AI model to analyze the collected product ingredient information.

[0211] Specific operation: The server sends the following prompt to the generative AI model:

[0212] Product ingredient information: Contains fish as the main ingredient and does not contain any spicy ingredients.

[0213] Rate this product and decide whether to recommend it to your users.

[0214] The generative AI model analyzes the ingredient information and returns the evaluation results to the server.

[0215] Input: Product ingredient information, prompt text

[0216] Output: Evaluation results from the generative AI model

[0217] Step 6:

[0218] The server matches the user's preference information with product ingredient information based on the evaluation results from the generative AI model.

[0219] Specific operation: The server analyzes the evaluation results and lists products that meet conditions such as "I like fish" or "I don't like spicy food."

[0220] Input: Evaluation results from the generative AI model, user preference information

[0221] Output: A list of matching products

[0222] Step 7:

[0223] The server generates a list of matching products and transmits it to the terminal.

[0224] Specific operation: The server sends a list of matching products in JSON format to the terminal, and the terminal displays the suggestions to the user.

[0225] Input: A list of matching items

[0226] Output: The proposal displayed on the terminal

[0227] Step 8:

[0228] The user uses the terminal to check the suggested products and, if they wish to purchase them, completes the purchase procedure.

[0229] Specific operation: The user checks the details of the proposed product and clicks the "Purchase" button. The server provides an interface to support the purchase procedure and processes the payment. For example, it displays a form for entering credit card information.

[0230] Input: User's purchase request

[0231] Output: Purchase completed

[0232] (Application example 2)

[0233] Next, a description will be given of Application Example 2 of Form 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."

[0234] Conventional food delivery systems do not adequately consider user preferences and allergy information when making menu suggestions, making it difficult for users to find dishes that suit them. They also lack a mechanism for easily ordering and paying for suggested dishes on the spot. For this reason, more personalized menu suggestions and smooth ordering and payment are required to improve user satisfaction.

[0235] 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.

[0236] In this invention, the server includes a system including a means for utilizing AI for various evaluations and judgments such as product ingredient analysis, monitor evaluations, and product design, a means for matching the results of the evaluations and judgments with the user's pre-registered preferences, a means for suggesting products based on the matching results, a mechanism for allowing the user to purchase the suggested products if they are on sale, a means for suggesting suitable dishes from restaurant menus based on the user's preference information, and a means for ordering and paying for the suggested dishes on the spot. This enables personalized menu suggestions that take into account the user's preferences and allergy information, and smooth ordering and payment.

[0237] "Ingredient analysis" refers to analyzing information about a product's ingredients, nutrients, allergens, etc.

[0238] "Monitor evaluation" refers to the collection and analysis of feedback and evaluations from users and experts when they use a product.

[0239] "Product design" refers to the design of a product's appearance, packaging, ease of use, etc.

[0240] "Means of utilizing AI" refers to methods of using artificial intelligence technology to analyze data and make evaluations and judgments.

[0241] "Preferences" refers to personal preferences such as the ingredients, flavors, and types of food that a user prefers.

[0242] "Matching" refers to comparing the user's preference information with the product's ingredients and evaluation results to select the most suitable product.

[0243] "Means of suggestion" refers to a method of presenting products and menus that are suitable for the user based on the matching results.

[0244] A "purchase mechanism" is a system that allows users to order and pay for suggested products on the spot.

[0245] A "restaurant menu" refers to a list of food and beverages offered by a restaurant.

[0246] "Means of ordering and payment" refers to the methods by which a User orders the selected dish and completes payment.

[0247] The system for implementing this invention is capable of suggesting suitable dishes from restaurant menus based on the user's preference information, and allowing the suggested dishes to be ordered and paid for on the spot. A specific embodiment of this system is described below.

[0248] System Configuration

[0249] The system consists of the following main components:

[0250] 1. User terminal: A device such as a smartphone or tablet that the user uses to input preference information and confirm and order suggested dishes.

[0251] 2. Server: Using AI models, it performs ingredient analysis and taste matching to suggest dishes suitable for the user.

[0252] 3. Database: Stores restaurant menu information, user preference information, past purchase history, etc.

[0253] Program Processing

[0254] The server does the following:

[0255] 1. Ingredient analysis: Analyze restaurant menu information and extract ingredients, nutrients, allergens, etc. for each dish. This process uses Python and libraries such as scikit-learn.

[0256] 2. Preference matching: The system compares the user's pre-registered preference information (favorite ingredients, disliked ingredients, allergy information) with the results of ingredient analysis to select dishes suitable for the user. This process uses TF-IDF vectorization and cosine similarity calculation.

[0257] 3. Recommendations and Ordering: Based on the matching results, the system will recommend dishes suitable for the user and allow the user to order and pay on the spot. Ordering and payment will be processed in conjunction with a smartphone app.

[0258] Examples

[0259] For example, if a user registers their preferences such as "I like fish" or "I don't like spicy food," the server will suggest dishes such as "salmon sushi" or "tempura" from the restaurant menu. Users can check these suggestions through a smartphone app and order and pay for their favorite dishes on the spot.

[0260] Examples of prompt statements

[0261] Here is an example of a prompt to be input to the generative AI model:

[0262] Create a Python program that suggests suitable dishes from a restaurant menu based on the user's preference information. The user's preference information includes "favorite ingredients," "disliked ingredients," and "allergy information." Convert the menu ingredient information into a TF-IDF vector, calculate the cosine similarity, and suggest the menu that best matches the user's preference.

[0263] In this way, it is possible to create a system that can provide personalized menu suggestions that take into account the user's preferences and allergy information, as well as enable smooth ordering and payment.

[0264] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0265] Step 1:

[0266] The user terminal inputs the user's preference information (favorite ingredients, disliked ingredients, allergy information). The input preference information is sent to the server. The input data is saved in text format.

[0267] Step 2:

[0268] The server retrieves restaurant menu information from the database. The retrieved menu information includes the ingredients, nutrients, allergens, etc. of each dish. The menu information is stored in JSON format.

[0269] Step 3:

[0270] The server performs ingredient analysis on the acquired menu information. Specifically, it uses Python and scikit-learn to convert the ingredient information of each dish into a TF-IDF vector. The input data is the menu information, and the output data is a TF-IDF vector.

[0271] Step 4:

[0272] The server compares the user's preference information with the results of the component analysis. Specifically, it calculates the cosine similarity and selects the dish that best matches the user's preference. The input data is the user's preference information and the TF-IDF vector, and the output data is the similarity score.

[0273] Step 5:

[0274] The server suggests suitable dishes for the user based on the matching results. The suggested dishes are sent to the user terminal. The input data is the similarity score, and the output data is a list of suggested dishes.

[0275] Step 6:

[0276] The user terminal displays the suggested dishes and provides an interface for the user to order the dish of their choice. The user selects among the suggested dishes and confirms the order. The input data is the list of suggested dishes and the output data is the user's selection.

[0277] Step 7:

[0278] The server receives the user's order information and processes the payment. The payment process uses credit card information and electronic payment services. The input data is the user's order information, and the output data is confirmation of payment completion.

[0279] Step 8:

[0280] The server sends the order information and confirmation of payment completion to the restaurant. The restaurant receives the order and starts preparing the food. The input data is the order information and confirmation of payment completion, and the output data is a notification to the restaurant.

[0281] The above processing steps enable personalized menu suggestions that take into account the user's preferences and allergy information, as well as smooth ordering and payment.

[0282] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0283] "Example 1"

[0284] In one embodiment of the present invention, an emotion engine is incorporated that recognizes the user's emotions. This emotion engine recognizes emotions from the user's facial expressions, voice, text input, etc., and provides this information to the system. For example, if the user inputs the text "I'm very tired today," the emotion engine recognizes this as an emotional state of "fatigue." This information is used to suggest products. Specifically, if it is recognized that the user is tired, products that are highly nutritious and effective in recovering from fatigue are suggested.

[0285] "Example 2"

[0286] In another embodiment of the present invention, the emotion engine is also used to register user preferences. Specifically, when a user rates a product, their emotional state is also recorded. For example, when a user rates "This chocolate is delicious!", the emotion of joy felt at that time is also recorded. This information is used for future product suggestions, and products that are likely to evoke similar emotions of joy for the user are suggested.

[0287] The process flow of each embodiment will be described below.

[0288] "Example 1"

[0289] Step 1: A user enters text into the system, for example, "I'm very tired today."

[0290] Step 2: The emotion engine recognizes emotions from the text. In this example, it recognizes the emotional state "fatigue."

[0291] Step 3: The system recommends products based on the information from the emotion engine. In this example, products that are nutritious and effective for relieving fatigue are recommended.

[0292] "Example 2"

[0293] Step 1: The user rates the product, for example, "This chocolate is delicious!"

[0294] Step 2: The emotion engine recognizes the user's emotional state and records that information. In this example, it recognizes and records the emotional state "happy."

[0295] Step 3: The system suggests products based on the information from the emotion engine. In this example, the system suggests products that are likely to evoke similar emotions of joy for the user.

[0296] Example 1

[0297] Next, a description will be given of Example 1 of the embodiment 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".

[0298] Conventional systems have a problem in that it is difficult to suggest the best products for users because product suggestions do not sufficiently take into account the user's preference information and emotional state. In addition, because product suggestions are not based on the user's emotional state, it is not possible to provide products that are suitable for the user's current state.

[0299] The identification process by the identification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for a user to register his / her preference information, a means for utilizing artificial intelligence for evaluation and judgment of the ingredients, evaluation, design, etc. of a product, and a means for matching the user's preference information with the result of the evaluation and judgment. This makes it possible to propose an optimal product based on the user's preference information and the result of the product evaluation and judgment. In addition, the server includes an emotion engine that recognizes the user's emotions, and further includes a means for recognizing emotions from the user's facial expressions, voice, text input, etc., and utilizing the information in proposing products. This makes it possible to propose products that are nutritious and effective for a specific emotional state based on the user's emotional state.

[0300] "Preference information" is information that indicates a user's personal preferences and restrictions regarding food, such as preferred ingredients, allergy information, and preferred seasonings.

[0301] "Ingredient analysis" is the process of analyzing a product's characteristics, such as its nutritional content, allergens, appearance, and taste.

[0302] "Evaluation and judgment" is a process that uses artificial intelligence to comprehensively evaluate a product's ingredient analysis results, design, monitor evaluations, etc.

[0303] "Matching" is the process of comparing the user's preference information with the product evaluation results and selecting the most suitable product.

[0304] "Suggestion" refers to the act of presenting the most suitable product to the user based on the matching results.

[0305] An "emotion engine" is a system that recognizes emotions from a user's facial expressions, voice, text input, etc., and analyzes that information.

[0306] "Emotional state" is information that indicates the user's current emotions or mood.

[0307] "Nutritional value" is an indicator that shows the value of the nutritional components of a food or product.

[0308] "Purchase history" is a record of products a user has purchased in the past.

[0309] "Rating history" is a record of past product ratings and feedback provided by a user.

[0310] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0311] The present invention is a system for proposing optimal products in consideration of a user's preference information and emotional state. A specific embodiment of this system will be described below.

[0312] Registration of user preferences

[0313] Users input their own preference information using a dedicated terminal or web interface. This information includes favorite ingredients, allergies, and preferred seasonings. The terminal sends this information in JSON format to the server. The server analyzes the received JSON data and stores it in a database.

[0314] Product composition analysis and evaluation

[0315] The server collects product data and inputs it into the AI ​​model. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to analyze the nutritional content, allergens, appearance, taste, etc. of the product. The server evaluates the analysis results and stores them in a database.

[0316] Matching user preferences with evaluation results

[0317] The server retrieves user preference information and product evaluation results from the database. It uses SQL or NoSQL queries to match the user preference information with the product evaluation results. The server generates an optimal product list and stores it in the database.

[0318] Optimal product proposals

[0319] The server sends the best product list to the user's device, which then displays the product list to the user and provides a purchase button. When the user clicks the purchase button, the device starts the purchase process.

[0320] Emotion engine recognizes user emotions

[0321] The user uses the device to input text, voice, and recognize facial expressions. For example, if the user inputs the text "I'm very tired today," the device sends this text to the server. The server uses an emotion engine to analyze the emotion "fatigue" from the text. The server stores the analysis results in a database.

[0322] Emotion-based product recommendations

[0323] Based on the analysis results of the emotion engine, the server recognizes that the user is fatigued. The server compares the user's preference information and selects products that are nutritious and effective in relieving fatigue. The server sends the selected products to the user's device. The device displays the products to the user and assists in the purchase process.

[0324] Examples

[0325] User A registers the following preferences in the system:

[0326] Favorite foods: Chicken, broccoli

[0327] Allergy Information: Nut allergies

[0328] Favorite seasoning: sweet and spicy

[0329] If User A enters the text "I'm very tired today," the emotion engine recognizes this as "fatigue." Based on User A's preference information and emotion information, the system suggests a sweet and spicy dish using chicken and broccoli, which is nutritious and effective in relieving fatigue.

[0330] Examples of prompt statements

[0331] "Design a system that suggests optimal products based on a user's preference and emotional information. Preference information includes favorite ingredients, allergies, and preferred seasonings, and emotional information is recognized from the user's facial expressions, voice, and text input. Please also include examples of specific product suggestions."

[0332] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0333] Step 1: Registering user preferences

[0334] 1. The user enters their preferences using a dedicated terminal or web interface.

[0335] 2. The device sends the entered preference information to the server in JSON format.

[0336] 3. The server parses the received JSON data and stores it in the database.

[0337] Input: User's preference information (favorite ingredients, allergy information, preferred seasoning)

[0338] Data processing: Parsing JSON data

[0339] Output: Preference information stored in a database

[0340] Step 2: Product composition analysis and evaluation

[0341] 1. The server collects product data and inputs it into the AI ​​model.

[0342] 2. The server uses machine learning frameworks such as TensorFlow and PyTorch to analyze the product's nutritional content, allergens, appearance, taste, etc.

[0343] 3. The server evaluates the analysis results and stores them in a database.

[0344] Input: Product data (nutritional information, allergens, appearance, taste)

[0345] Data calculation: Ingredient analysis and evaluation judgment using AI model

[0346] Output: Evaluation results stored in a database

[0347] Step 3: Matching user preferences with evaluation results

[0348] 1. The server obtains the user's preference information and product evaluation results from the database.

[0349] 2. The server uses SQL or NoSQL queries to match the user's preferences with the product ratings.

[0350] 3. The server generates the optimal product list and stores it in the database.

[0351] Input: User preference information, product evaluation results

[0352] Data Calculation: Matching by SQL or NoSQL queries

[0353] Output: A list of the best products stored in a database

[0354] Step 4: Recommend the best product

[0355] 1. The server sends the optimal product list to the user's device.

[0356] 2. The device displays a list of products to the user and provides a purchase button.

[0357] 3. When the user clicks the purchase button, the device begins the purchase process.

[0358] Input: Optimal product list

[0359] Data processing: Displaying product list, starting purchase procedure

[0360] Output: List of products shown to user, start of checkout process

[0361] Step 5: Recognizing user emotions with the emotion engine

[0362] 1. The user uses the device to input text, voice, and recognize facial expressions.

[0363] 2. The device transmits the input emotion information to the server.

[0364] 3. The server uses the emotion engine to analyze the user's emotions.

[0365] 4. The server stores the analysis results in a database.

[0366] Input: User emotion information (text input, voice input, facial expression recognition)

[0367] Data Computation: Sentiment Analysis with Emotion Engine

[0368] Output: Sentiment analysis results stored in a database

[0369] Step 6: Emotion-based product recommendations

[0370] 1. The server recognizes that the user is tired based on the analysis results of the emotion engine.

[0371] 2. The server compares the user's preference information and selects products that are highly nutritious and effective in recovering from fatigue.

[0372] 3. The server sends the selected product to the user's device.

[0373] 4. The terminal displays the products to the user and assists in the purchase process.

[0374] Input: Sentiment analysis results, user preference information

[0375] Data calculation: Matching preference information with emotion analysis results and selecting optimal products

[0376] Output: The best products displayed to the user, and assistance with the purchase process

[0377] (Application example 1)

[0378] Next, a description will be given of Application Example 1 of Form 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."

[0379] Conventional food delivery systems generally suggest products that take into account the user's preferences and allergy information, but do not suggest products that take into account the user's emotional state. As a result, there is a problem that the system cannot suggest optimal products when the user is tired or in a specific emotional state, and it is not possible to sufficiently increase user satisfaction.

[0380] 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.

[0381] In this invention, the server includes a means for utilizing AI for various evaluations and judgments such as product ingredient analysis, monitor evaluations, and product design, a means for matching the results of the evaluations and judgments with the user's preregistered preferences, a means for suggesting products based on the matching results, a system including a mechanism for allowing the user to purchase the suggested products if they are on sale, and a means for suggesting products based on the user's emotional state using an emotion engine that recognizes the user's emotions. This makes it possible to suggest optimal products that take into account not only the user's preferences and allergy information, but also their emotional state.

[0382] "Ingredient analysis" refers to analyzing information such as a product's nutritional components and allergens.

[0383] "Monitor evaluation" refers to the collection and analysis of product evaluations by users and testers.

[0384] "Product design" refers to evaluating the product's appearance and packaging design.

[0385] "Means of utilizing AI" refers to the use of artificial intelligence technology to analyze data and make evaluations and judgments.

[0386] "Preferences" refers to information about personal preferences, such as the user's favorite ingredients, seasonings, and allergy information.

[0387] A "matching means" is a means for comparing a user's preferences with the product evaluation results and selecting the most suitable product.

[0388] The "means of suggestion" refers to a means of presenting the most suitable product to the user based on the matching results.

[0389] An "emotion engine" is a technology that recognizes emotions from a user's facial expressions, voice, text input, etc.

[0390] "Emotional state" refers to a user's current mood or psychological state.

[0391] A "mechanism for enabling purchases" is a system that allows users to complete the purchase procedure on the spot if the suggested product is on sale.

[0392] The following system configuration is used as an embodiment of the present invention: The system proposes optimal food delivery items based on the user's preference information and emotional state.

[0393] System Configuration

[0394] Hardware

[0395] Smartphone: A device that allows users to input preference information and emotional state.

[0396] Server: A central processing unit for analyzing data and making product suggestions.

[0397] software

[0398] EmotionEngine: An emotion recognition library for recognizing user emotions.

[0399] FoodRecommendationEngine: A recommendation engine to suggest optimal products based on user preference information and emotional state.

[0400] Data processing and calculation

[0401] Registration of user preferences

[0402] Users use their smartphones to input their preferences (favorite ingredients, allergies, and preferred seasonings). This information is stored in JSON format on the server.

[0403] Emotion recognition

[0404] When a user inputs text, voice, or facial expressions into their smartphone, EmotionEngine analyzes them and recognizes the user's emotional state. For example, if a user inputs "I'm very tired today," EmotionEngine will recognize this as "fatigue."

[0405] Food delivery product proposals

[0406] The server uses the FoodRecommendationEngine to suggest optimal food delivery items based on the user's preference information and the user's recognized emotional state. For example, if the user is tired, nutritious items that are effective in recovering from fatigue (such as vitamin-rich salads and protein shakes) are suggested.

[0407] Examples

[0408] Registration of user preferences

[0409] The user opens the smartphone app and enters the following:

[0410] Favorite ingredients: Chicken, rice

[0411] Disliked food: Fish

[0412] Allergies: Nuts

[0413] Favorite seasoning: Spicy

[0414] Emotion recognition

[0415] A user types the text "I'm very tired today" into their smartphone. EmotionEngine recognizes this as "fatigue."

[0416] Food delivery product proposals

[0417] The server generates the following prompt sentence based on the user's preference information and emotional state:

[0418] "We will suggest food delivery options for you. Please wait a moment."

[0419] The FoodRecommendationEngine suggests products that are nutritious and effective in relieving fatigue, such as "vitamin-rich salads" and "protein shakes."

[0420] In this way, a system can be realized that suggests optimal food delivery items based on the user's preferences and emotional state.

[0421] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0422] Step 1:

[0423] Users use their smartphones to input their own preference information. Specifically, they input their favorite ingredients, disliked ingredients, allergy information, preferred seasonings, etc. The input data is sent to the server in JSON format and saved. The input data is saved on the server as the user's preference information.

[0424] Step 2:

[0425] A user uses a smartphone device to input their current emotional state. For example, they input the text "I'm very tired today." This input data is sent to the server and analyzed by EmotionEngine. EmotionEngine analyzes the input text data and recognizes the user's emotional state as "fatigue." The output data is saved on the server as the user's emotional state.

[0426] Step 3:

[0427] The server uses the FoodRecommendationEngine to suggest optimal food delivery items based on the stored user preference information and emotional state. Specifically, the server passes the preference information (favorite ingredients, disliked ingredients, allergy information, preferred seasoning) and emotional state (fatigue) as input data to the FoodRecommendationEngine. The FoodRecommendationEngine analyzes this data and outputs optimal items (for example, vitamin-rich salads or protein shakes).

[0428] Step 4:

[0429] The server proposes the optimal products output from the FoodRecommendationEngine to the user. Specifically, it sends a notification to the smartphone terminal and displays the products proposed to the user. The user can check the proposed products and choose whether or not to purchase them. The output data is the product information proposed to the user.

[0430] Step 5:

[0431] When the user wishes to purchase a suggested product, the user completes the purchase procedure using a smartphone terminal. The server accepts the purchase procedure and sends the order to the food delivery service. Specifically, the server sends the user's purchase information (product name, quantity, delivery address, etc.) to the food delivery service and confirms the order. The output data is the confirmed order information.

[0432] In this way, a system can be realized that suggests optimal food delivery items based on the user's preferences and emotional state and then carries out the purchase process.

[0433] Example 2

[0434] Next, a second embodiment of the second embodiment will be described. 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."

[0435] Conventional systems did not adequately suggest products based on the user's preferences, making it difficult to increase user satisfaction. In addition, product suggestions did not take into account the user's emotional state, making it difficult to stimulate the user's desire to purchase. Furthermore, it was difficult to properly analyze information on product ingredients and allergens and provide it to users.

[0436] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0437] In this invention, the server includes a means for receiving and storing user preference data, a means for collecting and analyzing product ingredient data, a means for comparing the user preference data with the product ingredient data and evaluating the product, a means for suggesting products based on the evaluation result, a means for making the suggested product available for purchase if it is on sale, a means for recording the user's evaluation data and emotion data, and a means for utilizing the recorded data for the next suggestion. This enables highly accurate product suggestions based on the user's preferences, and increases user satisfaction. Furthermore, product suggestions that take into account the user's emotional state can stimulate the user's purchasing desire. Furthermore, it becomes possible to appropriately analyze product ingredient information and allergen information and provide them to the user.

[0438] "User Preference Data" means information regarding a User's personal preferences, such as the foods the User prefers, ingredients the User wishes to avoid, and allergy information.

[0439] "Ingredient data" refers to specific ingredient information about a product, such as its nutritional components, allergens, and main ingredients.

[0440] "Evaluation" is the process of comparing the user's preference data with product ingredient data to select the product that is most suitable for the user.

[0441] "Product suggestion" refers to the act of presenting products suitable for a user based on the results of the evaluation judgment.

[0442] "Emotional Data" is information that records the emotional state a user felt when rating a product.

[0443] "Means for making a product available for purchase" refers to a mechanism that allows a user to purchase a product on the spot if the suggested product is on sale.

[0444] "Means of utilizing recorded data for next proposals" refers to a system that reflects the user's past evaluation data and emotional data in the next product proposal.

[0445] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0446] The present invention is a system for analyzing the ingredients of products based on user preference data and proposing suitable products. A specific embodiment of this system will be described below.

[0447] Server Roles

[0448] The server receives and stores the user's preference data. The preference data entered by the user through the terminal (e.g. "I like fish," "I don't like spicy food," "I have no allergies") is sent to the server and stored in a database. MySQL, PostgreSQL, or similar databases are used as the database.

[0449] Next, the server collects and analyzes the product's ingredient data. The ingredient data includes the product's nutritional content and allergens. The collected data is analyzed using AI models such as TensorFlow and PyTorch. As a result of the analysis, characteristics such as "mainly contains fish" and "does not contain spicy ingredients" are extracted.

[0450] The server compares the user's preference data with the product's ingredient data and makes an evaluation decision. It uses an SQL query to compare the data and selects products that match the user's preferences. Based on the evaluation results, it generates a list of products to suggest to the user and sends it to the terminal.

[0451] In addition, the server records the user's evaluation data and emotion data. When a user evaluates a product, the server receives the emotion data (e.g., "This chocolate is delicious!", an emotion of joy) along with the evaluation and records it in the database. The recorded data will be used for the next proposal.

[0452] Terminal Roles

[0453] The terminal provides an interface for the user to input preference data. A front-end framework such as React or Vue.js is used to display a form for the user to input the preference data. The input data is sent to the server using an HTTP request (e.g., POST request).

[0454] The terminal displays the product suggestion list sent from the server to the user. The product suggestion list is displayed in HTML format, and the user can check the suggested products.

[0455] The terminal also provides an interface for users to rate products. When users input emotion data along with their ratings, the data is sent to the server.

[0456] User Roles

[0457] The user inputs preference data through the terminal interface. For example, "I like fish," "I don't like spicy food," "I have no allergies," etc. The input data is sent to the server.

[0458] The user checks the product suggestion list displayed on the terminal, and if the suggested product is on sale, the user can purchase it on the spot.

[0459] The user rates the proposed products and inputs emotion data along with the rating, for example, "This salmon sashimi is delicious!" The input data is sent to the server.

[0460] Examples of concrete examples and prompts

[0461] As a specific example, if a user registers preferences such as "I like fish," "I don't like spicy food," and "I have no allergies," the server uses an AI model to analyze the ingredients of the product and evaluates and judges products that "are mainly made of fish" and "do not contain spicy ingredients." For example, the server might suggest "salmon sashimi" or "fried white fish." If the user evaluates the product as "This salmon sashimi is delicious!", the server also records the emotion of joy. The next time, a product that is likely to evoke a similar emotion of joy for the user (for example, "tuna sashimi") will be suggested.

[0462] An example of a prompt sentence is as follows:

[0463] "Based on the user's preference data (e.g., likes fish, dislikes spicy food, no allergies), please use an AI model to analyze the ingredients of the product and suggest products that suit the user. Also, please record the user's evaluation and their emotional state at the time, and use them for the next suggestion."

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

[0465] Program processing flow

[0466] Step 1: Enter and submit your preferences

[0467] Subject: User

[0468] The user inputs preference data through the terminal interface, such as "I like fish," "I don't like spicy food," and "I have no allergies." The input data is then sent to the server via an HTTP POST request.

[0469] Input: User preference data

[0470] Output: Preference data sent to the server

[0471] Step 2: Receiving and storing preference data

[0472] Subject: Server

[0473] The server receives the preference data sent by the user. The received data is stored in a database (e.g., MySQL or PostgreSQL). The stored data is used for later processing.

[0474] Input: Preference data submitted by the user

[0475] Output: Preference data stored in a database

[0476] Step 3: Collect and analyze product ingredient data

[0477] Subject: Server

[0478] The server collects product ingredient data. The collected data is input into an AI model (e.g., TensorFlow or PyTorch) and ingredient analysis is performed. As a result of the analysis, characteristics such as "mainly contains fish" and "does not contain spicy ingredients" are extracted.

[0479] Input: Product ingredient data

[0480] Output: Analyzed component data (feature extraction results)

[0481] Step 4: Matching preference data with ingredient data and evaluating

[0482] Subject: Server

[0483] The server compares the user's preference data stored in the database with the analyzed product ingredient data, and uses SQL queries to compare the data and evaluate and determine products that match the user's preferences.

[0484] Input: User preference data, analyzed ingredient data

[0485] Output: Evaluation result (list of products suitable for the user)

[0486] Step 5: Generate and submit product proposals

[0487] Subject: Server

[0488] The server generates a list of products to be proposed to the user based on the evaluation results, and sends the generated list of products to the terminal via an HTTP response.

[0489] Input: Evaluation result

[0490] Output: Product suggestions list sent to the terminal

[0491] Step 6: View product suggestions

[0492] Subject: Terminal

[0493] The terminal displays the product suggestion list sent from the server to the user. The product suggestion list is displayed in HTML format, and the user can check the suggested products.

[0494] Input: Product suggestions list sent from the server

[0495] Output: A list of product suggestions displayed to the user

[0496] Step 7: Enter and submit product ratings and sentiment data

[0497] Subject: User

[0498] The user rates the proposed products and inputs emotional data along with the rating, for example, "This salmon sashimi is delicious!" The input data is sent to the server via an HTTP POST request.

[0499] Input: User rating and sentiment data

[0500] Output: Rating and sentiment data sent to the server

[0501] Step 8: Receive and record rating and emotion data

[0502] Subject: Server

[0503] The server receives the evaluation data and emotion data sent by the user. The received data is recorded in a database. The recorded data is used for the next proposal.

[0504] Input: User-submitted rating and sentiment data

[0505] Output: Evaluation data and emotion data recorded in a database

[0506] Step 9: Use data to improve your next proposal

[0507] Subject: Server

[0508] The server analyzes the recorded evaluation data and emotion data and uses it to suggest products for the next time. For example, if a user evaluates "This salmon sashimi is delicious!", the server will suggest products that are likely to evoke a similar emotion of joy, such as "tuna sashimi."

[0509] Input: Recorded rating and emotion data

[0510] Output: Data used for the next proposal

[0511] (Application example 2)

[0512] Next, a description will be given of Application Example 2 of Form 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."

[0513] Conventional product recommendation systems can take into account the user's preferences and allergy information, but they do not consider the user's emotional state when making product recommendations. This makes it difficult to make product recommendations that recreate the joy and satisfaction that the user felt in the past. In addition, food delivery services lack the ability to suggest optimal dishes and foods based on the user's preferences and emotional state. This makes it difficult to increase user satisfaction.

[0514] 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.

[0515] In this invention, the server includes a means for utilizing AI for various evaluations and judgments such as product ingredient analysis, monitor evaluations, and product design, a means for matching the results of the evaluations and judgments with the user's preregistered preferences, a means for suggesting products based on the matching results, a means including a mechanism for allowing the user to purchase the suggested products if they are on sale, a means for recording the user's emotional state and suggesting products based on the emotional state, and a means for suggesting optimal dishes and foods based on the user's preferences and emotional state. This makes it possible to suggest optimal products and dishes based on the user's preferences and emotional state, thereby increasing user satisfaction.

[0516] "Ingredient analysis" is the process of analyzing the ingredients of a product and identifying their contents.

[0517] "Evaluation and judgment" is the process of using AI to evaluate the quality and characteristics of a product and judging the results.

[0518] "Preferences" refer to specific ingredients or characteristics that a user prefers.

[0519] "Matching" is the process of comparing a user's preferences with the results of their evaluation judgment and identifying matching products.

[0520] "Product suggestion" is the process of presenting the most suitable products to the user based on the matching results.

[0521] "Emotional state" refers to feelings such as pleasure, satisfaction, or discomfort that users experience when evaluating a product.

[0522] "Cuisine" refers to food made by cooking ingredients.

[0523] "Food" refers to ingredients or dishes offered for consumption by a consumer.

[0524] "Food delivery" is a service that delivers dishes or food ordered by users to a specified location.

[0525] The system for implementing the present invention proposes optimal products and dishes based on the preferences and emotional state of a user. A specific embodiment of this system will be described below.

[0526] System Configuration

[0527] The system mainly consists of a server, a user terminal, and a database. The server performs product ingredient analysis, evaluation judgment, preference matching, product suggestions, and recording and analysis of emotional states. User terminals include smartphones, smart glasses, head-mounted displays, etc., and provide an interface for users to input preferences and emotional states. The database stores product ingredient information, user preference data, and emotional state data.

[0528] Program Processing

[0529] The server performs the following process.

[0530] 1. Ingredient analysis: The server analyzes the ingredient information of the product and identifies its contents. Specifically, to obtain information on the product's nutritional content, allergens, etc., the server retrieves the necessary data from the database and analyzes it using an AI model.

[0531] 2. Evaluation judgment: The server uses AI to evaluate the quality and characteristics of the product and judges the result. The evaluation judgment also takes into account the user's past purchase history and evaluation history.

[0532] 3. Taste matching: The server compares the taste data registered by the user in advance with the results of the evaluation judgment and identifies matching products. This allows the server to select products that match the user's tastes.

[0533] 4. Product Suggestion: The server recommends the best products to the user based on the matching results. If the suggested products are on sale, the user can purchase them on the spot.

[0534] 5. Recording and analyzing emotional states: The server records the emotional states felt by the user when rating products and analyzes the data, which makes it possible to suggest products based on the user's emotional state.

[0535] Hardware and Software Used

[0536] Hardware: Servers, smartphones, smart glasses, head-mounted displays

[0537] Software: AI models (e.g. TensorFlow, PyTorch), database management systems (e.g. MySQL, PostgreSQL)

[0538] Examples

[0539] For example, if a user registers preferences such as "I like fish," "I don't like spicy food," and "I have no allergies," and in the past recorded the emotion of "happiness" when rating "salmon sushi," the system will suggest "salmon sushi" and also display the user's emotional state at the time.

[0540] Examples of prompt statements

[0541] Please register user preference data. Example: {"likes": ["fish"], "dislikes": ["spicy food"], "allergies": []}

[0542] Enter your product data. Example: [{"name": "Salmon Sushi", "ingredients": "Fish, Rice, Seaweed", "spicy": False}, {"name": "Spicy Ramen", "ingredients": "Noodles, Chili Pepper, Pork", "spicy": True}]

[0543] Enter user emotion data. Example: {"Salmon sushi": "Happy", "Spicy ramen": "Unhappy"}

[0544] In this way, a system can be realized that suggests optimal products and dishes based on the user's preferences and emotional state.

[0545] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0546] Step 1:

[0547] A user inputs preference data using a terminal.

[0548] Input: User preference data (e.g. "I like fish," "I don't like spicy food," "I have no allergies")

[0549] Output: The preference data is sent to the server and stored in a database.

[0550] Specific operation: The user inputs preference data through the terminal interface and presses the send button. The terminal sends this data to the server, which then stores it in the database.

[0551] Step 2:

[0552] The server retrieves the product's ingredient data from the database and performs ingredient analysis.

[0553] Input: Product ingredient data (e.g. "Salmon sushi: fish, rice, seaweed" "Spicy ramen: noodles, chili pepper, pork")

[0554] Output: Component analysis results (e.g. "Salmon sushi: contains fish as the main component" "Spicy ramen: contains spicy components")

[0555] Specific operation: The server retrieves the product's ingredient data from the database and performs ingredient analysis using the AI ​​model. The analysis results are temporarily stored in memory.

[0556] Step 3:

[0557] The server matches the preference data with the results of component analysis.

[0558] Input: preference data, component analysis results

[0559] Output: Matching results (e.g. "Salmon sushi is good" "Spicy ramen is not good")

[0560] Specific operation: The server compares the preference data with the results of the component analysis and identifies products that match the user's preferences. The matching results are temporarily stored in memory.

[0561] Step 4:

[0562] The server suggests products based on the matching results.

[0563] Input: Matching results

[0564] Output: Suggested items (e.g. "Salmon Sushi")

[0565] Specific operation: Based on the matching results, the server selects the most suitable products for the user and generates a list of suggested products. This list is sent to the terminal.

[0566] Step 5:

[0567] The user uses the terminal to rate the proposed products and input his / her emotional state.

[0568] Input: User's rating and emotional state (e.g. "Salmon sushi: Delicious! Delighted")

[0569] Output: The rating data and emotional state data are sent to the server and stored in a database.

[0570] Specific operation: The user evaluates the proposed products through the terminal interface and inputs his / her emotional state at that time. The terminal transmits this data to the server, which stores it in a database.

[0571] Step 6:

[0572] The server analyzes the emotional state data and uses it for the next suggestion.

[0573] Input: Rating data and emotional state data

[0574] Output: Analysis results (e.g. "Salmon sushi brings joy to the user")

[0575] How it works: The server analyzes the evaluation data and emotional state data, and uses an AI model to learn patterns to use in the next recommendation. The analysis results are stored in a database.

[0576] In this way, a system is realized that suggests optimal products and dishes based on the user's preferences and emotional state.

[0577] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0578] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0579] Another example of generative AI is Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0580] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0581] [Second embodiment]

[0582] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0583] 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.

[0584] 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.

[0585] 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 wide area network (WAN) and / or a local area network (LAN).

[0586] 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.

[0587] 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 the voice according to instructions from the processor 46.

[0588] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0589] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0590] Fig. 4 shows an example of 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.

[0591] 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.

[0592] 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.

[0593] 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.

[0594] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0595] "Example 1"

[0596] In one embodiment of the present invention, a user registers their preferences in the system. These preferences include various information related to food, such as favorite ingredients, allergy information, and preferred seasonings. The system then uses AI to evaluate and judge the product's ingredients, monitor evaluations, product design, and other factors. This evaluation takes into account various information related to the product, such as the product's nutritional content, allergens, appearance, and taste. The system then matches the user's preferences with the results of the evaluation and judgement, and suggests the most suitable product for the user. If the suggested product is on sale, the user can purchase it on the spot.

[0597] "Example 2"

[0598] As a specific example, let's say a user registers preferences such as "I like fish," "I don't like spicy food," and "I have no allergies." The system uses AI to analyze the ingredients of products and evaluates products that "have fish as a main ingredient" and "don't contain spicy ingredients." The system then matches this information and suggests products to the user that "have fish as a main ingredient and don't contain spicy ingredients." If the suggested products are on sale, the user can purchase them on the spot.

[0599] The process flow of each embodiment will be described below.

[0600] "Example 1"

[0601] Step 1: The user registers their preferences in the system. These preferences include various information about food, such as favorite ingredients, allergy information, and preferred seasonings.

[0602] Step 2: The system uses AI to evaluate and judge the product's ingredients, monitor evaluation, product design, etc. This evaluation takes into account various information about the product, such as the product's nutritional content, allergens, appearance, taste, etc.

[0603] Step 3: The system matches the user's preferences with the evaluation results and suggests the most suitable products for the user.

[0604] Step 4: If the suggested product is available, the user can purchase it on the spot.

[0605] "Example 2"

[0606] Step 1: The user registers their preferences, such as "I like fish," "I don't like spicy food," or "I have no allergies."

[0607] Step 2: The system uses AI to analyze the product's ingredients and evaluates the product as "containing fish as the main ingredient" and "not containing spicy ingredients."

[0608] Step 3: The system matches this information and suggests products to the user that are "fish-based and do not contain spicy ingredients."

[0609] Step 4: If the suggested product is available, the user can purchase it on the spot.

[0610] Example 1

[0611] Next, a description will be given of Example 1 of Form 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".

[0612] Conventional systems have difficulty in proposing optimal products based on users' preferences, and also do not adequately consider product ingredients and allergy information. As a result, it is difficult for users to find products that suit their preferences and health conditions.

[0613] 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.

[0614] In this invention, the server includes a means for a user to input his / her preference information, a means for collecting product ingredient data, a means for performing ingredient analysis and evaluation using AI based on the collected ingredient data, a means for matching the user's preference information with the product evaluation results, a means for suggesting products based on the matching results, and a means for allowing the user to purchase the suggested products if they are on sale. This makes it possible to suggest and purchase the most suitable products that match the user's preferences and health condition.

[0615] "User" refers to an individual who uses the system to input their own preference information and receive suggestions of the most suitable products.

[0616] "Preference information" refers to food-related information entered by the user, such as favorite ingredients, allergy information, and preferred seasonings.

[0617] "Ingredient data" refers to detailed information about a product, such as its nutritional content, allergens, appearance, and taste.

[0618] "AI" refers to artificial intelligence, specifically the technology of component analysis and evaluation using machine learning frameworks such as TensorFlow and PyTorch.

[0619] "Ingredient analysis" refers to the process of evaluating nutritional components, allergens, etc. based on a product's ingredient data.

[0620] "Evaluation results" refers to the results of ingredient analysis conducted by AI, and include evaluations of the product's nutritional content, allergens, appearance, taste, etc.

[0621] "Matching" refers to the process of comparing user preference information with product evaluation results and selecting the most suitable product.

[0622] "Suggestion" refers to the act of notifying the user of the most suitable product based on the matching results.

[0623] "Purchase Means" refers to the mechanism by which a User purchases a proposed Product if the Product is on sale.

[0624] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0625] This invention is a system that uses AI to analyze and evaluate the ingredients of products based on user preference information and proposes optimal products. A specific embodiment of this system will be described below.

[0626] Input of user preferences

[0627] Users input their own preference information using a dedicated device or smartphone app. Preference information includes favorite ingredients, allergy information, preferred seasonings, etc. For example, a user might input "I like tomatoes," "I'm allergic to nuts," and "I like spicy food."

[0628] Collect product data

[0629] The server collects product data through a database or external API. The collected data includes the product's nutritional content, allergens, appearance, taste, etc. For example, the server obtains "ingredients information for product X."

[0630] Product composition analysis and evaluation

[0631] The server uses AI to analyze ingredients and evaluate products based on the collected product data. This AI is built using machine learning frameworks such as TensorFlow and PyTorch. For example, the server might evaluate "Product X contains tomatoes, does not contain nuts, and is spicy."

[0632] Matching user preferences

[0633] The server matches the user's preference information with the evaluation results of the product. For example, the server "compares the preference information of user A with the evaluation results of product X and calculates a matching score."

[0634] Optimal product proposals

[0635] The server proposes products with high matching scores to users. The proposals are made through a dedicated terminal or smartphone app. For example, the server proposes "Product X to User A."

[0636] Purchase of products

[0637] Users can purchase the suggested products through a dedicated device or smartphone app. For example, User A "purchases Product X using a smartphone app."

[0638] Examples

[0639] Example 1: Registering user preferences

[0640] User A registers in the system his favorite food ingredient "tomato," his allergy information "nut allergy," and his favorite seasoning "spicy food."

[0641] Example 2: Product composition analysis and evaluation

[0642] The server analyzes the ingredients of product X. Product X contains "tomatoes" and no nuts. It also has a spicy flavor. The server uses TensorFlow to evaluate this information and decides whether it matches the preferences of user A.

[0643] Example 3: Matching and Suggestions

[0644] The server matches the preference information of User A with the evaluation result of Product X and proposes Product X to User A. User A can purchase Product X through a smartphone app.

[0645] Examples of prompt statements

[0646] "Please explain the system that uses AI to analyze and evaluate the ingredients of products based on user preference information and recommend the most suitable products. Please also specify the names of specific hardware and software."

[0647] By feeding this prompt into a generative AI model, a detailed explanation of the system can be obtained.

[0648] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0649] Step 1:

[0650] Users input their own preference information using a dedicated device or smartphone app. The input preference information includes favorite ingredients, allergy information, and preferred seasonings. For example, a user might input "I like tomatoes," "I'm allergic to nuts," and "I like spicy food." The input data is sent to the server and saved in a database.

[0651] Step 2:

[0652] The server collects product data through a database or external API. The collected data includes the product's nutritional content, allergens, appearance, and taste. For example, the server obtains "ingredients information for product X." The obtained data is stored in a database.

[0653] Step 3:

[0654] The server uses AI to analyze ingredients and perform evaluation based on the collected product data. This AI is built using machine learning frameworks such as TensorFlow and PyTorch. For example, the server evaluates "Product X contains tomatoes and no nuts. It is seasoned with hot sauce." The input is the product data, and the output is the evaluation result.

[0655] Step 4:

[0656] The server matches the user's preference information with the product evaluation results. For example, the server "compares the preference information of user A with the evaluation results of product X and calculates a matching score." The input is the user's preference information and the product evaluation results, and the output is the matching score.

[0657] Step 5:

[0658] The server proposes products with high matching scores to users. Suggestions are made through dedicated terminals or smartphone apps. For example, the server "proposes product X to user A." The input is the matching score, and the output is information about the proposed product.

[0659] Step 6:

[0660] The user can purchase the suggested product through a dedicated terminal or smartphone app. For example, user A "purchases product X using a smartphone app." The input is the information about the suggested product, and the output is a notification of purchase completion.

[0661] (Application example 1)

[0662] Next, a description will be given of Application Example 1 of Form 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".

[0663] Conventional food delivery services have had the problem that it is difficult to suggest optimal dishes that take into account the user's preferences and allergy information. In addition, users have to check many menus to find a dish that suits them, which is time-consuming and labor-intensive.

[0664] The identification process by the identification processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means. In this invention, the server includes a means for utilizing AI for various evaluations and judgments such as component analysis of products, monitor evaluations, and product design, a means for matching the results of the evaluations and judgments with the user's preferences registered in advance, a means for suggesting products based on the matching results, a system including a mechanism for allowing the user to purchase the suggested products if they are on sale, a means for registering user preference information, analyzing the menu of a food delivery service, and suggesting the most suitable dish, and a means for ordering the suggested dish on the spot. This makes it possible to suggest the most suitable dish taking into account the user's preferences and allergy information, and allows the user to easily find and order the dish that suits him or her.

[0665] "Product ingredient analysis" refers to obtaining and analyzing information about a product's nutritional components, allergens, etc.

[0666] "Monitor evaluation" refers to the collection and analysis of product evaluations by users and experts.

[0667] "Product design" refers to evaluating the product's appearance and packaging design.

[0668] "Means of utilizing AI" refers to the use of artificial intelligence to analyze data and make evaluations and judgments.

[0669] "My preferences" refers to information such as favorite ingredients, disliked ingredients, allergy information, and preferred seasonings that are registered in advance by the user.

[0670] The "evaluation result" refers to the evaluation conducted by AI based on the product's ingredient analysis, monitor evaluation, product design, etc.

[0671] A "matching means" is a means of comparing the user's preferences with the results of the evaluation judgment and selecting the most suitable product.

[0672] The "means for suggesting products" refers to a means for presenting the most suitable products to the user based on the matching results.

[0673] A "mechanism for enabling purchase" is a mechanism that allows users to purchase a suggested product on the spot if the product is on sale.

[0674] "User preference information" refers to information registered by the user, such as favorite ingredients, disliked ingredients, allergy information, and preferred seasonings.

[0675] A "food delivery service menu" is a list of dishes offered by a food delivery service.

[0676] The "means for suggesting the most suitable dish" refers to a means for analyzing a user's preference information and the menu of a food delivery service, and selecting and suggesting the most suitable dish to the user.

[0677] An "instant ordering solution" is a solution that allows a user to instantly order a suggested dish.

[0678] The system for implementing this invention registers user preference information, analyzes the menu of food delivery services, and suggests the most suitable dishes. The system is realized using the following hardware and software.

[0679] Hardware

[0680] Smartphone: A device that allows users to register their preferences and view and order suggested dishes.

[0681] Server: A device for running AI models and analyzing data.

[0682] software

[0683] Python: A programming language used for data analysis and running AI models.

[0684] scikit-learn: A machine learning library for data vectorization and similarity calculations.

[0685] requests: An HTTP library for retrieving menu information from food delivery service APIs.

[0686] Processing flow

[0687] 1. Registration of user preferences

[0688] Users register their preferences (favorite ingredients, disliked ingredients, allergy information, preferred seasonings, etc.) through a smartphone application. This information is sent to the server and stored in a database.

[0689] 2. Get menu information

[0690] The server uses the requests library to retrieve the latest menu information from the food delivery service's API, including product descriptions and ingredient information.

[0691] 3. Component analysis and evaluation

[0692] The server uses scikit-learn to convert the menu descriptions into TF-IDF vectors, compare them with the user's preference information, and calculate the cosine similarity, thereby identifying the dish that best matches the user's preference.

[0693] 4. Food suggestions

[0694] The server then suggests the best dishes to the user based on the calculated similarity, and the suggested dishes are notified to the user via a smartphone application.

[0695] 5. Order Execution

[0696] Users can review the suggested dishes and place their order on the spot, and the order information is sent to a food delivery service, which then delivers the food to the user.

[0697] Examples

[0698] For example, if a user registered the following preferences:

[0699] User Preferences:

[0700] Favorite ingredients: Chicken, Tomato

[0701] Disliked food: Peanuts

[0702] Allergies: Nuts

[0703] Favorite seasoning: Spicy

[0704] If a food delivery service's menu includes the following:

[0705] Food delivery service menu:

[0706] 1. Chicken Curry: Spicy chicken curry in a tomato-based sauce.

[0707] 2. Peanut Sauce Salad: Salad made with peanut sauce.

[0708] 3. Tomato pasta: Pasta with tomato sauce.

[0709] The system will analyze the user's preferences and menu information and make the following suggestions:

[0710] Recommended dishes:

[0711] 1. Chicken Curry: Spicy chicken curry in a tomato-based sauce.

[0712] 2. Tomato pasta: Pasta with tomato sauce.

[0713] In this way, users can easily find and order dishes that suit their tastes.

[0714] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0715] Step 1:

[0716] The user inputs his / her preference information (favorite ingredients, disliked ingredients, allergy information, preferred seasoning, etc.) through a smartphone application. The input preference information is sent from the smartphone to the server and stored in a database. The input for this step is the user's preference information, and the output is the preference information stored on the server.

[0717] Step 2:

[0718] The server uses the requests library to get the latest menu information from the food delivery service's API. The menu information includes product descriptions and ingredient information. The input of this step is the API request, and the output is the menu information.

[0719] Step 3:

[0720] The server uses scikit-learn to vectorize the menu descriptions using TF-IDF. Specifically, each menu description is converted into a numerical vector based on the frequency of occurrence of words. The input for this step is the menu description, and the output is the vectorized menu information.

[0721] Step 4:

[0722] The server vectorizes the user's preference information and compares it with the menu information to calculate the cosine similarity. Specifically, the user's preference information is expressed as a vector, and the cosine similarity is calculated between the vector of each menu. The input of this step is the vectorized user's preference information and menu information, and the output is the similarity score with each menu.

[0723] Step 5:

[0724] The server selects the best dishes for the user based on the calculated similarity score, taking into account allergy information and excluding dishes that contain allergens. The inputs of this step are the similarity score and allergy information, and the output is a list of dishes to suggest to the user.

[0725] Step 6:

[0726] The server sends the list of suggested dishes to the smartphone application, through which the user can review the suggested dishes. The input of this step is the list of suggested dishes, and the output is the list of dishes displayed in the smartphone application.

[0727] Step 7:

[0728] The user can review the proposed dishes and place an order on the spot. The order information is sent from the smartphone to the server, which then forwards it to the food delivery service. The input of this step is the user's order information, and the output is the order information sent to the food delivery service.

[0729] In this way, users can easily find and order dishes that suit their tastes.

[0730] Example 2

[0731] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0732] In conventional systems, it was difficult to efficiently match user preference information with product ingredient information, and it was not possible to suggest the most suitable products to users. In addition, there was a lack of means to analyze product ingredient information in detail and find products that match the user's preferences. Furthermore, there was an insufficient mechanism to check whether the suggested products were on sale and to smoothly carry out the purchasing procedure.

[0733] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0734] In this invention, the server includes a means for a user to input preference information using a terminal, a means for transmitting the input preference information to the server and storing it in a database, a means for collecting product ingredient information and analyzing the ingredient information using a generative AI model, a means for matching the user's preference information with the product ingredient information, a means for suggesting products based on the matching results, and a means for allowing the user to purchase the suggested products if they are on sale. This makes it possible to efficiently find products that match the user's preferences and smoothly carry out the purchase procedure if the suggested products are on sale.

[0735] "User" means an individual or group that uses the system to input preference information and receive product suggestions.

[0736] A "terminal" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[0737] "Preference information" is personal data entered by the user, such as their preferences or allergy information.

[0738] A "server" is a computer system that receives preference information sent by a user, stores it in a database, and analyzes product ingredient information.

[0739] A "database" is a data management system in which a server stores preference information and product ingredient information.

[0740] "Product ingredient information" is detailed information about a product, such as its nutritional components and allergens.

[0741] A "generative AI model" is an artificial intelligence model used to analyze product ingredient information and match it with user preference information.

[0742] "Matching" is the process of comparing a user's preference information with product ingredient information to find products that meet the conditions.

[0743] "Suggestion" refers to the act of presenting products suitable for the user based on the matching results.

[0744] A "checkout" is a series of operations and processes that a user performs to purchase a suggested product.

[0745] The present invention is a system for suggesting optimal products based on user preference information and supporting the purchase procedure. A specific embodiment of this system will be described below.

[0746] First, the user inputs preference information using a terminal. The terminal is an electronic device such as a smartphone, tablet, or computer. The user starts a dedicated application and inputs preference information. For example, the user inputs information such as "I like fish," "I don't like spicy food," and "I have no allergies."

[0747] Next, the terminal transmits the input preference information to a server. The server stores the received preference information in a database. The database is a data management system for managing the preference information and the ingredient information of the product. For example, a database such as MySQL can be used.

[0748] The server collects product ingredient information. The product ingredient information is detailed information such as the product's nutritional content and allergens. The server provides an API for scanning product barcodes. The user scans the product's barcode using the device's camera, and the device sends the scanned barcode information to the server. The server obtains the product's ingredient information based on the barcode information.

[0749] Next, the server uses a generative AI model to analyze the collected product ingredient information. The generative AI model uses, for example, OpenAI's GPT-4. The server sends the following prompt to the generative AI model:

[0750] Product ingredient information: Contains fish as the main ingredient and does not contain any spicy ingredients.

[0751] Rate this product and decide whether to recommend it to your users.

[0752] The generative AI model analyzes the ingredient information and returns the evaluation results to the server. The server matches the user's preference information with the product's ingredient information based on the evaluation results from the generative AI model. For example, it lists products that match conditions such as "I like fish" or "I don't like spicy food."

[0753] The server generates a list of matching products and sends it to the terminal, which displays the suggestions to the user, for example, displaying a message such as "We found a product that is fish-based and does not contain spicy ingredients."

[0754] The user uses the terminal to check the proposed products. If he / she wishes to purchase the product, he / she clicks the "Purchase" button on the terminal. The server provides an interface to support the purchase procedure and processes the payment. For example, it displays a form for entering credit card information.

[0755] In this way, products that match the user's preferences can be efficiently found, and if the suggested product is on sale, the user can smoothly complete the purchase procedure.

[0756] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0757] Step 1:

[0758] The user inputs preference information using the terminal.

[0759] Specific operations: The user launches a dedicated application and enters information such as "I like fish," "I don't like spicy food," and "I have no allergies" into a preference input form.

[0760] Input: User preference information

[0761] Output: Preference information entered into the device

[0762] Step 2:

[0763] The terminal transmits the input preference information to the server.

[0764] Specific operation: When the user clicks the "Send" button, the device sends the preference information to the server in JSON format.

[0765] Input: Preference information entered into the device

[0766] Output: Preference information sent to the server

[0767] Step 3:

[0768] The server stores the received preference information in a database.

[0769] Specific operation: The server parses the received JSON data and stores the preference information in a database, for example, a MySQL database.

[0770] Input: Preference information sent to the server

[0771] Output: Preference information stored in a database

[0772] Step 4:

[0773] The server collects information on ingredients of the product.

[0774] Specific operation: The user uses the device's camera to scan the barcode of the product, and the device sends the scanned barcode information to the server. The server obtains the product's ingredient information based on the barcode information.

[0775] Input: Barcode information of scanned item

[0776] Output: Product ingredient information collected on the server

[0777] Step 5:

[0778] The server uses a generative AI model to analyze the collected product ingredient information.

[0779] Specific operation: The server sends the following prompt to the generative AI model:

[0780] Product information: Fish-based, no spicy ingredients

[0781] Rate this product and decide whether to recommend it to your users.

[0782] The generative AI model analyzes the ingredient information and returns the evaluation results to the server.

[0783] Input: Product ingredient information, prompt text

[0784] Output: Evaluation results from the generative AI model

[0785] Step 6:

[0786] The server matches the user's preference information with product ingredient information based on the evaluation results from the generative AI model.

[0787] Specific operation: The server analyzes the evaluation results and lists products that meet conditions such as "I like fish" or "I don't like spicy food."

[0788] Input: Evaluation results from the generative AI model, user preference information

[0789] Output: A list of matching products

[0790] Step 7:

[0791] The server generates a list of matching products and transmits it to the terminal.

[0792] Specific operation: The server sends a list of matching products in JSON format to the terminal, and the terminal displays the suggestions to the user.

[0793] Input: A list of matching items

[0794] Output: The suggestions displayed on the terminal

[0795] Step 8:

[0796] The user uses the terminal to check the suggested products and, if they wish to purchase them, completes the purchase procedure.

[0797] Specific operation: The user checks the details of the proposed product and clicks the "Purchase" button. The server provides an interface to support the purchase procedure and processes the payment. For example, it displays a form for entering credit card information.

[0798] Input: User's purchase request

[0799] Output: Purchase completed

[0800] (Application example 2)

[0801] Next, a description will be given of Application Example 2 of Form 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".

[0802] Conventional food delivery systems do not adequately consider user preferences and allergy information when making menu suggestions, making it difficult for users to find dishes that suit them. They also lack a mechanism for easily ordering and paying for suggested dishes on the spot. For this reason, more personalized menu suggestions and smooth ordering and payment are required to improve user satisfaction.

[0803] 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.

[0804] In this invention, the server includes a system including a means for utilizing AI for various evaluations and judgments such as product ingredient analysis, monitor evaluations, and product design, a means for matching the results of the evaluations and judgments with the user's pre-registered preferences, a means for suggesting products based on the matching results, a mechanism for allowing the user to purchase the suggested products if they are on sale, a means for suggesting suitable dishes from restaurant menus based on the user's preference information, and a means for ordering and paying for the suggested dishes on the spot. This enables personalized menu suggestions that take into account the user's preferences and allergy information, and smooth ordering and payment.

[0805] "Ingredient analysis" refers to analyzing information about a product's ingredients, nutrients, allergens, etc.

[0806] "Monitor evaluation" refers to the collection and analysis of feedback and evaluations from users and experts when they use a product.

[0807] "Product design" refers to the design of a product's appearance, packaging, ease of use, etc.

[0808] "Means of utilizing AI" refers to methods of using artificial intelligence technology to analyze data and make evaluations and judgments.

[0809] "Preferences" refers to personal preferences such as the ingredients, flavors, and types of food that a user prefers.

[0810] "Matching" refers to comparing the user's preference information with the product's ingredients and evaluation results to select the most suitable product.

[0811] "Means of suggestion" refers to a method of presenting products and menus that are suitable for the user based on the matching results.

[0812] A "purchase mechanism" is a system that allows users to order and pay for suggested products on the spot.

[0813] A "restaurant menu" refers to a list of food and beverages offered by a restaurant.

[0814] "Means of ordering and payment" refers to the methods by which a User orders the selected dish and completes payment.

[0815] The system for implementing this invention is capable of suggesting suitable dishes from restaurant menus based on the user's preference information, and allowing the suggested dishes to be ordered and paid for on the spot. A specific embodiment of this system is described below.

[0816] System Configuration

[0817] The system consists of the following main components:

[0818] 1. User terminal: A device such as a smartphone or tablet that the user uses to input preference information and confirm and order suggested dishes.

[0819] 2. Server: Using AI models, it performs ingredient analysis and taste matching to suggest dishes suitable for the user.

[0820] 3. Database: Stores restaurant menu information, user preference information, past purchase history, etc.

[0821] Program Processing

[0822] The server does the following:

[0823] 1. Ingredient analysis: Analyze restaurant menu information and extract ingredients, nutrients, allergens, etc. for each dish. This process uses Python and libraries such as scikit-learn.

[0824] 2. Preference matching: The system compares the user's pre-registered preference information (favorite ingredients, disliked ingredients, allergy information) with the results of ingredient analysis to select dishes suitable for the user. This process uses TF-IDF vectorization and cosine similarity calculation.

[0825] 3. Recommendations and Ordering: Based on the matching results, the system will suggest dishes suitable for the user and allow the user to order and pay on the spot. Ordering and payment will be processed in conjunction with a smartphone app.

[0826] Examples

[0827] For example, if a user registers their preferences such as "I like fish" or "I don't like spicy food," the server will suggest dishes such as "salmon sushi" or "tempura" from the restaurant menu. Users can check these suggestions through a smartphone app and order and pay for their favorite dishes on the spot.

[0828] Examples of prompt statements

[0829] Here is an example of a prompt to be input to the generative AI model:

[0830] Create a Python program that suggests suitable dishes from a restaurant menu based on the user's preference information. The user's preference information includes "favorite ingredients," "disliked ingredients," and "allergy information." Convert the menu ingredient information into a TF-IDF vector, calculate the cosine similarity, and suggest the menu that best matches the user's preference.

[0831] In this way, it is possible to create a system that can provide personalized menu suggestions that take into account the user's preferences and allergy information, as well as enable smooth ordering and payment.

[0832] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0833] Step 1:

[0834] The user terminal inputs the user's preference information (favorite ingredients, disliked ingredients, allergy information). The input preference information is sent to the server. The input data is saved in text format.

[0835] Step 2:

[0836] The server retrieves restaurant menu information from the database. The retrieved menu information includes the ingredients, nutrients, allergens, etc. of each dish. The menu information is stored in JSON format.

[0837] Step 3:

[0838] The server performs ingredient analysis on the acquired menu information. Specifically, it uses Python and scikit-learn to convert the ingredient information of each dish into a TF-IDF vector. The input data is the menu information, and the output data is a TF-IDF vector.

[0839] Step 4:

[0840] The server compares the user's preference information with the results of the component analysis. Specifically, it calculates the cosine similarity and selects the dish that best matches the user's preference. The input data is the user's preference information and the TF-IDF vector, and the output data is the similarity score.

[0841] Step 5:

[0842] The server suggests suitable dishes for the user based on the matching results. The suggested dishes are sent to the user terminal. The input data is the similarity score, and the output data is a list of suggested dishes.

[0843] Step 6:

[0844] The user terminal displays the suggested dishes and provides an interface for the user to order the dish of their choice. The user selects among the suggested dishes and confirms the order. The input data is the list of suggested dishes and the output data is the user's selection.

[0845] Step 7:

[0846] The server receives the user's order information and processes the payment. The payment process uses credit card information and electronic payment services. The input data is the user's order information, and the output data is confirmation of payment completion.

[0847] Step 8:

[0848] The server sends the order information and confirmation of payment completion to the restaurant. The restaurant receives the order and starts preparing the food. The input data is the order information and confirmation of payment completion, and the output data is a notification to the restaurant.

[0849] The above processing steps enable personalized menu suggestions that take into account the user's preferences and allergy information, as well as smooth ordering and payment.

[0850] In addition, an emotion engine that estimates the emotion of the user may be further combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0851] "Example 1"

[0852] In one embodiment of the present invention, an emotion engine is incorporated that recognizes the user's emotions. This emotion engine recognizes emotions from the user's facial expressions, voice, text input, etc., and provides this information to the system. For example, if the user inputs the text "I'm very tired today," the emotion engine recognizes this as an emotional state of "fatigue." This information is used to suggest products. Specifically, if it is recognized that the user is tired, products that are highly nutritious and effective in recovering from fatigue are suggested.

[0853] "Example 2"

[0854] In another embodiment of the present invention, the emotion engine is also used to register user preferences. Specifically, when a user rates a product, their emotional state is also recorded. For example, when a user rates "This chocolate is delicious!", the emotion of joy felt at that time is also recorded. This information is used for future product suggestions, and products that are likely to evoke similar emotions of joy for the user are suggested.

[0855] The process flow of each embodiment will be described below.

[0856] "Example 1"

[0857] Step 1: A user enters text into the system, for example, "I'm very tired today."

[0858] Step 2: The emotion engine recognizes emotions from the text. In this example, it recognizes the emotional state "fatigue."

[0859] Step 3: The system recommends products based on the information from the emotion engine. In this example, products that are nutritious and effective for relieving fatigue are recommended.

[0860] "Example 2"

[0861] Step 1: The user rates the product, for example, "This chocolate is delicious!"

[0862] Step 2: The emotion engine recognizes the user's emotional state and records that information. In this example, it recognizes and records the emotional state "happy."

[0863] Step 3: The system suggests products based on the information from the emotion engine. In this example, the system suggests products that are likely to evoke similar emotions of joy for the user.

[0864] Example 1

[0865] Next, a description will be given of Example 1 of Form 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".

[0866] Conventional systems have a problem in that it is difficult to suggest the best products for users because product suggestions do not sufficiently take into account the user's preference information and emotional state. In addition, because product suggestions are not based on the user's emotional state, it is not possible to provide products that are suitable for the user's current state.

[0867] The identification process by the identification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for a user to register his / her preference information, a means for utilizing artificial intelligence for evaluation and judgment of the ingredients, evaluation, design, etc. of a product, and a means for matching the user's preference information with the result of the evaluation and judgment. This makes it possible to propose an optimal product based on the user's preference information and the result of the product evaluation and judgment. In addition, the server includes an emotion engine that recognizes the user's emotions, and further includes a means for recognizing emotions from the user's facial expressions, voice, text input, etc., and utilizing the information in proposing products. This makes it possible to propose products that are nutritious and effective for a specific emotional state based on the user's emotional state.

[0868] "Preference information" is information that indicates a user's personal preferences and restrictions regarding food, such as preferred ingredients, allergy information, and preferred seasonings.

[0869] "Ingredient analysis" is the process of analyzing a product's characteristics, such as its nutritional content, allergens, appearance, and taste.

[0870] "Evaluation and judgment" is a process that uses artificial intelligence to comprehensively evaluate a product's ingredient analysis results, design, monitor evaluations, etc.

[0871] "Matching" is the process of comparing the user's preference information with the product evaluation results and selecting the most suitable product.

[0872] "Suggestion" refers to the act of presenting the most suitable product to the user based on the matching results.

[0873] An "emotion engine" is a system that recognizes emotions from a user's facial expressions, voice, text input, etc., and analyzes that information.

[0874] "Emotional state" is information that indicates the user's current emotions or mood.

[0875] "Nutritional value" is an indicator that shows the value of the nutritional components of a food or product.

[0876] "Purchase history" is a record of products a user has purchased in the past.

[0877] "Rating history" is a record of past product ratings and feedback provided by a user.

[0878] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0879] The present invention is a system for proposing optimal products in consideration of a user's preference information and emotional state. A specific embodiment of this system will be described below.

[0880] Registration of user preferences

[0881] Users input their own preference information using a dedicated terminal or web interface. This information includes favorite ingredients, allergies, and preferred seasonings. The terminal sends this information in JSON format to the server. The server analyzes the received JSON data and stores it in a database.

[0882] Product composition analysis and evaluation

[0883] The server collects product data and inputs it into the AI ​​model. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to analyze the nutritional content, allergens, appearance, taste, etc. of the product. The server evaluates the analysis results and stores them in a database.

[0884] Matching user preferences with evaluation results

[0885] The server retrieves user preference information and product evaluation results from the database. It uses SQL or NoSQL queries to match the user preference information with the product evaluation results. The server generates an optimal product list and stores it in the database.

[0886] Optimal product proposals

[0887] The server sends the best product list to the user's device, which then displays the product list to the user and provides a purchase button. When the user clicks the purchase button, the device starts the purchase process.

[0888] Emotion engine recognizes user emotions

[0889] The user uses the device to input text, voice, and recognize facial expressions. For example, if the user inputs the text "I'm very tired today," the device sends this text to the server. The server uses an emotion engine to analyze the emotion "fatigue" from the text. The server stores the analysis results in a database.

[0890] Emotion-based product recommendations

[0891] Based on the analysis results of the emotion engine, the server recognizes that the user is fatigued. The server compares the user's preference information and selects products that are nutritious and effective in relieving fatigue. The server sends the selected products to the user's device. The device displays the products to the user and assists in the purchase process.

[0892] Examples

[0893] User A registers the following preferences in the system:

[0894] Favorite foods: Chicken, broccoli

[0895] Allergy Information: Nut allergies

[0896] Favorite seasoning: sweet and spicy

[0897] If User A enters the text "I'm very tired today," the emotion engine recognizes this as "fatigue." Based on User A's preference information and emotion information, the system suggests a sweet and spicy dish using chicken and broccoli, which is nutritious and effective in relieving fatigue.

[0898] Examples of prompt statements

[0899] "Design a system that suggests optimal products based on a user's preference and emotional information. Preference information includes favorite ingredients, allergies, and preferred seasonings, and emotional information is recognized from the user's facial expressions, voice, and text input. Please also include examples of specific product suggestions."

[0900] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0901] Step 1: Registering user preferences

[0902] 1. The user enters their preferences using a dedicated terminal or web interface.

[0903] 2. The device sends the entered preference information to the server in JSON format.

[0904] 3. The server parses the received JSON data and stores it in the database.

[0905] Input: User's preference information (favorite ingredients, allergy information, preferred seasoning)

[0906] Data processing: Parsing JSON data

[0907] Output: Preference information stored in a database

[0908] Step 2: Product composition analysis and evaluation

[0909] 1. The server collects product data and inputs it into the AI ​​model.

[0910] 2. The server uses machine learning frameworks such as TensorFlow and PyTorch to analyze the product's nutritional content, allergens, appearance, taste, etc.

[0911] 3. The server evaluates the analysis results and stores them in a database.

[0912] Input: Product data (nutritional information, allergens, appearance, taste)

[0913] Data calculation: Ingredient analysis and evaluation judgment using AI model

[0914] Output: Evaluation results stored in a database

[0915] Step 3: Matching user preferences with evaluation results

[0916] 1. The server obtains the user's preference information and product evaluation results from the database.

[0917] 2. The server uses SQL or NoSQL queries to match the user's preferences with the product ratings.

[0918] 3. The server generates the optimal product list and stores it in the database.

[0919] Input: User preference information, product evaluation results

[0920] Data Calculation: Matching by SQL or NoSQL queries

[0921] Output: A list of the best products stored in a database

[0922] Step 4: Recommend the best product

[0923] 1. The server sends the optimal product list to the user's device.

[0924] 2. The device displays a list of products to the user and provides a purchase button.

[0925] 3. When the user clicks the purchase button, the device begins the purchase process.

[0926] Input: Optimal product list

[0927] Data processing: Displaying product list, starting purchase procedure

[0928] Output: List of products shown to user, start of checkout process

[0929] Step 5: Recognizing user emotions with the emotion engine

[0930] 1. The user uses the device to input text, voice, and recognize facial expressions.

[0931] 2. The device transmits the input emotion information to the server.

[0932] 3. The server uses the emotion engine to analyze the user's emotions.

[0933] 4. The server stores the analysis results in a database.

[0934] Input: User emotion information (text input, voice input, facial expression recognition)

[0935] Data Computation: Sentiment Analysis with Emotion Engine

[0936] Output: Sentiment analysis results stored in a database

[0937] Step 6: Emotion-based product recommendations

[0938] 1. The server recognizes that the user is tired based on the analysis results of the emotion engine.

[0939] 2. The server compares the user's preference information and selects products that are highly nutritious and effective in recovering from fatigue.

[0940] 3. The server sends the selected product to the user's device.

[0941] 4. The terminal displays the products to the user and assists in the purchase process.

[0942] Input: Sentiment analysis results, user preference information

[0943] Data calculation: Matching preference information with emotion analysis results and selecting optimal products

[0944] Output: The best products displayed to the user, and assistance with the purchase process

[0945] (Application example 1)

[0946] Next, a description will be given of Application Example 1 of Form 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".

[0947] Conventional food delivery systems generally suggest products that take into account the user's preferences and allergy information, but do not suggest products that take into account the user's emotional state. As a result, there is a problem that the system cannot suggest optimal products when the user is tired or in a specific emotional state, and it is not possible to sufficiently increase user satisfaction.

[0948] 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.

[0949] In this invention, the server includes a means for utilizing AI for various evaluations and judgments such as product ingredient analysis, monitor evaluations, and product design, a means for matching the results of the evaluations and judgments with the user's preregistered preferences, a means for suggesting products based on the matching results, a system including a mechanism for allowing the user to purchase the suggested products if they are on sale, and a means for suggesting products based on the user's emotional state using an emotion engine that recognizes the user's emotions. This makes it possible to suggest optimal products that take into account not only the user's preferences and allergy information, but also their emotional state.

[0950] "Ingredient analysis" refers to analyzing information such as a product's nutritional components and allergens.

[0951] "Monitor evaluation" refers to the collection and analysis of product evaluations by users and testers.

[0952] "Product design" refers to evaluating the product's appearance and packaging design.

[0953] "Means of utilizing AI" refers to the use of artificial intelligence technology to analyze data and make evaluations and judgments.

[0954] "Preferences" refers to information about personal preferences, such as the user's favorite ingredients, seasonings, and allergy information.

[0955] A "matching means" is a means for comparing a user's preferences with the product evaluation results and selecting the most suitable product.

[0956] The "means of suggestion" refers to a means of presenting the most suitable product to the user based on the matching results.

[0957] An "emotion engine" is a technology that recognizes emotions from a user's facial expressions, voice, text input, etc.

[0958] "Emotional state" refers to a user's current mood or psychological state.

[0959] A "mechanism for enabling purchases" is a system that allows users to complete the purchase procedure on the spot if the suggested product is on sale.

[0960] The following system configuration is used as an embodiment of the present invention: The system proposes optimal food delivery items based on the user's preference information and emotional state.

[0961] System Configuration

[0962] Hardware

[0963] Smartphone: A device that allows users to input preference information and emotional state.

[0964] Server: A central processing unit for analyzing data and making product suggestions.

[0965] software

[0966] EmotionEngine: An emotion recognition library for recognizing user emotions.

[0967] FoodRecommendationEngine: A recommendation engine to suggest optimal products based on user preference information and emotional state.

[0968] Data processing and calculation

[0969] Registration of user preferences

[0970] Users use their smartphones to input their preferences (favorite ingredients, allergies, and preferred seasonings). This information is stored in JSON format on the server.

[0971] Emotion recognition

[0972] When a user inputs text, voice, or facial expressions into their smartphone, EmotionEngine analyzes them and recognizes the user's emotional state. For example, if a user inputs "I'm very tired today," EmotionEngine will recognize this as "fatigue."

[0973] Food delivery product proposals

[0974] The server uses the FoodRecommendationEngine to suggest optimal food delivery items based on the user's preference information and the user's recognized emotional state. For example, if the user is tired, nutritious items that are effective in recovering from fatigue (such as vitamin-rich salads and protein shakes) are suggested.

[0975] Examples

[0976] Registration of user preferences

[0977] The user opens the smartphone app and enters the following:

[0978] Favorite ingredients: Chicken, rice

[0979] Disliked food: Fish

[0980] Allergies: Nuts

[0981] Favorite seasoning: Spicy

[0982] Emotion recognition

[0983] A user types the text "I'm very tired today" into their smartphone. EmotionEngine recognizes this as "fatigue."

[0984] Food delivery product proposals

[0985] The server generates the following prompt sentence based on the user's preference information and emotional state:

[0986] "We will suggest food delivery options for you. Please wait a moment."

[0987] The FoodRecommendationEngine suggests products that are nutritious and effective in relieving fatigue, such as "vitamin-rich salads" and "protein shakes."

[0988] In this way, a system can be realized that suggests optimal food delivery items based on the user's preferences and emotional state.

[0989] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0990] Step 1:

[0991] Users use their smartphones to input their own preference information. Specifically, they input their favorite ingredients, disliked ingredients, allergy information, preferred seasonings, etc. The input data is sent to the server in JSON format and saved. The input data is saved on the server as the user's preference information.

[0992] Step 2:

[0993] A user uses a smartphone device to input their current emotional state. For example, they input the text "I'm very tired today." This input data is sent to the server and analyzed by EmotionEngine. EmotionEngine analyzes the input text data and recognizes the user's emotional state as "fatigue." The output data is saved on the server as the user's emotional state.

[0994] Step 3:

[0995] The server uses the FoodRecommendationEngine to suggest optimal food delivery items based on the stored user preference information and emotional state. Specifically, the server passes the preference information (favorite ingredients, disliked ingredients, allergy information, preferred seasoning) and emotional state (fatigue) as input data to the FoodRecommendationEngine. The FoodRecommendationEngine analyzes this data and outputs optimal items (for example, vitamin-rich salads or protein shakes).

[0996] Step 4:

[0997] The server proposes the optimal products output from the FoodRecommendationEngine to the user. Specifically, it sends a notification to the smartphone terminal and displays the products proposed to the user. The user can check the proposed products and choose whether or not to purchase them. The output data is the product information proposed to the user.

[0998] Step 5:

[0999] When the user wishes to purchase a suggested product, the user completes the purchase procedure using a smartphone terminal. The server accepts the purchase procedure and sends the order to the food delivery service. Specifically, the server sends the user's purchase information (product name, quantity, delivery address, etc.) to the food delivery service and confirms the order. The output data is the confirmed order information.

[1000] In this way, a system can be realized that suggests optimal food delivery items based on the user's preferences and emotional state and then carries out the purchase process.

[1001] Example 2

[1002] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[1003] Conventional systems did not adequately suggest products based on the user's preferences, making it difficult to increase user satisfaction. In addition, product suggestions did not take into account the user's emotional state, making it difficult to stimulate the user's desire to purchase. Furthermore, it was difficult to properly analyze information on product ingredients and allergens and provide it to users.

[1004] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1005] In this invention, the server includes a means for receiving and storing user preference data, a means for collecting and analyzing product ingredient data, a means for comparing the user preference data with the product ingredient data and evaluating the product, a means for suggesting products based on the evaluation result, a means for making the suggested product available for purchase if it is on sale, a means for recording the user's evaluation data and emotion data, and a means for utilizing the recorded data for the next suggestion. This enables highly accurate product suggestions based on the user's preferences, and increases user satisfaction. Furthermore, product suggestions that take into account the user's emotional state can stimulate the user's purchasing desire. Furthermore, it becomes possible to appropriately analyze product ingredient information and allergen information and provide them to the user.

[1006] "User Preference Data" means information regarding a User's personal preferences, such as the foods the User prefers, ingredients the User wishes to avoid, and allergy information.

[1007] "Ingredient data" refers to specific ingredient information for a product, such as the product's nutritional components, allergens, and main ingredients.

[1008] "Evaluation" is the process of comparing the user's preference data with product ingredient data to select products that are suitable for the user.

[1009] "Product suggestion" refers to the act of presenting products suitable for a user based on the results of the evaluation judgment.

[1010] "Emotional Data" is information that records the emotional state a user felt when rating a product.

[1011] "Means for making a product available for purchase" refers to a mechanism that allows a user to purchase a product on the spot if the suggested product is on sale.

[1012] "Means of utilizing recorded data for next proposals" refers to a system that reflects the user's past evaluation data and emotional data in the next product proposal.

[1013] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1014] The present invention is a system for analyzing the ingredients of products based on user preference data and proposing suitable products. A specific embodiment of this system will be described below.

[1015] Server Roles

[1016] The server receives and stores the user's preference data. The preference data entered by the user through the terminal (e.g. "I like fish," "I don't like spicy food," "I have no allergies") is sent to the server and stored in a database. MySQL, PostgreSQL, or similar databases are used as the database.

[1017] Next, the server collects and analyzes the product's ingredient data. The ingredient data includes the product's nutritional content and allergens. The collected data is analyzed using AI models such as TensorFlow and PyTorch. As a result of the analysis, characteristics such as "mainly contains fish" and "does not contain spicy ingredients" are extracted.

[1018] The server compares the user's preference data with the product's ingredient data and makes an evaluation decision. It uses an SQL query to compare the data and selects products that match the user's preferences. Based on the evaluation results, it generates a list of products to suggest to the user and sends it to the terminal.

[1019] In addition, the server records the user's evaluation data and emotion data. When a user evaluates a product, the server receives the emotion data (e.g., "This chocolate is delicious!", an emotion of joy) along with the evaluation and records it in the database. The recorded data will be used for the next proposal.

[1020] Terminal Roles

[1021] The terminal provides an interface for the user to input preference data. A front-end framework such as React or Vue.js is used to display a form for the user to input the preference data. The input data is sent to the server using an HTTP request (e.g., POST request).

[1022] The terminal displays the product suggestion list sent from the server to the user. The product suggestion list is displayed in HTML format, and the user can check the suggested products.

[1023] The terminal also provides an interface for users to rate products. When users input emotion data along with their ratings, the data is sent to the server.

[1024] User Roles

[1025] The user inputs preference data through the terminal interface. For example, "I like fish," "I don't like spicy food," "I have no allergies," etc. The input data is sent to the server.

[1026] The user checks the product suggestion list displayed on the terminal, and if the suggested product is on sale, the user can purchase it on the spot.

[1027] The user rates the proposed products and inputs emotion data along with the rating, for example, "This salmon sashimi is delicious!" The input data is sent to the server.

[1028] Examples of concrete examples and prompts

[1029] As a specific example, if a user registers preferences such as "I like fish," "I don't like spicy food," and "I have no allergies," the server uses an AI model to analyze the ingredients of the product and evaluates and judges products that "are mainly made of fish" and "do not contain spicy ingredients." For example, the server might suggest "salmon sashimi" or "fried white fish." If the user evaluates the product as "This salmon sashimi is delicious!", the server also records the emotion of joy. The next time, a product that is likely to evoke a similar emotion of joy for the user (for example, "tuna sashimi") will be suggested.

[1030] An example of a prompt sentence is as follows:

[1031] "Based on the user's preference data (e.g., likes fish, dislikes spicy food, no allergies), please use an AI model to analyze the ingredients of the product and suggest products that suit the user. Also, please record the user's evaluation and their emotional state at the time, and use them for the next suggestion."

[1032] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1033] Program processing flow

[1034] Step 1: Enter and submit your preferences

[1035] Subject: User

[1036] The user inputs preference data through the terminal interface, such as "I like fish," "I don't like spicy food," and "I have no allergies." The input data is then sent to the server via an HTTP POST request.

[1037] Input: User preference data

[1038] Output: Preference data sent to the server

[1039] Step 2: Receiving and storing preference data

[1040] Subject: Server

[1041] The server receives the preference data sent by the user. The received data is stored in a database (e.g., MySQL or PostgreSQL). The stored data is used for later processing.

[1042] Input: Preference data submitted by the user

[1043] Output: Preference data stored in a database

[1044] Step 3: Collect and analyze product ingredient data

[1045] Subject: Server

[1046] The server collects product ingredient data. The collected data is input into an AI model (e.g., TensorFlow or PyTorch) and ingredient analysis is performed. As a result of the analysis, characteristics such as "mainly contains fish" and "does not contain spicy ingredients" are extracted.

[1047] Input: Product ingredient data

[1048] Output: Analyzed component data (feature extraction results)

[1049] Step 4: Matching preference data with ingredient data and evaluating

[1050] Subject: Server

[1051] The server compares the user's preference data stored in the database with the analyzed product ingredient data, and uses SQL queries to compare the data and evaluate and determine products that match the user's preferences.

[1052] Input: User preference data, analyzed ingredient data

[1053] Output: Evaluation result (list of products suitable for the user)

[1054] Step 5: Generate and submit product proposals

[1055] Subject: Server

[1056] The server generates a list of products to be proposed to the user based on the evaluation results, and sends the generated list of products to the terminal via an HTTP response.

[1057] Input: Evaluation result

[1058] Output: Product suggestions list sent to the terminal

[1059] Step 6: View product suggestions

[1060] Subject: Terminal

[1061] The terminal displays the product suggestion list sent from the server to the user. The product suggestion list is displayed in HTML format, and the user can check the suggested products.

[1062] Input: Product suggestions list sent from the server

[1063] Output: A list of product suggestions displayed to the user

[1064] Step 7: Enter and submit product ratings and sentiment data

[1065] Subject: User

[1066] The user rates the proposed products and inputs emotional data along with the rating, for example, "This salmon sashimi is delicious!" The input data is sent to the server via an HTTP POST request.

[1067] Input: User rating and sentiment data

[1068] Output: Rating and sentiment data sent to the server

[1069] Step 8: Receive and record rating and emotion data

[1070] Subject: Server

[1071] The server receives the evaluation data and emotion data sent by the user. The received data is recorded in a database. The recorded data is used for the next proposal.

[1072] Input: User-submitted rating and sentiment data

[1073] Output: Evaluation data and emotion data recorded in a database

[1074] Step 9: Use data to improve your next proposal

[1075] Subject: Server

[1076] The server analyzes the recorded evaluation data and emotion data and uses it to suggest products for the next time. For example, if a user evaluates "This salmon sashimi is delicious!", the server will suggest products that are likely to evoke a similar emotion of joy, such as "tuna sashimi."

[1077] Input: Recorded rating and emotion data

[1078] Output: Data used for the next proposal

[1079] (Application example 2)

[1080] Next, a description will be given of Application Example 2 of Form 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".

[1081] Conventional product recommendation systems can take into account the user's preferences and allergy information, but they do not consider the user's emotional state when making product recommendations. This makes it difficult to make product recommendations that recreate the joy and satisfaction that the user felt in the past. In addition, food delivery services lack the ability to suggest optimal dishes and foods based on the user's preferences and emotional state. This makes it difficult to increase user satisfaction.

[1082] 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.

[1083] In this invention, the server includes a means for utilizing AI for various evaluations and judgments such as product ingredient analysis, monitor evaluations, and product design, a means for matching the results of the evaluations and judgments with the user's preregistered preferences, a means for suggesting products based on the matching results, a means including a mechanism for allowing the user to purchase the suggested products if they are on sale, a means for recording the user's emotional state and suggesting products based on the emotional state, and a means for suggesting optimal dishes and foods based on the user's preferences and emotional state. This makes it possible to suggest optimal products and dishes based on the user's preferences and emotional state, thereby increasing user satisfaction.

[1084] "Ingredient analysis" is the process of analyzing the ingredients of a product and identifying their contents.

[1085] "Evaluation and judgment" is the process of using AI to evaluate the quality and characteristics of a product and judging the results.

[1086] "Preferences" refer to specific ingredients or characteristics that a user prefers.

[1087] "Matching" is the process of comparing a user's preferences with the results of their evaluation judgment and identifying matching products.

[1088] "Product suggestion" is the process of presenting the most suitable products to the user based on the matching results.

[1089] "Emotional state" refers to the feelings such as pleasure, satisfaction, and discomfort that users have when evaluating a product.

[1090] "Cuisine" refers to food made by cooking ingredients.

[1091] "Food" refers to ingredients or dishes offered for consumption by a consumer.

[1092] "Food delivery" is a service that delivers dishes or food ordered by users to a specified location.

[1093] The system for implementing the present invention proposes optimal products and dishes based on the preferences and emotional state of a user. A specific embodiment of this system will be described below.

[1094] System Configuration

[1095] The system mainly consists of a server, a user terminal, and a database. The server performs product ingredient analysis, evaluation judgment, preference matching, product suggestions, and recording and analysis of emotional states. User terminals include smartphones, smart glasses, head-mounted displays, etc., and provide an interface for users to input preferences and emotional states. The database stores product ingredient information, user preference data, and emotional state data.

[1096] Program Processing

[1097] The server performs the following process.

[1098] 1. Ingredient analysis: The server analyzes the ingredient information of the product and identifies its contents. Specifically, to obtain information on the product's nutritional content, allergens, etc., the server retrieves the necessary data from the database and analyzes it using an AI model.

[1099] 2. Evaluation judgment: The server uses AI to evaluate the quality and characteristics of the product and judges the result. The evaluation judgment also takes into account the user's past purchase history and evaluation history.

[1100] 3. Taste matching: The server compares the taste data registered by the user in advance with the results of the evaluation judgment and identifies matching products. This allows the server to select products that match the user's tastes.

[1101] 4. Product Suggestion: The server recommends the best products to the user based on the matching results. If the suggested products are on sale, the user can purchase them on the spot.

[1102] 5. Recording and analyzing emotional states: The server records the emotional states felt by the user when rating products and analyzes the data, which makes it possible to suggest products based on the user's emotional state.

[1103] Hardware and Software Used

[1104] Hardware: Servers, smartphones, smart glasses, head-mounted displays

[1105] Software: AI models (e.g. TensorFlow, PyTorch), database management systems (e.g. MySQL, PostgreSQL)

[1106] Examples

[1107] For example, if a user registers preferences such as "I like fish," "I don't like spicy food," and "I have no allergies," and in the past recorded the emotion of "happiness" when rating "salmon sushi," the system will suggest "salmon sushi" and also display the user's emotional state at the time.

[1108] Examples of prompt statements

[1109] Please register user preference data. Example: {"likes": ["fish"], "dislikes": ["spicy food"], "allergies": []}

[1110] Enter your product data. Example: [{"name": "Salmon Sushi", "ingredients": "Fish, Rice, Seaweed", "spicy": False}, {"name": "Spicy Ramen", "ingredients": "Noodles, Chili Pepper, Pork", "spicy": True}]

[1111] Enter user emotion data. Example: {"Salmon sushi": "Happy", "Spicy ramen": "Unhappy"}

[1112] In this way, a system can be realized that suggests optimal products and dishes based on the user's preferences and emotional state.

[1113] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1114] Step 1:

[1115] A user inputs preference data using a terminal.

[1116] Input: User preference data (e.g. "I like fish," "I don't like spicy food," "I have no allergies")

[1117] Output: The preference data is sent to the server and stored in a database.

[1118] Specific operation: The user inputs preference data through the terminal interface and presses the send button. The terminal sends this data to the server, which then stores it in the database.

[1119] Step 2:

[1120] The server retrieves the product's ingredient data from the database and performs ingredient analysis.

[1121] Input: Product ingredient data (e.g. "Salmon sushi: fish, rice, seaweed" "Spicy ramen: noodles, chili pepper, pork")

[1122] Output: Component analysis results (e.g. "Salmon sushi: contains fish as the main component" "Spicy ramen: contains spicy components")

[1123] Specific operation: The server retrieves the product's ingredient data from the database and performs ingredient analysis using the AI ​​model. The analysis results are temporarily stored in memory.

[1124] Step 3:

[1125] The server matches the preference data with the results of component analysis.

[1126] Input: preference data, component analysis results

[1127] Output: Matching results (e.g. "Salmon sushi is good" "Spicy ramen is not good")

[1128] Specific operation: The server compares the preference data with the results of the component analysis and identifies products that match the user's preferences. The matching results are temporarily stored in memory.

[1129] Step 4:

[1130] The server suggests products based on the matching results.

[1131] Input: Matching results

[1132] Output: Suggested items (e.g. "Salmon Sushi")

[1133] Specific operation: Based on the matching results, the server selects the most suitable products for the user and generates a list of suggested products. This list is sent to the terminal.

[1134] Step 5:

[1135] The user uses the terminal to rate the proposed products and input his / her emotional state.

[1136] Input: User's rating and emotional state (e.g. "Salmon sushi: Delicious! Delighted")

[1137] Output: The rating data and emotional state data are sent to the server and stored in a database.

[1138] Specific operation: The user evaluates the proposed products through the terminal interface and inputs his / her emotional state at that time. The terminal transmits this data to the server, which stores it in a database.

[1139] Step 6:

[1140] The server analyzes the emotional state data and uses it for the next suggestion.

[1141] Input: Rating data and emotional state data

[1142] Output: Analysis results (e.g. "Salmon sushi brings joy to the user")

[1143] How it works: The server analyzes the evaluation data and emotional state data, and uses an AI model to learn patterns to use in the next recommendation. The analysis results are stored in a database.

[1144] In this way, a system is realized that suggests optimal products and dishes based on the user's preferences and emotional state.

[1145] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[1146] 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> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[1147] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1148] 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 smart glasses 214.

[1149] [Third embodiment]

[1150] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1151] 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.

[1152] 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 wide area network (WAN) and / or a local area network (LAN).

[1153] 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.

[1154] 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 the voice according to instructions from the processor 46.

[1155] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[1156] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1157] Fig. 6 shows an example of 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.

[1158] 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.

[1159] 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.

[1160] In the headset type terminal 314, 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.

[1161] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1162] "Example 1"

[1163] In one embodiment of the present invention, a user registers their preferences in the system. These preferences include various information related to food, such as favorite ingredients, allergy information, and preferred seasonings. The system then uses AI to evaluate and judge the product's ingredients, monitor evaluations, product design, and other factors. This evaluation takes into account various information related to the product, such as the product's nutritional content, allergens, appearance, and taste. The system then matches the user's preferences with the results of the evaluation and judgement, and suggests the most suitable product for the user. If the suggested product is on sale, the user can purchase it on the spot.

[1164] "Example 2"

[1165] As a specific example, let's say a user registers preferences such as "I like fish," "I don't like spicy food," and "I have no allergies." The system uses AI to analyze the ingredients of products and evaluates products that "have fish as a main ingredient" and "don't contain spicy ingredients." The system then matches this information and suggests products to the user that "have fish as a main ingredient and don't contain spicy ingredients." If the suggested products are on sale, the user can purchase them on the spot.

[1166] The process flow of each embodiment will be described below.

[1167] "Example 1"

[1168] Step 1: The user registers their preferences in the system. These preferences include various information about food, such as favorite ingredients, allergy information, and preferred seasonings.

[1169] Step 2: The system uses AI to evaluate and judge the product's ingredients, monitor evaluation, product design, etc. This evaluation takes into account various information about the product, such as the product's nutritional content, allergens, appearance, taste, etc.

[1170] Step 3: The system matches the user's preferences with the evaluation results and suggests the most suitable products for the user.

[1171] Step 4: If the suggested product is available, the user can purchase it on the spot.

[1172] "Example 2"

[1173] Step 1: The user registers their preferences, such as "I like fish," "I don't like spicy food," or "I have no allergies."

[1174] Step 2: The system uses AI to analyze the product's ingredients and evaluates the product as "containing fish as the main ingredient" and "not containing spicy ingredients."

[1175] Step 3: The system matches this information and suggests products to the user that are "fish-based and do not contain spicy ingredients."

[1176] Step 4: If the suggested product is available, the user can purchase it on the spot.

[1177] Example 1

[1178] Next, a description will be given of Example 1 of the embodiment 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".

[1179] Conventional systems have difficulty in proposing optimal products based on users' preferences, and also do not adequately consider product ingredients and allergy information. As a result, it is difficult for users to find products that suit their preferences and health conditions.

[1180] 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.

[1181] In this invention, the server includes a means for a user to input his / her preference information, a means for collecting product ingredient data, a means for performing ingredient analysis and evaluation using AI based on the collected ingredient data, a means for matching the user's preference information with the product evaluation results, a means for suggesting products based on the matching results, and a means for allowing the user to purchase the suggested products if they are on sale. This makes it possible to suggest and purchase the most suitable products that match the user's preferences and health condition.

[1182] "User" refers to an individual who uses the system to input their own preference information and receive suggestions of the most suitable products.

[1183] "Preference information" refers to food-related information entered by the user, such as favorite ingredients, allergy information, and preferred seasonings.

[1184] "Ingredient data" refers to detailed information about a product, such as its nutritional content, allergens, appearance, and taste.

[1185] "AI" refers to artificial intelligence, specifically the technology of component analysis and evaluation using machine learning frameworks such as TensorFlow and PyTorch.

[1186] "Ingredient analysis" refers to the process of evaluating nutritional components, allergens, etc. based on a product's ingredient data.

[1187] "Evaluation results" refers to the results of ingredient analysis conducted by AI, and include evaluations of the product's nutritional content, allergens, appearance, taste, etc.

[1188] "Matching" refers to the process of comparing user preference information with product evaluation results and selecting the most suitable product.

[1189] "Suggestion" refers to the act of notifying the user of the most suitable product based on the matching results.

[1190] "Purchase Means" refers to the mechanism by which a User purchases a proposed Product if the Product is on sale.

[1191] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1192] This invention is a system that uses AI to analyze and evaluate the ingredients of products based on user preference information and proposes optimal products. A specific embodiment of this system will be described below.

[1193] Input of user preferences

[1194] Users input their own preference information using a dedicated device or smartphone app. Preference information includes favorite ingredients, allergy information, preferred seasonings, etc. For example, a user might input "I like tomatoes," "I'm allergic to nuts," and "I like spicy food."

[1195] Collect product data

[1196] The server collects product data through a database or external API. The collected data includes the product's nutritional content, allergens, appearance, taste, etc. For example, the server obtains "ingredients information for product X."

[1197] Product composition analysis and evaluation

[1198] The server uses AI to analyze ingredients and evaluate products based on the collected product data. This AI is built using machine learning frameworks such as TensorFlow and PyTorch. For example, the server might evaluate "Product X contains tomatoes, does not contain nuts, and is spicy."

[1199] Matching user preferences

[1200] The server matches the user's preference information with the evaluation results of the product. For example, the server "compares the preference information of user A with the evaluation results of product X and calculates a matching score."

[1201] Optimal product proposals

[1202] The server proposes products with high matching scores to users. The proposals are made through a dedicated terminal or smartphone app. For example, the server proposes "Product X to User A."

[1203] Purchase of products

[1204] Users can purchase the suggested products through a dedicated device or smartphone app. For example, User A "purchases Product X using a smartphone app."

[1205] Examples

[1206] Example 1: Registering user preferences

[1207] User A registers in the system his favorite food ingredient "tomato," his allergy information "nut allergy," and his favorite seasoning "spicy food."

[1208] Example 2: Product composition analysis and evaluation

[1209] The server analyzes the ingredients of product X. Product X contains "tomatoes" and no nuts. It also has a spicy flavor. The server uses TensorFlow to evaluate this information and decides whether it matches the preferences of user A.

[1210] Example 3: Matching and Suggestions

[1211] The server matches the preference information of User A with the evaluation result of Product X and proposes Product X to User A. User A can purchase Product X through a smartphone app.

[1212] Examples of prompt statements

[1213] "Please explain the system that uses AI to analyze and evaluate the ingredients of products based on user preference information and recommend the most suitable products. Please also specify the names of specific hardware and software."

[1214] By feeding this prompt into a generative AI model, a detailed explanation of the system can be obtained.

[1215] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1216] Step 1:

[1217] Users input their own preference information using a dedicated device or smartphone app. The input preference information includes favorite ingredients, allergy information, and preferred seasonings. For example, a user might input "I like tomatoes," "I'm allergic to nuts," and "I like spicy food." The input data is sent to the server and saved in a database.

[1218] Step 2:

[1219] The server collects product data through a database or external API. The collected data includes the product's nutritional content, allergens, appearance, and taste. For example, the server obtains "ingredients information for product X." The obtained data is stored in a database.

[1220] Step 3:

[1221] The server uses AI to analyze ingredients and perform evaluation based on the collected product data. This AI is built using machine learning frameworks such as TensorFlow and PyTorch. For example, the server evaluates "Product X contains tomatoes and no nuts. It is seasoned with hot sauce." The input is the product data, and the output is the evaluation result.

[1222] Step 4:

[1223] The server matches the user's preference information with the product evaluation results. For example, the server "compares the preference information of user A with the evaluation results of product X and calculates a matching score." The input is the user's preference information and the product evaluation results, and the output is the matching score.

[1224] Step 5:

[1225] The server proposes products with high matching scores to users. Suggestions are made through dedicated terminals or smartphone apps. For example, the server "proposes product X to user A." The input is the matching score, and the output is information about the proposed product.

[1226] Step 6:

[1227] The user can purchase the suggested product through a dedicated terminal or smartphone app. For example, user A "purchases product X using a smartphone app." The input is the information about the suggested product, and the output is a notification of purchase completion.

[1228] (Application example 1)

[1229] Next, a description will be given of Application Example 1 of Form 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".

[1230] Conventional food delivery services have had the problem that it is difficult to suggest optimal dishes that take into account the user's preferences and allergy information. In addition, users have to check many menus to find a dish that suits them, which is time-consuming and labor-intensive.

[1231] The identification process by the identification processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means. In this invention, the server includes a means for utilizing AI for various evaluations and judgments such as component analysis of products, monitor evaluations, and product design, a means for matching the results of the evaluations and judgments with the user's preferences registered in advance, a means for suggesting products based on the matching results, a system including a mechanism for allowing the user to purchase the suggested products if they are on sale, a means for registering user preference information, analyzing the menu of a food delivery service, and suggesting the most suitable dish, and a means for ordering the suggested dish on the spot. This makes it possible to suggest the most suitable dish taking into account the user's preferences and allergy information, and allows the user to easily find and order the dish that suits him or her.

[1232] "Product ingredient analysis" refers to obtaining and analyzing information about a product's nutritional components, allergens, etc.

[1233] "Monitor evaluation" refers to the collection and analysis of product evaluations by users and experts.

[1234] "Product design" refers to evaluating the product's appearance and packaging design.

[1235] "Means of utilizing AI" refers to the use of artificial intelligence to analyze data and make evaluations and judgments.

[1236] "My preferences" refers to information such as favorite ingredients, disliked ingredients, allergy information, and preferred seasonings that are registered in advance by the user.

[1237] The "evaluation result" refers to the evaluation conducted by AI based on the product's ingredient analysis, monitor evaluation, product design, etc.

[1238] A "matching means" is a means of comparing the user's preferences with the results of the evaluation judgment and selecting the most suitable product.

[1239] The "means for suggesting products" refers to a means for presenting the most suitable products to the user based on the matching results.

[1240] A "mechanism for enabling purchase" is a mechanism that allows users to purchase a suggested product on the spot if the product is on sale.

[1241] "User preference information" refers to information registered by the user, such as favorite ingredients, disliked ingredients, allergy information, and preferred seasonings.

[1242] A "food delivery service menu" is a list of dishes offered by a food delivery service.

[1243] The "means for suggesting the most suitable dish" refers to a means for analyzing a user's preference information and the menu of a food delivery service, and selecting and suggesting the most suitable dish to the user.

[1244] An "instant ordering solution" is a solution that allows a user to instantly order a suggested dish.

[1245] The system for implementing this invention registers user preference information, analyzes the menu of food delivery services, and suggests the most suitable dishes. The system is realized using the following hardware and software.

[1246] Hardware

[1247] Smartphone: A device that allows users to register their preferences and view and order suggested dishes.

[1248] Server: A device for running AI models and analyzing data.

[1249] software

[1250] Python: A programming language used for data analysis and running AI models.

[1251] scikit-learn: A machine learning library for data vectorization and similarity calculations.

[1252] requests: An HTTP library for retrieving menu information from food delivery service APIs.

[1253] Processing flow

[1254] 1. Registration of user preferences

[1255] Users register their preferences (favorite ingredients, disliked ingredients, allergy information, preferred seasonings, etc.) through a smartphone application. This information is sent to the server and stored in a database.

[1256] 2. Get menu information

[1257] The server uses the requests library to retrieve the latest menu information from the food delivery service's API, including product descriptions and ingredient information.

[1258] 3. Component analysis and evaluation

[1259] The server uses scikit-learn to convert the menu descriptions into TF-IDF vectors, compare them with the user's preference information, and calculate the cosine similarity, thereby identifying the dish that best matches the user's preference.

[1260] 4. Food suggestions

[1261] The server then suggests the best dishes to the user based on the calculated similarity, and the suggested dishes are notified to the user via a smartphone application.

[1262] 5. Order Execution

[1263] Users can review the suggested dishes and place their order on the spot, and the order information is sent to a food delivery service, which then delivers the food to the user.

[1264] Examples

[1265] For example, if a user registered the following preferences:

[1266] User Preferences:

[1267] Favorite ingredients: Chicken, Tomato

[1268] Disliked food: Peanuts

[1269] Allergies: Nuts

[1270] Favorite seasoning: Spicy

[1271] If a food delivery service's menu includes the following:

[1272] Food delivery service menu:

[1273] 1. Chicken Curry: Spicy chicken curry in a tomato-based sauce.

[1274] 2. Peanut Sauce Salad: Salad made with peanut sauce.

[1275] 3. Tomato pasta: Pasta with tomato sauce.

[1276] The system will analyze the user's preferences and menu information and make the following suggestions:

[1277] Recommended dishes:

[1278] 1. Chicken Curry: Spicy chicken curry in a tomato-based sauce.

[1279] 2. Tomato pasta: Pasta with tomato sauce.

[1280] In this way, users can easily find and order dishes that suit their tastes.

[1281] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1282] Step 1:

[1283] The user inputs his / her preference information (favorite ingredients, disliked ingredients, allergy information, preferred seasoning, etc.) through a smartphone application. The input preference information is sent from the smartphone to the server and stored in a database. The input for this step is the user's preference information, and the output is the preference information stored on the server.

[1284] Step 2:

[1285] The server uses the requests library to get the latest menu information from the food delivery service's API. The menu information includes product descriptions and ingredient information. The input of this step is the API request, and the output is the menu information.

[1286] Step 3:

[1287] The server uses scikit-learn to vectorize the menu descriptions using TF-IDF. Specifically, each menu description is converted into a numerical vector based on the frequency of occurrence of words. The input for this step is the menu description, and the output is the vectorized menu information.

[1288] Step 4:

[1289] The server vectorizes the user's preference information and compares it with the menu information to calculate the cosine similarity. Specifically, the user's preference information is expressed as a vector, and the cosine similarity is calculated between the vector of each menu. The input of this step is the vectorized user's preference information and menu information, and the output is the similarity score with each menu.

[1290] Step 5:

[1291] The server selects the best dishes for the user based on the calculated similarity score, taking into account allergy information and excluding dishes that contain allergens. The inputs of this step are the similarity score and allergy information, and the output is a list of dishes to suggest to the user.

[1292] Step 6:

[1293] The server sends the list of suggested dishes to the smartphone application, through which the user can review the suggested dishes. The input of this step is the list of suggested dishes, and the output is the list of dishes displayed in the smartphone application.

[1294] Step 7:

[1295] The user can review the proposed dishes and place an order on the spot. The order information is sent from the smartphone to the server, which then forwards it to the food delivery service. The input of this step is the user's order information, and the output is the order information sent to the food delivery service.

[1296] In this way, users can easily find and order dishes that suit their tastes.

[1297] Example 2

[1298] Next, a second embodiment of the second form will be described. 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".

[1299] In conventional systems, it was difficult to efficiently match user preference information with product ingredient information, and it was not possible to suggest the most suitable products to users. In addition, there was a lack of means to analyze product ingredient information in detail and find products that match the user's preferences. Furthermore, there was an insufficient mechanism to check whether the suggested products were on sale and to smoothly carry out the purchasing procedure.

[1300] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1301] In this invention, the server includes a means for a user to input preference information using a terminal, a means for transmitting the input preference information to the server and storing it in a database, a means for collecting product ingredient information and analyzing the ingredient information using a generative AI model, a means for matching the user's preference information with the product ingredient information, a means for suggesting products based on the matching results, and a means for allowing the user to purchase the suggested products if they are on sale. This makes it possible to efficiently find products that match the user's preferences and smoothly carry out the purchase procedure if the suggested products are on sale.

[1302] "User" means an individual or group that uses the system to input preference information and receive product suggestions.

[1303] A "terminal" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[1304] "Preference information" is personal data entered by the user, such as their preferences or allergy information.

[1305] A "server" is a computer system that receives preference information sent by a user, stores it in a database, and analyzes product ingredient information.

[1306] A "database" is a data management system in which a server stores preference information and product ingredient information.

[1307] "Product ingredient information" is detailed information about a product, such as its nutritional components and allergens.

[1308] A "generative AI model" is an artificial intelligence model used to analyze product ingredient information and match it with user preference information.

[1309] "Matching" is the process of comparing a user's preference information with product ingredient information to find products that meet the conditions.

[1310] "Suggestion" refers to the act of presenting products suitable for the user based on the matching results.

[1311] A "checkout" is a series of operations and processes that a user performs to purchase a suggested product.

[1312] The present invention is a system for suggesting optimal products based on user preference information and supporting the purchase procedure. A specific embodiment of this system will be described below.

[1313] First, the user inputs preference information using a terminal. The terminal is an electronic device such as a smartphone, tablet, or computer. The user starts a dedicated application and inputs preference information. For example, the user inputs information such as "I like fish," "I don't like spicy food," and "I have no allergies."

[1314] Next, the terminal transmits the input preference information to a server. The server stores the received preference information in a database. The database is a data management system for managing the preference information and the ingredient information of the product. For example, a database such as MySQL can be used.

[1315] The server collects product ingredient information. The product ingredient information is detailed information such as the product's nutritional content and allergens. The server provides an API for scanning product barcodes. The user scans the product's barcode using the device's camera, and the device sends the scanned barcode information to the server. The server obtains the product's ingredient information based on the barcode information.

[1316] Next, the server uses a generative AI model to analyze the collected product ingredient information. The generative AI model uses, for example, OpenAI's GPT-4. The server sends the following prompt to the generative AI model:

[1317] Product ingredient information: Contains fish as the main ingredient and does not contain any spicy ingredients.

[1318] Rate this product and decide whether to recommend it to your users.

[1319] The generative AI model analyzes the ingredient information and returns the evaluation results to the server. The server matches the user's preference information with the product's ingredient information based on the evaluation results from the generative AI model. For example, it lists products that match conditions such as "I like fish" or "I don't like spicy food."

[1320] The server generates a list of matching products and sends it to the terminal, which displays the suggestions to the user, for example, displaying a message such as "We found a product that is fish-based and does not contain spicy ingredients."

[1321] The user uses the terminal to check the proposed products. If he / she wishes to purchase the product, he / she clicks the "Purchase" button on the terminal. The server provides an interface to support the purchase procedure and processes the payment. For example, it displays a form for entering credit card information.

[1322] In this way, products that match the user's preferences can be efficiently found, and if the suggested product is on sale, the user can smoothly complete the purchase procedure.

[1323] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1324] Step 1:

[1325] The user inputs preference information using the terminal.

[1326] Specific operations: The user launches a dedicated application and enters information such as "I like fish," "I don't like spicy food," and "I have no allergies" into a preference input form.

[1327] Input: User preference information

[1328] Output: Preference information entered into the device

[1329] Step 2:

[1330] The terminal transmits the input preference information to the server.

[1331] Specific operation: When the user clicks the "Send" button, the device sends the preference information to the server in JSON format.

[1332] Input: Preference information entered into the device

[1333] Output: Preference information sent to the server

[1334] Step 3:

[1335] The server stores the received preference information in a database.

[1336] Specific operation: The server parses the received JSON data and stores the preference information in a database, for example, a MySQL database.

[1337] Input: Preference information sent to the server

[1338] Output: Preference information stored in a database

[1339] Step 4:

[1340] The server collects information on ingredients of the product.

[1341] Specific operation: The user uses the device's camera to scan the barcode of the product, and the device sends the scanned barcode information to the server. The server obtains the product's ingredient information based on the barcode information.

[1342] Input: Barcode information of scanned item

[1343] Output: Product ingredient information collected on the server

[1344] Step 5:

[1345] The server uses a generative AI model to analyze the collected product ingredient information.

[1346] Specific operation: The server sends the following prompt to the generative AI model:

[1347] Product ingredient information: Contains fish as the main ingredient and does not contain any spicy ingredients.

[1348] Rate this product and decide whether to recommend it to your users.

[1349] The generative AI model analyzes the ingredient information and returns the evaluation results to the server.

[1350] Input: Product ingredient information, prompt text

[1351] Output: Evaluation results from the generative AI model

[1352] Step 6:

[1353] The server matches the user's preference information with product ingredient information based on the evaluation results from the generative AI model.

[1354] Specific operation: The server analyzes the evaluation results and lists products that meet conditions such as "I like fish" or "I don't like spicy food."

[1355] Input: Evaluation results from the generative AI model, user preference information

[1356] Output: A list of matching products

[1357] Step 7:

[1358] The server generates a list of matching products and transmits it to the terminal.

[1359] Specific operation: The server sends a list of matching products in JSON format to the terminal, and the terminal displays the suggestions to the user.

[1360] Input: A list of matching items

[1361] Output: The suggestions displayed on the terminal

[1362] Step 8:

[1363] The user uses the terminal to check the suggested products and, if they wish to purchase them, completes the purchase procedure.

[1364] Specific operation: The user checks the details of the proposed product and clicks the "Purchase" button. The server provides an interface to support the purchase procedure and processes the payment. For example, it displays a form for entering credit card information.

[1365] Input: User's purchase request

[1366] Output: Purchase completed

[1367] (Application example 2)

[1368] Next, a description will be given of Application Example 2 of Form 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".

[1369] Conventional food delivery systems do not adequately consider user preferences and allergy information when making menu suggestions, making it difficult for users to find dishes that suit them. They also lack a mechanism for easily ordering and paying for suggested dishes on the spot. For this reason, more personalized menu suggestions and smooth ordering and payment are required to improve user satisfaction.

[1370] 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.

[1371] In this invention, the server includes a system including a means for utilizing AI for various evaluations and judgments such as product ingredient analysis, monitor evaluations, and product design, a means for matching the results of the evaluations and judgments with the user's pre-registered preferences, a means for suggesting products based on the matching results, a mechanism for allowing the user to purchase the suggested products if they are on sale, a means for suggesting suitable dishes from restaurant menus based on the user's preference information, and a means for ordering and paying for the suggested dishes on the spot. This enables personalized menu suggestions that take into account the user's preferences and allergy information, and smooth ordering and payment.

[1372] "Ingredient analysis" refers to analyzing information about a product's ingredients, nutrients, allergens, etc.

[1373] "Monitor evaluation" refers to the collection and analysis of feedback and evaluations from users and experts when they use a product.

[1374] "Product design" refers to the design of a product's appearance, packaging, ease of use, etc.

[1375] "Means of utilizing AI" refers to methods of using artificial intelligence technology to analyze data and make evaluations and judgments.

[1376] "Preferences" refers to personal preferences such as the ingredients, flavors, and types of food that a user prefers.

[1377] "Matching" refers to comparing the user's preference information with the product's ingredients and evaluation results to select the most suitable product.

[1378] "Means of suggestion" refers to a method of presenting products and menus that are suitable for the user based on the matching results.

[1379] A "purchase mechanism" is a system that allows users to order and pay for suggested products on the spot.

[1380] A "restaurant menu" refers to a list of food and beverages offered by a restaurant.

[1381] "Means of ordering and payment" refers to the methods by which a User orders the selected dish and completes payment.

[1382] The system for implementing this invention is capable of suggesting suitable dishes from restaurant menus based on the user's preference information, and allowing the suggested dishes to be ordered and paid for on the spot. A specific embodiment of this system is described below.

[1383] System Configuration

[1384] The system consists of the following main components:

[1385] 1. User terminal: A device such as a smartphone or tablet that the user uses to input preference information and confirm and order suggested dishes.

[1386] 2. Server: Using AI models, it performs ingredient analysis and taste matching to suggest dishes suitable for the user.

[1387] 3. Database: Stores restaurant menu information, user preference information, past purchase history, etc.

[1388] Program Processing

[1389] The server does the following:

[1390] 1. Ingredient analysis: Analyze restaurant menu information and extract ingredients, nutrients, allergens, etc. for each dish. This process uses Python and libraries such as scikit-learn.

[1391] 2. Preference matching: The system compares the user's pre-registered preference information (favorite ingredients, disliked ingredients, allergy information) with the results of ingredient analysis to select dishes suitable for the user. This process uses TF-IDF vectorization and cosine similarity calculation.

[1392] 3. Recommendations and Ordering: Based on the matching results, the system will suggest dishes suitable for the user and allow the user to order and pay on the spot. Ordering and payment will be processed in conjunction with a smartphone app.

[1393] Examples

[1394] For example, if a user registers their preferences such as "I like fish" or "I don't like spicy food," the server will suggest dishes such as "salmon sushi" or "tempura" from the restaurant menu. Users can check these suggestions through a smartphone app and order and pay for their favorite dishes on the spot.

[1395] Examples of prompt statements

[1396] Here is an example of a prompt to be input to the generative AI model:

[1397] Create a Python program that suggests suitable dishes from a restaurant menu based on the user's preference information. The user's preference information includes "favorite ingredients," "disliked ingredients," and "allergy information." Convert the menu ingredient information into a TF-IDF vector, calculate the cosine similarity, and suggest the menu that best matches the user's preference.

[1398] In this way, it is possible to create a system that can provide personalized menu suggestions that take into account the user's preferences and allergy information, as well as enable smooth ordering and payment.

[1399] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1400] Step 1:

[1401] The user terminal inputs the user's preference information (favorite ingredients, disliked ingredients, allergy information). The input preference information is sent to the server. The input data is saved in text format.

[1402] Step 2:

[1403] The server retrieves restaurant menu information from the database. The retrieved menu information includes the ingredients, nutrients, allergens, etc. of each dish. The menu information is stored in JSON format.

[1404] Step 3:

[1405] The server performs ingredient analysis on the acquired menu information. Specifically, it uses Python and scikit-learn to convert the ingredient information of each dish into a TF-IDF vector. The input data is the menu information, and the output data is a TF-IDF vector.

[1406] Step 4:

[1407] The server compares the user's preference information with the results of the component analysis. Specifically, it calculates the cosine similarity and selects the dish that best matches the user's preference. The input data is the user's preference information and the TF-IDF vector, and the output data is the similarity score.

[1408] Step 5:

[1409] The server suggests suitable dishes for the user based on the matching results. The suggested dishes are sent to the user terminal. The input data is the similarity score, and the output data is a list of suggested dishes.

[1410] Step 6:

[1411] The user terminal displays the suggested dishes and provides an interface for the user to order the dish of their choice. The user selects among the suggested dishes and confirms the order. The input data is the list of suggested dishes and the output data is the user's selection.

[1412] Step 7:

[1413] The server receives the user's order information and processes the payment. The payment process uses credit card information and electronic payment services. The input data is the user's order information, and the output data is confirmation of payment completion.

[1414] Step 8:

[1415] The server sends the order information and confirmation of payment completion to the restaurant. The restaurant receives the order and starts preparing the food. The input data is the order information and confirmation of payment completion, and the output data is a notification to the restaurant.

[1416] The above processing steps enable personalized menu suggestions that take into account the user's preferences and allergy information, as well as smooth ordering and payment.

[1417] In addition, an emotion engine that estimates the emotion of the user may be further combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[1418] "Example 1"

[1419] In one embodiment of the present invention, an emotion engine is incorporated that recognizes the user's emotions. This emotion engine recognizes emotions from the user's facial expressions, voice, text input, etc., and provides this information to the system. For example, if the user inputs the text "I'm very tired today," the emotion engine recognizes this as an emotional state of "fatigue." This information is used to suggest products. Specifically, if it is recognized that the user is tired, products that are highly nutritious and effective in recovering from fatigue are suggested.

[1420] "Example 2"

[1421] In another embodiment of the present invention, the emotion engine is also used to register user preferences. Specifically, when a user rates a product, their emotional state is also recorded. For example, when a user rates "This chocolate is delicious!", the emotion of joy felt at that time is also recorded. This information is used for future product suggestions, and products that are likely to evoke similar emotions of joy for the user are suggested.

[1422] The process flow of each embodiment will be described below.

[1423] "Example 1"

[1424] Step 1: A user enters text into the system, for example, "I'm very tired today."

[1425] Step 2: The emotion engine recognizes emotions from the text. In this example, it recognizes the emotional state "fatigue."

[1426] Step 3: The system recommends products based on the information from the emotion engine. In this example, products that are nutritious and effective for relieving fatigue are recommended.

[1427] "Example 2"

[1428] Step 1: The user rates the product, for example, "This chocolate is delicious!"

[1429] Step 2: The emotion engine recognizes the user's emotional state and records that information. In this example, it recognizes and records the emotional state "happy."

[1430] Step 3: The system suggests products based on the information from the emotion engine. In this example, the system suggests products that are likely to evoke similar emotions of joy for the user.

[1431] Example 1

[1432] Next, a description will be given of Example 1 of the embodiment 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".

[1433] Conventional systems have a problem in that it is difficult to suggest the best products for users because product suggestions do not sufficiently take into account the user's preference information and emotional state. In addition, because product suggestions are not based on the user's emotional state, it is not possible to provide products that are suitable for the user's current state.

[1434] The identification process by the identification processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means. In this invention, the server includes a means for a user to register his / her preference information, a means for utilizing artificial intelligence for evaluation and judgment of the ingredients, evaluation, design, etc. of a product, and a means for matching the user's preference information with the result of the evaluation and judgment. This makes it possible to propose an optimal product based on the user's preference information and the result of the product evaluation and judgment. In addition, the server includes an emotion engine that recognizes the user's emotions, and further includes a means for recognizing emotions from the user's facial expressions, voice, text input, etc., and utilizing the information in proposing products. This makes it possible to propose products that are nutritious and effective for a specific emotional state based on the user's emotional state.

[1435] "Preference information" is information that indicates a user's personal preferences and restrictions regarding food, such as preferred ingredients, allergy information, and preferred seasonings.

[1436] "Ingredient analysis" is the process of analyzing a product's characteristics, such as its nutritional content, allergens, appearance, and taste.

[1437] "Evaluation and judgment" is a process that uses artificial intelligence to comprehensively evaluate a product's ingredient analysis results, design, monitor evaluations, etc.

[1438] "Matching" is the process of comparing the user's preference information with the product evaluation results and selecting the most suitable product.

[1439] "Suggestion" refers to the act of presenting the most suitable product to the user based on the matching results.

[1440] An "emotion engine" is a system that recognizes emotions from a user's facial expressions, voice, text input, etc., and analyzes that information.

[1441] "Emotional state" is information that indicates the user's current emotions or mood.

[1442] "Nutritional value" is an indicator that shows the value of the nutritional components of a food or product.

[1443] "Purchase history" is a record of products a user has purchased in the past.

[1444] "Rating history" is a record of past product ratings and feedback provided by a user.

[1445] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1446] The present invention is a system for proposing optimal products in consideration of a user's preference information and emotional state. A specific embodiment of this system will be described below.

[1447] Registration of user preferences

[1448] Users input their own preference information using a dedicated terminal or web interface. This information includes favorite ingredients, allergies, and preferred seasonings. The terminal sends this information in JSON format to the server. The server analyzes the received JSON data and stores it in a database.

[1449] Product composition analysis and evaluation

[1450] The server collects product data and inputs it into the AI ​​model. Specifically, it uses machine learning frameworks such as TensorFlow and PyTorch to analyze the nutritional content, allergens, appearance, taste, etc. of the product. The server evaluates the analysis results and stores them in a database.

[1451] Matching user preferences with evaluation results

[1452] The server retrieves user preference information and product evaluation results from the database. It uses SQL or NoSQL queries to match the user preference information with the product evaluation results. The server generates an optimal product list and stores it in the database.

[1453] Optimal product proposals

[1454] The server sends the best product list to the user's device, which then displays the product list to the user and provides a purchase button. When the user clicks the purchase button, the device starts the purchase process.

[1455] Emotion engine recognizes user emotions

[1456] The user uses the device to input text, voice, and recognize facial expressions. For example, if the user inputs the text "I'm very tired today," the device sends this text to the server. The server uses an emotion engine to analyze the emotion "fatigue" from the text. The server stores the analysis results in a database.

[1457] Emotion-based product recommendations

[1458] Based on the analysis results of the emotion engine, the server recognizes that the user is fatigued. The server compares the user's preference information and selects products that are nutritious and effective in relieving fatigue. The server sends the selected products to the user's device. The device displays the products to the user and assists in the purchase process.

[1459] Examples

[1460] User A registers the following preferences in the system:

[1461] Favorite foods: Chicken, broccoli

[1462] Allergy Information: Nut allergies

[1463] Favorite seasoning: sweet and spicy

[1464] If User A enters the text "I'm very tired today," the emotion engine recognizes this as "fatigue." Based on User A's preference information and emotion information, the system suggests a sweet and spicy dish using chicken and broccoli, which is nutritious and effective in relieving fatigue.

[1465] Examples of prompt statements

[1466] "Design a system that suggests optimal products based on a user's preference and emotional information. Preference information includes favorite ingredients, allergies, and preferred seasonings, and emotional information is recognized from the user's facial expressions, voice, and text input. Please also include examples of specific product suggestions."

[1467] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1468] Step 1: Registering user preferences

[1469] 1. The user enters their preferences using a dedicated terminal or web interface.

[1470] 2. The device sends the entered preference information to the server in JSON format.

[1471] 3. The server parses the received JSON data and stores it in the database.

[1472] Input: User's preference information (favorite ingredients, allergy information, preferred seasoning)

[1473] Data processing: Parsing JSON data

[1474] Output: Preference information stored in a database

[1475] Step 2: Product composition analysis and evaluation

[1476] 1. The server collects product data and inputs it into the AI ​​model.

[1477] 2. The server uses machine learning frameworks such as TensorFlow and PyTorch to analyze the product's nutritional content, allergens, appearance, taste, etc.

[1478] 3. The server evaluates the analysis results and stores them in a database.

[1479] Input: Product data (nutritional information, allergens, appearance, taste)

[1480] Data calculation: Ingredient analysis and evaluation judgment using AI model

[1481] Output: Evaluation results stored in a database

[1482] Step 3: Matching user preferences with evaluation results

[1483] 1. The server obtains the user's preference information and product evaluation results from the database.

[1484] 2. The server uses SQL or NoSQL queries to match the user's preferences with the product ratings.

[1485] 3. The server generates the optimal product list and stores it in the database.

[1486] Input: User preference information, product evaluation results

[1487] Data Calculation: Matching by SQL or NoSQL queries

[1488] Output: A list of the best products stored in a database

[1489] Step 4: Recommend the best product

[1490] 1. The server sends the optimal product list to the user's device.

[1491] 2. The device displays a list of products to the user and provides a purchase button.

[1492] 3. When the user clicks the purchase button, the device begins the purchase process.

[1493] Input: Optimal product list

[1494] Data processing: Displaying product list, starting purchase procedure

[1495] Output: List of products shown to user, start of checkout process

[1496] Step 5: Recognizing user emotions with the emotion engine

[1497] 1. The user uses the device to input text, voice, and recognize facial expressions.

[1498] 2. The device transmits the input emotion information to the server.

[1499] 3. The server uses the emotion engine to analyze the user's emotions.

[1500] 4. The server stores the analysis results in a database.

[1501] Input: User emotion information (text input, voice input, facial expression recognition)

[1502] Data Computation: Sentiment Analysis with Emotion Engine

[1503] Output: Sentiment analysis results stored in a database

[1504] Step 6: Emotion-based product recommendations

[1505] 1. The server recognizes that the user is tired based on the analysis results of the emotion engine.

[1506] 2. The server compares the user's preference information and selects products that are highly nutritious and effective in recovering from fatigue.

[1507] 3. The server sends the selected product to the user's device.

[1508] 4. The terminal displays the products to the user and assists in the purchase process.

[1509] Input: Sentiment analysis results, user preference information

[1510] Data calculation: Matching preference information with emotion analysis results and selecting optimal products

[1511] Output: The best products displayed to the user, and assistance with the purchase process

[1512] (Application example 1)

[1513] Next, a description will be given of Application Example 1 of Form 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".

[1514] Conventional food delivery systems generally suggest products that take into account the user's preferences and allergy information, but do not suggest products that take into account the user's emotional state. As a result, there is a problem that the system cannot suggest optimal products when the user is tired or in a specific emotional state, and it is not possible to sufficiently increase user satisfaction.

[1515] 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.

[1516] In this invention, the server includes a means for utilizing AI for various evaluations and judgments such as product ingredient analysis, monitor evaluations, and product design, a means for matching the results of the evaluations and judgments with the user's preregistered preferences, a means for suggesting products based on the matching results, a system including a mechanism for allowing the user to purchase the suggested products if they are on sale, and a means for suggesting products based on the user's emotional state using an emotion engine that recognizes the user's emotions. This makes it possible to suggest optimal products that take into account not only the user's preferences and allergy information, but also their emotional state.

[1517] "Ingredient analysis" refers to analyzing information such as a product's nutritional components and allergens.

[1518] "Monitor evaluation" refers to the collection and analysis of product evaluations by users and testers.

[1519] "Product design" refers to evaluating the product's appearance and packaging design.

[1520] "Means of utilizing AI" refers to the use of artificial intelligence technology to analyze data and make evaluations and judgments.

[1521] "Preferences" refers to information about personal preferences, such as the user's favorite ingredients, seasonings, and allergy information.

[1522] A "matching means" is a means for comparing a user's preferences with the product evaluation results and selecting the most suitable product.

[1523] The "means of suggestion" refers to a means of presenting the most suitable product to the user based on the matching results.

[1524] An "emotion engine" is a technology that recognizes emotions from a user's facial expressions, voice, text input, etc.

[1525] "Emotional state" refers to a user's current mood or psychological state.

[1526] A "mechanism for enabling purchases" is a system that allows users to complete the purchase procedure on the spot if the suggested product is on sale.

[1527] The following system configuration is used as an embodiment of the present invention: The system proposes optimal food delivery items based on the user's preference information and emotional state.

[1528] System Configuration

[1529] Hardware

[1530] Smartphone: A device that allows users to input preference information and emotional state.

[1531] Server: A central processing unit for analyzing data and making product suggestions.

[1532] software

[1533] EmotionEngine: An emotion recognition library for recognizing user emotions.

[1534] FoodRecommendationEngine: A recommendation engine to suggest optimal products based on user preference information and emotional state.

[1535] Data processing and calculation

[1536] Registration of user preferences

[1537] Users use their smartphones to input their preferences (favorite ingredients, allergies, and preferred seasonings). This information is stored in JSON format on the server.

[1538] Emotion recognition

[1539] When a user inputs text, voice, or facial expressions into their smartphone, EmotionEngine analyzes them and recognizes the user's emotional state. For example, if a user inputs "I'm very tired today," EmotionEngine will recognize this as "fatigue."

[1540] Food delivery product proposals

[1541] The server uses the FoodRecommendationEngine to suggest optimal food delivery items based on the user's preference information and the user's recognized emotional state. For example, if the user is tired, nutritious items that are effective in recovering from fatigue (such as vitamin-rich salads and protein shakes) are suggested.

[1542] Examples

[1543] Registration of user preferences

[1544] The user opens the smartphone app and enters the following:

[1545] Favorite ingredients: Chicken, rice

[1546] Disliked food: Fish

[1547] Allergies: Nuts

[1548] Favorite seasoning: Spicy

[1549] Emotion recognition

[1550] A user types the text "I'm very tired today" into their smartphone. EmotionEngine recognizes this as "fatigue."

[1551] Food delivery product proposals

[1552] The server generates the following prompt sentence based on the user's preference information and emotional state:

[1553] "We will suggest food delivery options for you. Please wait a moment."

[1554] The FoodRecommendationEngine suggests products that are nutritious and effective in relieving fatigue, such as "vitamin-rich salads" and "protein shakes."

[1555] In this way, a system can be realized that suggests optimal food delivery items based on the user's preferences and emotional state.

[1556] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1557] Step 1:

[1558] Users use their smartphones to input their own preference information. Specifically, they input their favorite ingredients, disliked ingredients, allergy information, preferred seasonings, etc. The input data is sent to the server in JSON format and saved. The input data is saved on the server as the user's preference information.

[1559] Step 2:

[1560] A user uses a smartphone device to input their current emotional state. For example, they input the text "I'm very tired today." This input data is sent to the server and analyzed by EmotionEngine. EmotionEngine analyzes the input text data and recognizes the user's emotional state as "fatigue." The output data is saved on the server as the user's emotional state.

[1561] Step 3:

[1562] The server uses the FoodRecommendationEngine to suggest optimal food delivery items based on the stored user preference information and emotional state. Specifically, the server passes the preference information (favorite ingredients, disliked ingredients, allergy information, preferred seasoning) and emotional state (fatigue) as input data to the FoodRecommendationEngine. The FoodRecommendationEngine analyzes this data and outputs optimal items (for example, vitamin-rich salads or protein shakes).

[1563] Step 4:

[1564] The server proposes the optimal products output from the FoodRecommendationEngine to the user. Specifically, it sends a notification to the smartphone terminal and displays the products proposed to the user. The user can check the proposed products and choose whether or not to purchase them. The output data is the product information proposed to the user.

[1565] Step 5:

[1566] When the user wishes to purchase a suggested product, the user completes the purchase procedure using a smartphone terminal. The server accepts the purchase procedure and sends the order to the food delivery service. Specifically, the server sends the user's purchase information (product name, quantity, delivery address, etc.) to the food delivery service and confirms the order. The output data is the confirmed order information.

[1567] In this way, a system can be realized that suggests optimal food delivery items based on the user's preferences and emotional state and then carries out the purchase process.

[1568] Example 2

[1569] Next, a second embodiment of the second form will be described. 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".

[1570] Conventional systems did not adequately suggest products based on the user's preferences, making it difficult to increase user satisfaction. In addition, product suggestions did not take into account the user's emotional state, making it difficult to stimulate the user's desire to purchase. Furthermore, it was difficult to properly analyze information on product ingredients and allergens and provide it to users.

[1571] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1572] In this invention, the server includes a means for receiving and storing user preference data, a means for collecting and analyzing product ingredient data, a means for comparing the user preference data with the product ingredient data and evaluating the product, a means for suggesting products based on the evaluation result, a means for making the suggested product available for purchase if it is on sale, a means for recording the user's evaluation data and emotion data, and a means for utilizing the recorded data for the next suggestion. This enables highly accurate product suggestions based on the user's preferences, and increases user satisfaction. Furthermore, product suggestions that take into account the user's emotional state can stimulate the user's purchasing desire. Furthermore, it becomes possible to appropriately analyze product ingredient information and allergen information and provide them to the user.

[1573] "User Preference Data" means information regarding a User's personal preferences, such as the foods the User prefers, ingredients the User wishes to avoid, and allergy information.

[1574] "Ingredient data" refers to specific ingredient information for a product, such as the product's nutritional components, allergens, and main ingredients.

[1575] "Evaluation" is the process of comparing the user's preference data with product ingredient data to select products that are suitable for the user.

[1576] "Product suggestion" refers to the act of presenting products suitable for a user based on the results of the evaluation judgment.

[1577] "Emotional Data" is information that records the emotional state a user felt when rating a product.

[1578] "Means for making a product available for purchase" refers to a mechanism that allows a user to purchase a product on the spot if the suggested product is on sale.

[1579] "Means of utilizing recorded data for next proposals" refers to a system that reflects the user's past evaluation data and emotional data in the next product proposal.

[1580] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1581] The present invention is a system for analyzing the ingredients of products based on user preference data and proposing suitable products. A specific embodiment of this system will be described below.

[1582] Server Roles

[1583] The server receives and stores the user's preference data. The preference data entered by the user through the terminal (e.g. "I like fish," "I don't like spicy food," "I have no allergies") is sent to the server and stored in a database. MySQL, PostgreSQL, or similar databases are used as the database.

[1584] Next, the server collects and analyzes the product's ingredient data. The ingredient data includes the product's nutritional content and allergens. The collected data is analyzed using AI models such as TensorFlow and PyTorch. As a result of the analysis, characteristics such as "mainly contains fish" and "does not contain spicy ingredients" are extracted.

[1585] The server compares the user's preference data with the product's ingredient data and makes an evaluation decision. It uses an SQL query to compare the data and selects products that match the user's preferences. Based on the evaluation results, it generates a list of products to suggest to the user and sends it to the terminal.

[1586] In addition, the server records the user's evaluation data and emotion data. When a user evaluates a product, the server receives the emotion data (e.g., "This chocolate is delicious!", an emotion of joy) along with the evaluation and records it in the database. The recorded data will be used for the next proposal.

[1587] Terminal Roles

[1588] The terminal provides an interface for the user to input preference data. A front-end framework such as React or Vue.js is used to display a form for the user to input the preference data. The input data is sent to the server using an HTTP request (e.g., POST request).

[1589] The terminal displays the product suggestion list sent from the server to the user. The product suggestion list is displayed in HTML format, and the user can check the suggested products.

[1590] The terminal also provides an interface for users to rate products. When users input emotion data along with their ratings, the data is sent to the server.

[1591] User Roles

[1592] The user inputs preference data through the terminal interface. For example, "I like fish," "I don't like spicy food," "I have no allergies," etc. The input data is sent to the server.

[1593] The user checks the product suggestion list displayed on the terminal, and if the suggested product is on sale, the user can purchase it on the spot.

[1594] The user rates the proposed products and inputs emotion data along with the rating, for example, "This salmon sashimi is delicious!" The input data is sent to the server.

[1595] Examples of concrete examples and prompts

[1596] As a specific example, if a user registers preferences such as "I like fish," "I don't like spicy food," and "I have no allergies," the server uses an AI model to analyze the ingredients of the product and evaluates and judges products that "are mainly made of fish" and "do not contain spicy ingredients." For example, the server might suggest "salmon sashimi" or "fried white fish." If the user evaluates the product as "This salmon sashimi is delicious!", the server also records the emotion of joy. The next time, a product that is likely to evoke a similar emotion of joy for the user (for example, "tuna sashimi") will be suggested.

[1597] An example of a prompt sentence is as follows:

[1598] "Based on the user's preference data (e.g., likes fish, dislikes spicy food, no allergies), please use an AI model to analyze the ingredients of the products and suggest products that suit the user. Also, please record the user's evaluation and their emotional state at the time, and use them for the next suggestion."

[1599] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1600] Program processing flow

[1601] Step 1: Enter and submit your preferences

[1602] Subject: User

[1603] The user inputs preference data through the terminal interface, such as "I like fish," "I don't like spicy food," and "I have no allergies." The input data is then sent to the server via an HTTP POST request.

[1604] Input: User preference data

[1605] Output: Preference data sent to the server

[1606] Step 2: Receiving and storing preference data

[1607] Subject: Server

[1608] The server receives the preference data sent by the user. The received data is stored in a database (e.g., MySQL or PostgreSQL). The stored data is used for later processing.

[1609] Input: Preference data submitted by the user

[1610] Output: Preference data stored in a database

[1611] Step 3: Collect and analyze product ingredient data

[1612] Subject: Server

[1613] The server collects product ingredient data. The collected data is input into an AI model (e.g., TensorFlow or PyTorch) and ingredient analysis is performed. As a result of the analysis, characteristics such as "mainly contains fish" and "does not contain spicy ingredients" are extracted.

[1614] Input: Product ingredient data

[1615] Output: Analyzed component data (feature extraction results)

[1616] Step 4: Matching preference data with ingredient data and evaluating

[1617] Subject: Server

[1618] The server compares the user's preference data stored in the database with the analyzed product ingredient data, and uses SQL queries to compare the data and evaluate and determine products that match the user's preferences.

[1619] Input: User preference data, analyzed ingredient data

[1620] Output: Evaluation result (list of products suitable for the user)

[1621] Step 5: Generate and submit product proposals

[1622] Subject: Server

[1623] The server generates a list of products to be proposed to the user based on the evaluation results, and sends the generated list of products to the terminal via an HTTP response.

[1624] Input: Evaluation result

[1625] Output: Product suggestions list sent to the terminal

[1626] Step 6: View product suggestions

[1627] Subject: Terminal

[1628] The terminal displays the product suggestion list sent from the server to the user. The product suggestion list is displayed in HTML format, and the user can check the suggested products.

[1629] Input: Product suggestions list sent from the server

[1630] Output: A list of product suggestions displayed to the user

[1631] Step 7: Enter and submit product ratings and sentiment data

[1632] Subject: User

[1633] The user rates the proposed products and inputs emotional data along with the rating, for example, "This salmon sashimi is delicious!" The input data is sent to the server via an HTTP POST request.

[1634] Input: User rating and sentiment data

[1635] Output: Rating and sentiment data sent to the server

[1636] Step 8: Receive and record rating and emotion data

[1637] Subject: Server

[1638] The server receives the evaluation data and emotion data sent by the user. The received data is recorded in a database. The recorded data is used for the next proposal.

[1639] Input: User-submitted rating and sentiment data

[1640] Output: Evaluation data and emotion data recorded in a database

[1641] Step 9: Use data to improve your next proposal

[1642] Subject: Server

[1643] The server analyzes the recorded evaluation data and emotion data and uses it to suggest products for the next time. For example, if a user evaluates "This salmon sashimi is delicious!", the server will suggest products that are likely to evoke a similar emotion of joy, such as "tuna sashimi."

[1644] Input: Recorded rating and emotion data

[1645] Output: Data used for the next proposal

[1646] (Application example 2)

[1647] Next, a description will be given of Application Example 2 of Form 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".

[1648] Conventional product recommendation systems can take into account the user's preferences and allergy information, but they do not consider the user's emotional state when making product recommendations. This makes it difficult to make product recommendations that recreate the joy and satisfaction that the user felt in the past. In addition, food delivery services lack the ability to suggest optimal dishes and foods based on the user's preferences and emotional state. This makes it difficult to increase user satisfaction.

[1649] 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.

[1650] In this invention, the server includes a means for utilizing AI for various evaluations and judgments such as product ingredient analysis, monitor evaluations, and product design, a means for matching the results of the evaluations and judgments with the user's preregistered preferences, a means for suggesting products based on the matching results, a means including a mechanism for allowing the user to purchase the suggested products if they are on sale, a means for recording the user's emotional state and suggesting products based on the emotional state, and a means for suggesting optimal dishes and foods based on the user's preferences and emotional state. This makes it possible to suggest optimal products and dishes based on the user's preferences and emotional state, thereby increasing user satisfaction.

[1651] "Ingredient analysis" is the process of analyzing the ingredients of a product and identifying their contents.

[1652] "Evaluation and judgment" is the process of using AI to evaluate the quality and characteristics of a product and judging the results.

[1653] "Preferences" refer to specific ingredients or characteristics that a user prefers.

[1654] "Matching" is the process of comparing a user's preferences with the results of their evaluation judgment and identifying matching products.

[1655] "Product suggestion" is the process of presenting the most suitable products to the user based on the matching results.

[1656] "Emotional state" refers to the feelings such as pleasure, satisfaction, and discomfort that users have when evaluating a product.

[1657] "Cuisine" refers to food made by cooking ingredients.

[1658] "Food" refers to ingredients or dishes offered for consumption by a consumer.

[1659] "Food delivery" is a service that delivers dishes or food ordered by users to a specified location.

[1660] The system for implementing the present invention proposes optimal products and dishes based on the preferences and emotional state of a user. A specific embodiment of this system will be described below.

[1661] System Configuration

[1662] The system mainly consists of a server, a user terminal, and a database. The server performs product ingredient analysis, evaluation judgment, preference matching, product suggestions, and recording and analysis of emotional states. User terminals include smartphones, smart glasses, head-mounted displays, etc., and provide an interface for users to input preferences and emotional states. The database stores product ingredient information, user preference data, and emotional state data.

[1663] Program Processing

[1664] The server performs the following process.

[1665] 1. Ingredient analysis: The server analyzes the ingredient information of the product and identifies its contents. Specifically, to obtain information on the product's nutritional content, allergens, etc., the server retrieves the necessary data from the database and analyzes it using an AI model.

[1666] 2. Evaluation judgment: The server uses AI to evaluate the quality and characteristics of the product and judges the result. The evaluation judgment also takes into account the user's past purchase history and evaluation history.

[1667] 3. Taste matching: The server compares the taste data registered by the user in advance with the results of the evaluation judgment and identifies matching products. This allows the server to select products that match the user's tastes.

[1668] 4. Product Suggestion: The server recommends the best products to the user based on the matching results. If the suggested products are on sale, the user can purchase them on the spot.

[1669] 5. Recording and analyzing emotional states: The server records the emotional states felt by the user when rating products and analyzes the data, which makes it possible to suggest products based on the user's emotional state.

[1670] Hardware and Software Used

[1671] Hardware: Servers, smartphones, smart glasses, head-mounted displays

[1672] Software: AI models (e.g. TensorFlow, PyTorch), database management systems (e.g. MySQL, PostgreSQL)

[1673] Examples

[1674] For example, if a user registers preferences such as "I like fish," "I don't like spicy food," and "I have no allergies," and in the past recorded the emotion of "happiness" when rating "salmon sushi," the system will suggest "salmon sushi" and also display the user's emotional state at the time.

[1675] Examples of prompt statements

[1676] Please register user preference data. Example: {"likes": ["fish"], "dislikes": ["spicy food"], "allergies": []}

[1677] Enter your product data. Example: [{"name": "Salmon Sushi", "ingredients": "Fish, Rice, Seaweed", "spicy": False}, {"name": "Spicy Ramen", "ingredients": "Noodles, Chili Pepper, Pork", "spicy": True}]

[1678] Enter user emotion data. Example: {"Salmon sushi": "Happy", "Spicy ramen": "Unhappy"}

[1679] In this way, a system can be realized that suggests optimal products and dishes based on the user's preferences and emotional state.

[1680] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1681] Step 1:

[1682] A user inputs preference data using a terminal.

[1683] Input: User preference data (e.g. "I like fish," "I don't like spicy food," "I have no allergies")

[1684] Output: The preference data is sent to the server and stored in a database.

[1685] Specific operation: The user inputs preference data through the terminal interface and presses the send button. The terminal sends this data to the server, which then stores it in the database.

[1686] Step 2:

[1687] The server retrieves the product's ingredient data from the database and performs ingredient analysis.

[1688] Input: Product ingredient data (e.g. "Salmon sushi: fish, rice, seaweed" "Spicy ramen: noodles, chili pepper, pork")

[1689] Output: Component analysis results (e.g. "Salmon sushi: contains fish as the main component" "Spicy ramen: contains spicy components")

[1690] Specific operation: The server retrieves the product's ingredient data from the database and performs ingredient analysis using the AI ​​model. The analysis results are temporarily stored in memory.

[1691] Step 3:

[1692] The server matches the preference data with the results of component analysis.

[1693] Input: preference data, component analysis results

[1694] Output: Matching results (e.g. "Salmon sushi is good" "Spicy ramen is not good")

[1695] Specific operation: The server compares the preference data with the results of the component analysis and identifies products that match the user's preferences. The matching results are temporarily stored in memory.

[1696] Step 4:

[1697] The server suggests products based on the matching results.

[1698] Input: Matching results

[1699] Output: Suggested items (e.g. "Salmon Sushi")

[1700] Specific operation: Based on the matching results, the server selects the most suitable products for the user and generates a list of suggested products. This list is sent to the terminal.

[1701] Step 5:

[1702] The user uses the terminal to rate the proposed products and input his / her emotional state.

[1703] Input: User's rating and emotional state (e.g. "Salmon sushi: Delicious! Delighted")

[1704] Output: The rating data and emotional state data are sent to the server and stored in a database.

[1705] Specific operation: The user evaluates the proposed products through the terminal interface and inputs his / her emotional state at that time. The terminal transmits this data to the server, which stores it in a database.

[1706] Step 6:

[1707] The server analyzes the emotional state data and uses it for the next suggestion.

[1708] Input: Rating data and emotional state data

[1709] Output: Analysis results (e.g. "Salmon sushi brings joy to the user")

[1710] How it works: The server analyzes the evaluation data and emotional state data, and uses an AI model to learn patterns to use in the next recommendation. The analysis results are stored in a database.

[1711] In this way, a system is realized that suggests optimal products and dishes based on the user's preferences and emotional state.

[1712] 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 voice indicating a user input for 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.

[1713] 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> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[1714] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1715] 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.

[1716] [Fourth embodiment]

[1717] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1718] 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.

[1719] 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 wide area network (WAN) and / or a local area network (LAN).

[1720] 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. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1721] 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 the voice according to instructions from the processor 46.

[1722] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[1723] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1724] The control target 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, legs, etc. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, legs, etc. 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.

[1725] Fig. 8 shows an example of 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.

[1726] 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.

[1727] 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.

[1728] In the robot 414, 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.

[1729] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1730] "Example 1"

[1731] In one embodiment of the present invention, a user registers their preferences in the system. These preferences include various information related to food, such as favorite ingredients, allergy information, and preferred seasonings. The system then uses AI to evaluate and judge the product's ingredients, monitor evaluations, product design, and other aspects. This evaluation takes into account various information related to the product, such as the product's nutritional content, allergens, appearance, and taste. The system then matches the user's preferences with the results of the evaluation and judgement, and suggests the most suitable product for the user. If the suggested product is on sale, the user can purchase it on the spot.

[1732] "Example 2"

[1733] As a specific example, let's say a user registers preferences such as "I like fish," "I don't like spicy food," and "I have no allergies." The system uses AI to analyze the ingredients of products and evaluates products that "have fish as a main ingredient" and "don't contain spicy ingredients." The system then matches this information and suggests products to the user that "have fish as a main ingredient and don't contain spicy ingredients." If the suggested products are on sale, the user can purchase them on the spot.

[1734] The process flow of each embodiment will be described below.

[1735] "Example 1"

[1736] Step 1: The user registers their preferences in the system. These preferences include various information about food, such as favorite ingredients, allergy information, and preferred seasonings.

[1737] Step 2: The system uses AI to evaluate and judge the product's ingredients, monitor evaluation, product design, etc. This evaluation takes into account various information about the product, such as the product's nutritional content, allergens, appearance, taste, etc.

[1738] Step 3: The system matches the user's preferences with the evaluation results and suggests the most suitable products for the user.

[1739] Step 4: If the suggested product is available for sale, the user can purchase it on the spot.

[1740] "Example 2"

[1741] Step 1: The user registers their preferences, such as "I like fish," "I don't like spicy food," or "I have no allergies."

[1742] Step 2: The system uses AI to analyze the product's ingredients and evaluates the product as "containing fish as the main ingredient" and "not containing spicy ingredients."

[1743] Step 3: The system matches this information and suggests products to the user that are "fish-based and do not contain spicy ingredients."

[1744] Step 4: If the suggested product is available for sale, the user can purchase it on the spot.

[1745] Example 1

[1746] Next, a description will be given of Example 1 of the embodiment 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".

[1747] Conventional systems have difficulty in proposing optimal products based on users' preferences, and also do not adequately consider product ingredients and allergy information. As a result, it is difficult for users to find products that suit their preferences and health conditions.

[1748] 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.

[1749] In this invention, the server includes a means for a user to input his / her preference information, a means for collecting product ingredient data, a means for performing ingredient analysis and evaluation using AI based on the collected ingredient data, a means for matching the user's preference information with the product evaluation results, a means for suggesting products based on the matching results, and a means for allowing the user to purchase the suggested products if they are on sale. This makes it possible to suggest and purchase the most suitable products that match the user's preferences and health condition.

[1750] "User" refers to an individual who uses the system to input their own preference information and receive suggestions of the most suitable products.

[1751] "Preference information" refers to food-related information entered by the user, such as favorite ingredients, allergy information, and preferred seasonings.

[1752] "Ingredient data" refers to detailed information about a product, such as its nutritional content, allergens, appearance, and taste.

[1753] "AI" refers to artificial intelligence, specifically the technology of component analysis and evaluation using machine learning frameworks such as TensorFlow and PyTorch.

[1754] "Ingredient analysis" refers to the process of evaluating nutritional components, allergens, etc. based on a product's ingredient data.

[1755] "Evaluation results" refers to the results of ingredient analysis conducted by AI, and include evaluations of the product's nutritional content, allergens, appearance, taste, etc.

[1756] "Matching" refers to the process of comparing user preference information with product evaluation results and selecting the most suitable product.

[1757] "Suggestion" refers to the act of notifying the user of the most suitable product based on the matching results.

[1758] "Purchase Means" refers to the mechanism by which a User purchases a proposed Product if the Product is on sale.

[1759] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1760] This invention is a system that uses AI to analyze and evaluate the ingredients of products based on user preference information and proposes optimal products. A specific embodiment of this system will be described below.

[1761] Input of user preferences

[1762] Users use a dedicated device or smartphone app to input their own preference information, which includes favorite ingredients, allergy information, preferred seasonings, etc. For example, a user might input "I like tomatoes," "I'm allergic to nuts," and "I like spicy food."

[1763] Collect product data

[1764] The server collects product data through a database or external API. The collected data includes the product's nutritional content, allergens, appearance, taste, etc. For example, the server obtains "ingredients information for product X."

[1765] Product composition analysis and evaluation

[1766] The server uses AI to analyze ingredients and evaluate products based on the collected product data. This AI is built using machine learning frameworks such as TensorFlow and PyTorch. For example, the server might evaluate "Product X contains tomatoes, does not contain nuts, and is spicy."

[1767] Matching user preferences

[1768] The server matches the user's preference information with the evaluation results of the product. For example, the server "compares the preference information of user A with the evaluation results of product X and calculates a matching score."

[1769] Optimal product proposals

[1770] The server proposes products with high matching scores to users. The proposals are made through a dedicated terminal or smartphone app. For example, the server proposes "Product X to User A."

[1771] Purchase of products

[1772] Users can purchase the suggested products through a dedicated device or smartphone app. For example, User A "purchases Product X using a smartphone app."

[1773] Examples

[1774] Example 1: Registering user preferences

[1775] User A registers in the system his favorite food ingredient "tomato," his allergy information "nut allergy," and his favorite seasoning "spicy food."

[1776] Example 2: Product composition analysis and evaluation

[1777] The server analyzes the ingredients of product X. Product X contains "tomatoes" and no nuts. It also has a spicy flavor. The server uses TensorFlow to evaluate this information and decides whether it matches the preferences of user A.

[1778] Example 3: Matching and Suggestions

[1779] The server matches the preference information of User A with the evaluation result of Product X and proposes Product X to User A. User A can purchase Product X through a smartphone app.

[1780] Examples of prompt statements

[1781] "Please explain the system that uses AI to analyze and evaluate the ingredients of products based on user preference information and recommend the most suitable products. Please also specify the names of specific hardware and software."

[1782] By feeding this prompt into a generative AI model, a detailed explanation of the system can be obtained.

[1783] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1784] Step 1:

[1785] Users input their own preference information using a dedicated device or smartphone app. The input preference information includes favorite ingredients, allergy information, and preferred seasonings. For example, a user might input "I like tomatoes," "I'm allergic to nuts," and "I like spicy food." The input data is sent to the server and saved in a database.

[1786] Step 2:

[1787] The server collects product data through a database or external API. The collected data includes the product's nutritional content, allergens, appearance, and taste. For example, the server obtains "ingredients information for product X." The obtained data is stored in a database.

[1788] Step 3:

[1789] The server uses AI to analyze ingredients and perform evaluation based on the collected product data. This AI is built using machine learning frameworks such as TensorFlow and PyTorch. For example, the server evaluates "Product X contains tomatoes and no nuts. It is seasoned with hot sauce." The input is the product data, and the output is the evaluation result.

[1790] Step 4:

[1791] The server matches the user's preference information with the product evaluation results. For example, the server "compares the preference information of user A with the evaluation results of product X and calculates a matching score." The input is the user's preference information and the product evaluation results, and the output is the matching score.

[1792] Step 5:

[1793] The server proposes products with high matching scores to users. Suggestions are made through dedicated terminals or smartphone apps. For example, the server "proposes product X to user A." The input is the matching score, and the output is information about the proposed product.

[1794] Step 6:

[1795] The user can purchase the suggested product through a dedicated terminal or smartphone app. For example, user A "purchases product X using a smartphone app." The input is the information about the suggested product, and the output is a notification of purchase completion.

[1796] (Application example 1)

[1797] Next, a description will be given of Application Example 1 of Form 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".

[1798] Conventional food delivery services have had the problem that it is difficult to suggest optimal dishes that take into account the user's preferences and allergy information. In addition, users have to check many menus to find a dish that suits them, which is time-consuming and labor-intensive.

[1799] The identification process by the identification processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means. In this invention, the server includes a means for utilizing AI for various evaluations and judgments such as component analysis of products, monitor evaluations, and product design, a means for matching the results of the evaluations and judgments with the user's preferences registered in advance, a means for suggesting products based on the matching results, a system including a mechanism for allowing the user to purchase the suggested products if they are on sale, a means for registering user preference information, analyzing the menu of a food delivery service, and suggesting the most suitable dish, and a means for ordering the suggested dish on the spot. This makes it possible to suggest the most suitable dish taking into account the user's preferences and allergy information, and allows the user to easily find and order the dish that suits him or her.

[1800] "Product ingredient analysis" refers to obtaining and analyzing information about a product's nutritional components, allergens, etc.

[1801] "Monitor evaluation" refers to the collection and analysis of product evaluations by users and experts.

[1802] "Product design" refers to evaluating the product's appearance and packaging design.

[1803] "Means of utilizing AI" refers to the use of artificial intelligence to analyze data and make evaluations and judgments.

[1804] "My preferences" refers to information such as favorite ingredients, disliked ingredients, allergy information, and preferred seasonings that are registered in advance by the user.

[1805] The "evaluation result" refers to the evaluation conducted by AI based on the product's ingredient analysis, monitor evaluation, product design, etc.

[1806] A "matching means" is a means of comparing the user's preferences with the results of the evaluation judgment and selecting the most suitable product.

[1807] The "means for suggesting products" refers to a means for presenting the most suitable products to the user based on the matching results.

[1808] A "mechanism for enabling purchase" is a mechanism that allows users to purchase a suggested product on the spot if the product is on sale.

[1809] "User preference information" refers to information registered by the user, such as favorite ingredients, disliked ingredients, allergy information, and preferred seasonings.

[1810] A "food delivery service menu" is a list of dishes offered by a food delivery service.

[1811] The "means for suggesting the most suitable dish" refers to a means for analyzing a user's preference information and the menu of a food delivery service, and selecting and suggesting the most suitable dish to the user.

[1812] An "instant ordering solution" is a solution that allows a user to instantly order a suggested dish.

[1813] The system for implementing this invention registers user preference information, analyzes the menu of food delivery services, and suggests the most suitable dishes. The system is realized using the following hardware and software.

[1814] Hardware

[1815] Smartphone: A device that allows users to register their preferences and view and order suggested dishes.

[1816] Server: A device for running AI models and analyzing data.

[1817] software

[1818] Python: A programming language used for data analysis and running AI models.

[1819] scikit-learn: A machine learning library for data vectorization and similarity calculations.

[1820] requests: An HTTP library for retrieving menu information from food delivery service APIs.

[1821] Processing flow

[1822] 1. Registration of user preferences

[1823] Users register their preferences (favorite ingredients, disliked ingredients, allergy information, preferred seasonings, etc.) through a smartphone application. This information is sent to the server and stored in a database.

[1824] 2. Get menu information

[1825] The server uses the requests library to retrieve the latest menu information from the food delivery service's API, including product descriptions and ingredient information.

[1826] 3. Component analysis and evaluation

[1827] The server uses scikit-learn to convert the menu descriptions into TF-IDF vectors, compare them with the user's preference information, and calculate the cosine similarity, thereby identifying the dish that best matches the user's preference.

[1828] 4. Food suggestions

[1829] The server then suggests the best dishes to the user based on the calculated similarity, and the suggested dishes are notified to the user via a smartphone application.

[1830] 5. Order Execution

[1831] Users can review the suggested dishes and place their order on the spot, and the order information is sent to a food delivery service, which then delivers the food to the user.

[1832] Examples

[1833] For example, if a user registered the following preferences:

[1834] User Preferences:

[1835] Favorite ingredients: Chicken, Tomato

[1836] Disliked food: Peanuts

[1837] Allergies: Nuts

[1838] Favorite seasoning: Spicy

[1839] If a food delivery service's menu includes the following:

[1840] Food delivery service menu:

[1841] 1. Chicken Curry: Spicy chicken curry in a tomato-based sauce.

[1842] 2. Peanut Sauce Salad: Salad made with peanut sauce.

[1843] 3. Tomato pasta: Pasta with tomato sauce.

[1844] The system will analyze the user's preferences and menu information and make the following suggestions:

[1845] Recommended dishes:

[1846] 1. Chicken Curry: Spicy chicken curry in a tomato-based sauce.

[1847] 2. Tomato pasta: Pasta with tomato sauce.

[1848] In this way, users can easily find and order dishes that suit their tastes.

[1849] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1850] Step 1:

[1851] The user inputs his / her preference information (favorite ingredients, disliked ingredients, allergy information, preferred seasoning, etc.) through a smartphone application. The input preference information is sent from the smartphone to the server and stored in a database. The input for this step is the user's preference information, and the output is the preference information stored on the server.

[1852] Step 2:

[1853] The server uses the requests library to get the latest menu information from the food delivery service's API. The menu information includes product descriptions and ingredient information. The input of this step is the API request, and the output is the menu information.

[1854] Step 3:

[1855] The server uses scikit-learn to vectorize the menu descriptions using TF-IDF. Specifically, each menu description is converted into a numerical vector based on the frequency of occurrence of words. The input for this step is the menu description, and the output is the vectorized menu information.

[1856] Step 4:

[1857] The server vectorizes the user's preference information and compares it with the menu information to calculate the cosine similarity. Specifically, the user's preference information is expressed as a vector, and the cosine similarity is calculated between the vector of each menu. The input of this step is the vectorized user's preference information and menu information, and the output is the similarity score with each menu.

[1858] Step 5:

[1859] The server selects the best dishes for the user based on the calculated similarity score, taking into account allergy information and excluding dishes that contain allergens. The inputs of this step are the similarity score and allergy information, and the output is a list of dishes to suggest to the user.

[1860] Step 6:

[1861] The server sends the list of suggested dishes to the smartphone application, through which the user can review the suggested dishes. The input of this step is the list of suggested dishes, and the output is the list of dishes displayed in the smartphone application.

[1862] Step 7:

[1863] The user can review the proposed dishes and place an order on the spot. The order information is sent from the smartphone to the server, which then forwards it to the food delivery service. The input of this step is the user's order information, and the output is the order information sent to the food delivery service.

[1864] In this way, users can easily find and order dishes that suit their tastes.

[1865] Example 2

[1866] Next, a second embodiment of the second embodiment will be described. 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".

[1867] In conventional systems, it was difficult to efficiently match user preference information with product ingredient information, and it was not possible to suggest the most suitable products to users. In addition, there was a lack of means to analyze product ingredient information in detail and find products that match the user's preferences. Furthermore, there was an insufficient mechanism to check whether the suggested products were on sale and to smoothly carry out the purchasing procedure.

[1868] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1869] In this invention, the server includes a means for a user to input preference information using a terminal, a means for transmitting the input preference information to the server and storing it in a database, a means for collecting product ingredient information and analyzing the ingredient information using a generative AI model, a means for matching the user's preference information with the product ingredient information, a means for suggesting products based on the matching results, and a means for allowing the user to purchase the suggested products if they are on sale. This makes it possible to efficiently find products that match the user's preferences and smoothly carry out the purchase procedure if the suggested products are on sale.

[1870] "User" means an individual or group that uses the system to input preference information and receive product suggestions.

[1871] A "terminal" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[1872] "Preference information" is personal data entered by the user, such as their preferences or allergy information.

[1873] A "server" is a computer system that receives preference information sent by a user, stores it in a database, and analyzes product ingredient information.

[1874] A "database" is a data management system in which a server stores preference information and product ingredient information.

[1875] "Product ingredient information" is detailed information about a product, such as its nutritional components and allergens.

[1876] A "generative AI model" is an artificial intelligence model used to analyze product ingredient information and match it with user preference information.

[1877] "Matching" is the process of comparing a user's preference information with product ingredient information to find products that meet the conditions.

[1878] "Suggestion" refers to the act of presenting products suitable for the user based on the matching results.

[1879] A "checkout" is a series of operations and processes that a user performs to purchase a suggested product.

[1880] The present invention is a system for suggesting optimal products based on user preference information and supporting the purchase procedure. A specific embodiment of this system will be described below.

[1881] First, the user inputs preference information using a terminal. The terminal is an electronic device such as a smartphone, tablet, or computer. The user starts a dedicated application and inputs preference information. For example, the user inputs information such as "I like fish," "I don't like spicy food," and "I have no allergies."

[1882] Next, the terminal transmits the input preference information to a server. The server stores the received preference information in a database. The database is a data management system for managing the preference information and the ingredient information of the product. For example, a database such as MySQL can be used.

[1883] The server collects product ingredient information. The product ingredient information is detailed information such as the product's nutritional content and allergens. The server provides an API for scanning product barcodes. The user scans the product's barcode using the device's camera, and the device sends the scanned barcode information to the server. The server obtains the product's ingredient information based on the barcode information.

[1884] Next, the server uses a generative AI model to analyze the collected product ingredient information. The generative AI model uses, for example, OpenAI's GPT-4. The server sends the following prompt to the generative AI model:

[1885] Product ingredient information: Contains fish as the main ingredient and does not contain any spicy ingredients.

[1886] Rate this product and decide whether to recommend it to your users.

[1887] The generative AI model analyzes the ingredient information and returns the evaluation results to the server. The server matches the user's preference information with the product's ingredient information based on the evaluation results from the generative AI model. For example, it lists products that match conditions such as "I like fish" or "I don't like spicy food."

[1888] The server generates a list of matching products and sends it to the terminal, which displays the suggestions to the user, for example, displaying a message such as "We found a product that is fish-based and does not contain spicy ingredients."

[1889] The user uses the terminal to check the proposed products. If he / she wishes to purchase the product, he / she clicks the "Purchase" button on the terminal. The server provides an interface to support the purchase procedure and processes the payment. For example, it displays a form for entering credit card information.

[1890] In this way, products that match the user's preferences can be efficiently found, and if the suggested product is on sale, the user can smoothly complete the purchase procedure.

[1891] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1892] Step 1:

[1893] The user inputs preference information using the terminal.

[1894] Specific operations: The user launches a dedicated application and enters information such as "I like fish," "I don't like spicy food," and "I have no allergies" into a preference input form.

[1895] Input: User preference information

[1896] Output: Preference information entered into the device

[1897] Step 2:

[1898] The terminal transmits the input preference information to the server.

[1899] Specific operation: When the user clicks the "Send" button, the device sends...

Claims

1. Means for receiving and storing user preference data; A means for collecting and analyzing product ingredient data; means for determining an emotional state of a user using an emotion engine; means for generating a prompt sentence for instructing the generation of a list of product suggestions that match the user's preferences and emotional state based on the user's preference data, the component data of the product, and the user's emotional state; A means for generating a list of product suggestions that match the user's preferences using the generated prompt sentence and a generation AI model; means for presenting the generated suggestion list to the user; and if the suggested product is on sale, means for enabling operations related to a purchase procedure.

2. The system according to claim 1 , wherein the means for collecting and analyzing the ingredient data of the product identifies at least one of information on nutritional components and allergens of the product based on the ingredient data.

3. A means for storing at least one of a purchase history and a rating history of a user, The system of claim 1 , wherein the means for generating a prompt sentence generates a prompt sentence that instructs the generation of a suggested list of products that match at least one of the user's purchase history and evaluation history, the user's preferences, and the user's emotional state, based on at least one of the user's purchase history and evaluation history, the user's preference data, the product ingredient data, and the user's emotional state.

Images