system

Abstract

Provide a system. 【Solution means】Means for collecting purchase history data from users, Means for collecting inventory data of users, Means for collecting advertisements, coupon information, and inventory data from partner merchants, Means for integrating the purchase history data and inventory data and analyzing the user's preferences and past purchase patterns, Means for collating the user's inventory data with the partner merchant's inventory data to identify out-of-stock ingredients, Means for generating a meal menu considering the user's preferences and nutritional balance, Means for proposing the ingredients to be purchased and the stores where they are to be purchased, Means for notifying the user of the proposal results, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003] [[ID=??]]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Recently, the burden on consumers in managing food ingredients and deciding on meal menus has been increasing, and there is a problem that it is difficult to ensure a nutritional balance. Also, in food manufacturers and retailers, the lack of effective marketing methods and the increase in food loss have become management issues. In such a situation, there is a demand for a system that allows consumers to easily manage their own purchase history and inventory information, purchase food ingredients efficiently, and have a nutritionally balanced meal.

Means for Solving the Problems

[0005] This invention relates to a system that collects user purchase history data and inventory data, and obtains advertisements, coupon information, and inventory data from partner merchants. Specifically, the following means are used. It should be noted that there seems to be a typo in the original text where "[[ID=??]]" is present. This should be corrected to a proper ID if available in the original source.

[0006] 1. Provide a means for the user to input or scan purchase history data.

[0007] 2. Provide a means for users to input or record their household inventory.

[0008] 3. Provide means to obtain advertising, coupon information, and inventory data from partner companies.

[0009] 4. To provide a means of integrating purchase history data and inventory data to analyze user preferences and past purchasing patterns.

[0010] 5. Provide a means to identify out-of-stock ingredients by comparing user inventory data with partner supplier inventory data.

[0011] 6. Provide a means for generating meal menus that take into account the user's preferences and nutritional balance.

[0012] 7. Provide a means to suggest ingredients to purchase and the stores where they can be purchased, taking into account advertisements and coupons.

[0013] 8. Provide a means to notify the user of the proposal results.

[0014] This allows users to easily obtain nutritionally balanced meal menus, enables partner businesses to achieve efficient targeted advertising, and contributes to reducing food waste.

[0015] "Purchase history data" refers to data that records information about products a user has purchased in the past.

[0016] "Inventory data" refers to data that records information about the types and quantities of goods currently stored in the user's home.

[0017] The "cooperating vendor" refers to food manufacturers and retailers who provide advertising information, coupon information, and inventory data in cooperation with the system.

[0018] "Advertising information" refers to the promotional information of products provided by cooperating vendors.

[0019] "Coupon information" refers to information for using discounts and benefits for specific products or services.

[0020] "Means for collecting inventory data" refers to methods or devices for inputting or recording the user's current inventory information and storing it in a database.

[0021] "Means for integrating data" refers to methods or devices for summarizing different types of data and centrally managing them as an overall dataset.

[0022] "Means for analyzing the user's preferences and past purchase patterns" refers to methods or devices for analyzing the user's purchase history and other related data to identify the user's preferences and behavior patterns.

[0023] "Means for identifying out-of-stock ingredients" refers to methods or devices for comparing the user's current inventory with the required ingredient list to find out the missing ingredients.

[0024] "Means for generating meal menus" refers to methods or devices for automatically creating proposed meal menus considering the user's preferences and nutritional balance.

[0025] "Means for proposing the ingredients to be purchased and their purchase stores" refers to methods or devices for proposing to the user based on the optimal store information for purchasing specific ingredients and the coupon information of cooperating vendors.

[0026] "Means for notifying the user of the proposal results" refers to methods or devices for sending the proposal content generated by the system to the user's device for notification.

Brief Description of the Drawings

[0027] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0028] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0029] First, let's explain the terminology used in the following explanation.

[0030] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0031] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0032] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0033] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0034] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0035] [First Embodiment]

[0036] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0037] As shown in Figure 1, the 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.

[0038] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0039] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0040] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0041] 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 perceptible to the user 20 (e.g., audio 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 audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0042] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0043] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0044] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0045] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0046] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0047] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0048] Embodiments of this invention relate to a system that collects user purchase history data and inventory data, and obtains advertising, coupon information, and inventory data from partner companies. Details are described below.

[0049] System Configuration

[0050] 1. User terminal

[0051] User terminals include devices such as smartphones, tablets, and personal computers, which users can use to input purchase history, record inventory data, and receive suggestions from the system.

[0052] 2. Server

[0053] The server is a central system that integrates and analyzes data, generates menus, creates suggestions, and notifies users. The database works in conjunction with it, managing information from users and data from partner companies.

[0054] 3. Partner companies

[0055] Partners include food manufacturers and retailers, who provide advertising, coupon information, and inventory data to the server.

[0056] Program Processing Description

[0057] 1. Data Collection

[0058] Users enter or scan their purchase history via a smartphone app or web portal. This data includes details such as date, product name, and store of purchase.

[0059] Users can record their household inventory by taking photos of ingredients with their smartphone camera or manually entering text.

[0060] The terminal sends the purchase history data and inventory data entered by the user to the server via an API.

[0061] 2. Acquisition of external data

[0062] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. This data includes product discounts, special offers, and in-store inventory status.

[0063] The server organizes the acquired data and stores it in the database.

[0064] 3. Data Integration and Analysis

[0065] The server integrates and centrally manages purchase history data and inventory data collected for each user.

[0066] The server uses machine learning algorithms to analyze the user's past purchasing patterns and food consumption rate.

[0067] The server compares the user's current inventory data with the inventory data of partner suppliers to identify out-of-stock ingredients.

[0068] 4. Menu and store suggestions

[0069] The server generates the optimal meal menu considering the user's preferences and nutritional balance. For example, for a user who has frequently consumed tomatoes and chicken in the past, it will suggest "tomato and chicken pasta."

[0070] The server suggests the most suitable store to purchase ingredients the user is lacking (e.g., chicken). In doing so, it considers any coupons or special offers provided to select the store that is most advantageous to the user.

[0071] The server sends the generated menu and purchase store information to the user's terminal via the API.

[0072] 5. Notification of Results and Purchase Information

[0073] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include meal menus, lists of necessary ingredients, stores where to buy them, and available coupon information.

[0074] The user checks the notification and purchases the necessary ingredients from the suggested store.

[0075] Specific example

[0076] 1. Data collection:

[0077] User A enters their recent purchase history of tomatoes and chicken through a smartphone app.

[0078] The device sends information to the server indicating that there are tomatoes in the household inventory but no chicken.

[0079] 2. Obtaining external data:

[0080] The server retrieves coupon information for "30% off chicken" and inventory data from retailer B via API.

[0081] 3. Data Integration and Analysis:

[0082] The server identifies from past usage history that user A prefers to use tomatoes and chicken, and analyzes that there is currently a shortage of chicken.

[0083] 4. Menu and store suggestions:

[0084] The server generates a menu for "Tomato and Chicken Pasta" and suggests purchasing chicken from retailer B.

[0085] The server will show that you can get a 30% discount by using a coupon from retailer B.

[0086] 5. Notification of results and purchase information:

[0087] The terminal notifies user A of the menu and coupon information for "Tomato and Chicken Pasta".

[0088] User A checks the notification, buys chicken from retailer B, and creates a menu.

[0089] In this way, users can efficiently manage ingredients and easily prepare nutritionally balanced meals. Furthermore, partner businesses can effectively deploy targeted advertising and contribute to reducing food waste.

[0090] The following describes the processing flow.

[0091] Step 1:

[0092] Users log in to their accounts via a smartphone app or web portal.

[0093] Step 2:

[0094] Users can manually enter their purchase history or scan loyalty cards or receipts from partner retailers. This involves entering or scanning details such as product name, purchase date, price, and store location.

[0095] Step 3:

[0096] The device sends the entered or scanned purchase history data to the server via an API.

[0097] Step 4:

[0098] Users can record their household inventory by taking photos of ingredients with their smartphone camera or by manually entering text.

[0099] Step 5:

[0100] The terminal sends recorded inventory data to the server via an API. The data includes information such as the type and quantity of ingredients and their expiration dates.

[0101] Step 6:

[0102] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. The retrieved data includes product sale information and inventory status.

[0103] Step 7:

[0104] The server integrates user-specific purchase history and inventory data and stores it in a database. This stored data is used for later analysis.

[0105] Step 8:

[0106] The server uses machine learning algorithms to analyze the user's past purchasing patterns and food consumption rate. In this process, it identifies the user's preferences and frequently purchased items.

[0107] Step 9:

[0108] The server compares the user's current inventory data with the inventory data of partner suppliers to identify out-of-stock ingredients. For example, it might identify a situation where tomatoes are in stock but chicken is in short supply.

[0109] Step 10:

[0110] The server automatically generates meal menus, taking into account the user's preferences and nutritional balance. For example, it might suggest "tomato and chicken pasta" to a user who has previously enjoyed tomatoes and chicken.

[0111] Step 11:

[0112] The server suggests purchasing the missing ingredient (in this case, chicken) from the most suitable retailer. It considers coupon information from partner suppliers to select the most advantageous purchase location for the user. For example, it might say, "A 30% off coupon for chicken is available at Retailer B."

[0113] Step 12:

[0114] The server sends the generated menu and purchase store information to the user's terminal via API.

[0115] Step 13:

[0116] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include suggested menus, a list of necessary ingredients, store locations, and available coupon information.

[0117] Step 14:

[0118] The user checks the notification and purchases any missing ingredients to create the suggested menu. For example, the user purchases chicken from retailer B.

[0119] Step 15:

[0120] After a purchase, the user updates the inventory status in the app and sends that information back to the server. This ensures that the latest inventory information is reflected in the next offer.

[0121] This allows users to easily create nutritionally balanced meal plans, partner businesses to conduct effective targeted advertising, and contribute to reducing food waste.

[0122] (Example 1)

[0123] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0124] Traditionally, it has been difficult for users to manage their household ingredients while preparing nutritionally balanced meals. Furthermore, partner companies have faced challenges in effectively advertising based on user purchasing patterns, making food waste reduction a significant issue. A system was needed to solve these problems, improving user convenience and enhancing the marketing effectiveness of partner companies.

[0125] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0126] In this invention, the server includes means for analyzing purchase history data and inventory data using machine learning algorithms, means for identifying out-of-stock ingredients, and means for suggesting the optimal store for purchase and transmitting that information to the user terminal via an API. This streamlines the user's ingredient management and enables the suggestion of nutritionally balanced meals. Furthermore, partner companies can effectively deploy targeted advertising and contribute to reducing food waste.

[0127] "Purchase history data" refers to data containing information about products that a user has purchased in the past. Specifically, it includes details such as product name, store of purchase, and purchase date.

[0128] "Inventory data" refers to data containing information about the food and products currently in a household. Specifically, it includes details such as the name of the food item, the quantity, and its storage condition.

[0129] "Partner companies" refer to external companies and stores that provide advertising, coupon information, and inventory data in conjunction with the system.

[0130] "Advertising" refers to promotional information for products and services provided by partner companies.

[0131] "Coupon information" refers to information about discounts and benefits offered by partner companies.

[0132] A "machine learning algorithm" refers to computational techniques used to analyze data and find patterns and trends.

[0133] An "API" refers to an interface used to exchange functions between different software programs.

[0134] "Push notification" refers to a function that instantly sends information from the server to the user's device.

[0135] A "database" refers to a system for efficiently storing, searching, and managing large amounts of data.

[0136] "Centralized management" refers to the integrated management of different types of data in a single database or system.

[0137] "Preferences" refer to a user's tastes and preferences. Specifically, this includes the user's preferences for ingredients and products derived from past purchase data.

[0138] "Nutritional balance" refers to a state where the food a user consumes contains the necessary nutrients in appropriate amounts.

[0139] "Meal menu" refers to a list of meal recipes and dishes suggested to the user.

[0140] "Purchase store" refers to the store suggested to the user for purchasing ingredients or other products.

[0141] Embodiments of this invention relate to a system that collects user purchase history data and inventory data, and analyzes this data in combination with advertisements, coupon information, and inventory data from partner companies. This system enables users to manage their household inventory and receive suggestions for nutritionally balanced meal menus.

[0142] System Configuration

[0143] 1. User terminal

[0144] User terminals include devices such as smartphones, tablets, and personal computers. Users can use these devices to input purchase history, record inventory data, and receive suggestions from the system.

[0145] 2. Server

[0146] The server is a central system that integrates and analyzes data, generates menus, creates suggestions, and notifies users. The database works in conjunction with it, managing information from users and data from partner companies.

[0147] 3. Partner companies

[0148] Partners include food manufacturers and retailers, who provide advertising, coupon information, and inventory data to the server.

[0149] Hardware and software to be used

[0150] Hardware: Smartphones, tablets, PCs, servers, network infrastructure

[0151] Software: Smartphone apps, web portals, databases (e.g., MySQL®, PostgreSQL), APIs, machine learning algorithms (e.g., Python's Scikit-learn, TENSORFLOW®)

[0152] Data processing and calculations

[0153] Data collection

[0154] Users enter their purchase history through a smartphone app or web portal. This data includes details such as the date, product name, and store of purchase.

[0155] Users record their household inventory by taking photos of ingredients with their smartphone camera or manually entering text.

[0156] The device sends this purchase history data and inventory data to the server via an API.

[0157] Retrieving external data

[0158] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. This data includes product discounts, special offers, and in-store inventory status.

[0159] The server organizes the acquired data and stores it in the database.

[0160] Data Integration and Analysis

[0161] The server integrates and centrally manages purchase history data and inventory data collected for each user.

[0162] The server uses machine learning algorithms to analyze the user's past purchasing patterns and food consumption rate.

[0163] The server compares the user's current inventory data with that of partner suppliers to identify out-of-stock ingredients.

[0164] Menu and store suggestions

[0165] The server generates the optimal meal menu considering the user's preferences and nutritional balance. For example, for a user who frequently consumes tomatoes and chicken, it will suggest "tomato and chicken pasta."

[0166] The server suggests the most suitable store to purchase any ingredients the user is lacking. In doing so, it selects the store that is most advantageous to the user, taking into account any coupons or special offers provided.

[0167] The server sends the generated menu and purchase store information to the user's terminal via an API.

[0168] Notification of results and purchase information

[0169] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include meal menus, lists of necessary ingredients, stores where to buy them, and available coupon information.

[0170] The user checks the notification and purchases the necessary ingredients from the suggested store.

[0171] Specific example

[0172] 1. Data collection:

[0173] User A enters their recent purchase history of tomatoes and chicken through a smartphone app.

[0174] The device sends information to the server indicating that there are tomatoes in the household inventory but no chicken.

[0175] 2. Obtaining external data:

[0176] The server retrieves coupon information for "30% off chicken" and inventory data from retail stores.

[0177] 3. Data Integration and Analysis:

[0178] The server identifies from past usage history that user A prefers to use tomatoes and chicken, and analyzes that there is currently a shortage of chicken.

[0179] 4. Menu and store suggestions:

[0180] The server generates a menu for "Tomato and Chicken Pasta" and suggests purchasing chicken from a retail store.

[0181] The server will show that you can get 30% off by using a retail coupon.

[0182] 5. Notification of results and purchase information:

[0183] The terminal notifies user A of the menu and coupon information for "Tomato and Chicken Pasta".

[0184] User A checks the notification, buys chicken from a retail store, and creates a menu.

[0185] In this way, this system helps users efficiently manage ingredients and easily prepare nutritionally balanced meals. Furthermore, partner businesses can effectively deploy targeted advertising and contribute to reducing food waste.

[0186] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0187] Step 1: Enter the user's purchase history.

[0188] The user launches a smartphone app or web portal and enters their purchase history. For example, they might use the app's barcode scanning function to enter purchase information for tomatoes and chicken.

[0189] Input: Product name, store of purchase, date of purchase

[0190] The device temporarily stores this purchase history data in storage and sends it to the server via an API.

[0191] Output: Purchase history data is sent to the server.

[0192] Step 2: Record household inventory

[0193] The user uses their smartphone camera to take a picture of the food items currently in their household inventory. For example, they might take a picture of tomatoes in their refrigerator.

[0194] Input: Photo of the ingredient, or manually entered name of the ingredient.

[0195] The terminal sends this inventory data to the server via an API.

[0196] Output: Inventory data is sent to the server.

[0197] Step 3: Obtain data from partner companies

[0198] The server periodically sends requests to partner vendors via API to retrieve the latest advertisements, coupon information, and inventory data.

[0199] Input: API request from partner company

[0200] The server retrieves, for example, coupon information for "30% off chicken" and inventory data from partner suppliers.

[0201] Output: Advertisements, coupon information, and inventory data from partner companies are stored on the server.

[0202] Step 4: Data Integration and Processing

[0203] The server performs a join operation to integrate the purchase history data and inventory data collected for each user. For example, it might combine a user's past purchase data and current inventory data into a single table.

[0204] Input: Purchase history data, inventory data

[0205] The server stores integrated data in a database and manages it centrally.

[0206] Output: Integrated purchase history data and inventory data

[0207] Step 5: Data Analysis

[0208] The server uses machine learning algorithms to analyze users' past purchasing patterns and food consumption rates. For example, it analyzes users' purchase history as time-series data to analyze trends in food consumption over certain periods.

[0209] Input: Integrated purchase history data, inventory data

[0210] The server compares the user's current inventory data with that of its partners to identify any out-of-stock ingredients. For example, the server might identify that chicken is currently in short supply.

[0211] Output: Analysis results of ingredient shortage information, purchasing patterns, and consumption speed.

[0212] Step 6: Menu Generation

[0213] The server generates the optimal meal menu considering the user's preferences and nutritional balance. For example, for a user who has frequently consumed tomatoes and chicken in the past, it will suggest "tomato and chicken pasta."

[0214] Input: User preference data, nutritional balance information, out-of-stock information

[0215] The server saves the generated meal menu to a database.

[0216] Output: Optimal meal plan

[0217] Step 7: Suggestion of a store to purchase from

[0218] The server suggests the most suitable store to purchase ingredients the user is lacking. For example, store selection is made considering coupon information and special offers. In this process, information such as a 30% discount on chicken at a retail store will be reflected.

[0219] Input: Out-of-stock information, advertisements and coupon information from partner companies

[0220] The server stores purchase information in a database and sends it to the user's terminal via an API.

[0221] Output: Optimal store information

[0222] Step 8: Notification of Results

[0223] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include meal menus, lists of necessary ingredients, stores where to buy them, and available coupon information. For example, it might notify the user of a "Tomato and Chicken Pasta" menu and coupon information.

[0224] Input: Suggestion results (menu, ingredient list, store where to buy, coupon information)

[0225] Output: Notification content to the user

[0226] Through these steps, users can efficiently manage ingredients and easily prepare nutritionally balanced meals. Furthermore, partner businesses can effectively deploy targeted advertising and contribute to reducing food waste.

[0227] (Application Example 1)

[0228] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0229] In recent years, there has been a growing demand for systems that suggest optimal products and services based on user purchasing behavior and inventory management. However, conventional systems have not adequately provided personalized recommendations tailored to user needs, and the use of coupons and special offers has been limited. Furthermore, there has been a lack of means to centrally manage and effectively analyze purchase history and inventory data. As a result, users have not been able to obtain the optimal purchasing experience, and companies have faced challenges in effective targeting.

[0230] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0231] In this invention, the server includes means for collecting purchase history data from users, means for collecting user inventory data, means for collecting advertisements, coupon information, and inventory data from partner companies, means for integrating the purchase history data and inventory data to analyze user preferences and past purchasing patterns, means for comparing user inventory data with partner company inventory data to identify out-of-stock items, means for generating meal recommendation menus considering user preferences and nutritional balance, means for recommending items to purchase and suggesting stores where to purchase them, and means for sending push notifications to users based on the suggested data. As a result, users can efficiently manage their purchase history and inventory data and receive recommendations for optimal products and menus. Furthermore, companies can implement effective targeted advertising and coupon distribution, leading to improved purchasing experiences and increased sales.

[0232] - A "user" is an individual or group that uses the system to provide purchase history data and inventory data, and receives suggestions for the most suitable products and menus.

[0233] "Purchase history data" refers to detailed information about products and services that a user has purchased in the past, and often includes information such as the date, product name, and store where the purchase was made.

[0234] "Inventory data" refers to information about the current quantity and types of goods and materials owned by households, businesses, etc.

[0235] "Partner companies" refer to companies such as food manufacturers and retailers that provide advertising, coupon information, and inventory data to the system.

[0236] "Advertising" refers to information provided by partner companies for the purpose of promoting the sale of goods or services.

[0237] "Coupon information" refers to information that indicates the right or conditions for purchasing specific products or services at a discounted price.

[0238] A "server" refers to a central system that integrates and analyzes data, generates menus, creates suggestions, and notifies users, and is a computer system that works in conjunction with a database.

[0239] "Push notifications" refer to a function that automatically sends information to smartphones and other devices even when the user does not have the application open.

[0240] "Recommended menu" refers to meal suggestions generated by the server, taking into account the user's preferences and nutritional balance.

[0241] "Purchase location" refers to a specific retail store or online store suggested to the user for purchasing an out-of-stock item.

[0242] "Targeted advertising" refers to advertisements that are customized for specific user groups based on their interests and past behavior.

[0243] An "API" refers to an interface for exchanging data between different software systems, and is used, for example, to send data from a user terminal to a server or to retrieve data from a partner company.

[0244] Modes for carrying out the invention

[0245] Embodiments of this invention are systems that collect user purchase history data and inventory data, and retrieve advertisements, coupon information, and inventory data provided by partner companies. The following details how this system works.

[0246] System Configuration

[0247] 1. User terminal

[0248] User terminals include devices such as smartphones, tablets, and personal computers, which users can use to input purchase history, record inventory data, receive system suggestions, and check push notifications.

[0249] 2. Server

[0250] The server is the central management system at the heart of this system. The server is linked to a database that receives purchase history data and inventory data from users, as well as advertisements, coupon information, and inventory data from partner companies, and then integrates, analyzes, and generates recommendations.

[0251] 3. Partner companies

[0252] Partner companies, such as food manufacturers and retailers, provide advertising, coupon information, and inventory data to the server.

[0253] Program processing

[0254] Data collection

[0255] Users enter their purchase history and record their household inventory through a smartphone app or web portal. Purchase history data includes details such as date, product name, and store of purchase, while inventory data includes the types and quantities of products they have at home. This data is sent to the server via an API.

[0256] Retrieving external data

[0257] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via APIs. This data is organized and stored in the server's database and integrated with user purchase history data and inventory data.

[0258] Data Integration and Analysis

[0259] The server uses integrated data to build machine learning models and analyze user preferences and past purchasing patterns. This allows it to predict what products users currently need and what products they are likely to purchase in the future. Furthermore, it cross-references this data with inventory data provided by partner suppliers to identify out-of-stock items.

[0260] Suggestions for meal menus and stores where to purchase them.

[0261] Based on the analysis results, the server generates meal recommendations that take into account the user's preferences and nutritional balance. For example, for a user who has frequently consumed tomatoes and chicken in the past, it will suggest "Tomato and Chicken Pasta." It will also suggest stores where users can purchase any missing ingredients (e.g., chicken) based on the recommended recipe. At this time, it will consider any provided coupons or special offers to select the store that is most advantageous to the user.

[0262] Notification of results

[0263] The user's device will notify them of the suggestions via push notifications or in-app messages. The notifications will include recommended meal menus, a list of necessary ingredients, suggested stores for purchase, and available coupon information. Users can review these notifications, purchase items at the recommended stores, and create the suggested menu.

[0264] Hardware and software to be used

[0265] Hardware: Smartphones (iOS, Android®), tablets, PCs, servers (including cloud-based databases).

[0266] Software: Python (used for data collection and analysis), Requests (HTTP library), JSON (data format), machine learning frameworks (e.g., TensorFlow and Scikit-learn).

[0267] Specific example

[0268] 1. User A enters their recent purchase history of tomatoes and chicken into a smartphone app.

[0269] 2. The terminal sends information to the server indicating that there are tomatoes in the household inventory but no chicken.

[0270] 3. The server retrieves coupon information for "30% off chicken" and inventory data from retailers via API.

[0271] 4. The server identifies from past usage history that user A prefers to use tomatoes and chicken, and analyzes that there is currently a shortage of chicken.

[0272] 5. The server generates a menu for "Tomato and Chicken Pasta" and suggests purchasing chicken from a retail store. The suggestion also includes discount information if a coupon is used.

[0273] 6. The terminal notifies user A of the menu and coupon information for "Tomato and Chicken Pasta".

[0274] 7. User A checks the notification, buys chicken from a retail store, and creates a menu.

[0275] Example of a prompt

[0276] Enter the following prompt into the generative AI model:

[0277] Based on the user's purchase history data and inventory data, please suggest the most suitable products and menus for that user. Please also consider the latest coupon information obtained from partner companies. Please use the following history data and inventory data.

[0278] Purchase history data: Tomatoes, chicken

[0279] Inventory data: Tomatoes: 2, Chicken: 0

[0280] Coupon Information: Chicken: 30% off

[0281] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0282] Step 1:

[0283] The user inputs or scans purchase history data using a smartphone app. For example, when purchasing tomatoes and chicken, the date, product name, and details of the store where the purchase was made are entered. The input data is sent to the server through an API.

[0284] Input: Purchase history data (e.g., tomatoes, chicken), date, store where purchased

[0285] Output: Data sent to the server through an API

[0286] Step 2:

[0287] The user records the inventory data in the home using a smartphone. For example, when there are 2 tomatoes and 0 chickens in stock, take a photo of them or enter the data by text input. This is also sent to the server through an API.

[0288] Input: Inventory data (e.g., tomatoes: 2, chicken: 0)

[0289] Output: Data sent to the server through an API

[0290] Step 3:

[0291] The server periodically obtains advertisements, coupon information, and inventory data from partner merchants using an API. For example, it includes coupon information of "30% off for chicken" and the inventory status. This data is stored in the server's database.

[0292] Input: Advertisements, coupon information, inventory data from partner merchants

[0293] Output: Data stored in the database on the server

[0294] Step 4:

[0295] The server integrates purchase history data, inventory data, and data from partner suppliers, and uses machine learning models to analyze user preferences and past purchasing patterns. This allows it to predict what products users currently need and what products they may purchase in the future.

[0296] Input: Purchase history data, inventory data, advertisements and coupon information from partner companies.

[0297] Output: Analysis results based on user preferences and purchasing patterns

[0298] Step 5:

[0299] The server checks inventory data and identifies out-of-stock items. For example, it might detect that the chicken inventory is zero. Based on this information, it generates recommended menu items.

[0300] Input: Integrated data, inventory data

[0301] Output: Out-of-stock items and recommended menu items

[0302] Step 6:

[0303] The server suggests the best store to purchase recommended meals and any missing items from the user. It also takes into account coupons and special offers provided by partner companies.

[0304] Input: Out-of-stock items, coupon information from partner companies

[0305] Output: Recommended menu items and suggested stores for purchase.

[0306] Step 7:

[0307] The terminal presents the recommended menu and purchase store information from the server to the user through push notifications. The notification content includes the recommended meal menu, the required ingredient list, the proposed purchase store, and available coupon information.

[0308] Input: Recommended menu and purchase store information from the server

[0309] Output: Push notification to the user

[0310] By executing the above processing steps in sequence, the user can efficiently manage the purchase history and inventory data and receive proposals for optimal products and menus. In addition, partner merchants can effectively promote their products through targeted advertising and coupon delivery.

[0311] Furthermore, an emotion engine for estimating the user's emotions may be combined. That is, the specific processing unit 290 may estimate the user's emotions using the emotion identification model 59 and perform specific processing using the user's emotions.

[0312] An embodiment of this invention relates to a method for proposing an optimal meal menu based on the user's emotions by combining an emotion engine in a system that collects the user's purchase history data and inventory data and obtains advertisements, coupon information, and inventory data from partner merchants. The details will be described below.

[0313] System Configuration

[0314] 1. User Terminal

[0315] The user terminal is a device such as a smartphone, tablet, or personal computer, and the user can use it to input the purchase history, record inventory data, input emotions using the emotion engine, and receive proposals from the system.

[0316] 2. Server

[0317] The server is a central system that integrates, analyzes, recognizes sentiment, generates menus, creates suggestions, and notifies users. The database works in conjunction with it, managing information from users and data from partner companies.

[0318] 3. Partner companies

[0319] Partners include food manufacturers and retailers, who provide advertising, coupon information, and inventory data to the server.

[0320] 4. Emotional Engine

[0321] An emotion engine is software or hardware that recognizes emotions from a user's facial expressions and voice and generates emotion data. This emotion data reflects the user's current mental state, and menu suggestions are made based on it.

[0322] Program Processing Description

[0323] 1. Data Collection

[0324] Users enter or scan their purchase history via a smartphone app or web portal. This data includes details such as date, product name, and store of purchase.

[0325] Users can record their household inventory by taking photos of ingredients with their smartphone camera or manually entering text.

[0326] The device sends the collected purchase history data and inventory data to the server via an API.

[0327] 2. Acquisition of external data

[0328] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. This data includes product discounts, special offers, and in-store inventory status.

[0329] The server organizes the acquired data and stores it in the database.

[0330] 3. Acquisition of emotional data

[0331] Users register their emotional states through a smartphone app using facial recognition cameras and voice input. The emotion engine recognizes the user's emotions from these inputs and generates emotion data.

[0332] The device sends the generated emotion data to the server via an API.

[0333] 4. Data Integration and Analysis

[0334] The server integrates and centrally manages purchase history, inventory data, and sentiment data.

[0335] The server uses machine learning algorithms to analyze the user's past purchasing patterns, food consumption rate, and emotional data.

[0336] The server compares the user's current inventory data with the inventory data of partner suppliers to identify out-of-stock ingredients.

[0337] 5. Menu and store suggestions

[0338] The server generates an optimal meal plan considering the user's preferences, nutritional balance, and emotional state. For example, if the user is feeling stressed, it will suggest a menu that includes ingredients that help alleviate stress.

[0339] The server suggests the best store to purchase any missing ingredients (e.g., chicken). In doing so, it considers any coupons or special offers provided to select the store that is most advantageous to the user.

[0340] The server sends the generated menu and purchase store information to the user's terminal via API.

[0341] 6. Notification of Results and Purchase Information

[0342] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include suggested menus, a list of necessary ingredients, stores where to purchase them, and available coupon information.

[0343] The user checks the notification and purchases the ingredients needed to make the suggested menu.

[0344] Specific example

[0345] 1. Data collection:

[0346] User A enters their recent purchase history of tomatoes and chicken through a smartphone app.

[0347] The device sends information to the server indicating that there are tomatoes in the household inventory but no chicken.

[0348] 2. Obtaining external data:

[0349] The server retrieves coupon information for "30% off chicken" and inventory data from retailers via API.

[0350] 3. Acquisition of emotional data:

[0351] User A uses the app's facial recognition function to register with the emotion engine that they are feeling stressed.

[0352] The device sends emotional data to the server.

[0353] 4. Data Integration and Analysis:

[0354] The server identifies from past usage history that user A prefers to use tomatoes and chicken, and analyzes that there is currently a shortage of chicken.

[0355] The server takes into account that user A is experiencing stress and includes suggestions for foods that can help alleviate stress.

[0356] 5. Menu and store suggestions:

[0357] The server generates a menu item called "Tomato and Chicken Pasta" and suggests purchasing chicken from a retail store.

[0358] The server displays a coupon from a retail store, offering 30% off chicken.

[0359] 6. Notification of results and purchase information:

[0360] The terminal notifies user A of the menu item "Tomato and Chicken Pasta" and coupon information.

[0361] User A checks the notification, buys chicken at a retail store, and prepares the suggested menu.

[0362] In this way, users can efficiently manage ingredients and easily prepare meals that consider nutritional balance and emotional state. Furthermore, partner businesses can effectively conduct targeted advertising and contribute to reducing food waste.

[0363] The following describes the processing flow.

[0364] Step 1:

[0365] Users log in to their accounts via a smartphone app or web portal.

[0366] Step 2:

[0367] Users can manually enter their purchase history or scan loyalty cards or receipts from partner retailers. This involves entering or scanning details such as product name, purchase date, price, and store location.

[0368] Step 3:

[0369] The device sends the entered or scanned purchase history data to the server via an API.

[0370] Step 4:

[0371] Users can record their household inventory by taking photos of ingredients with their smartphone camera or by manually entering text.

[0372] Step 5:

[0373] The terminal sends recorded inventory data to the server via an API. The data includes information such as the type and quantity of ingredients and their expiration dates.

[0374] Step 6:

[0375] Users register their emotional states (stress, joy, sadness, etc.) with the emotion engine using the app's facial recognition and voice input functions.

[0376] Step 7:

[0377] The emotion engine generates recognized emotion data and sends it to the server.

[0378] Step 8:

[0379] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. The retrieved data includes product sale information and inventory status.

[0380] Step 9:

[0381] The server integrates user-specific purchase history data, inventory data, and sentiment data, and stores it in a database. This data is used for later analysis.

[0382] Step 10:

[0383] The server uses machine learning algorithms to analyze the user's past purchasing patterns, food consumption rate, and emotional data. In doing so, it identifies the user's preferences and frequently purchased items.

[0384] Step 11:

[0385] The server compares the user's current inventory data with the inventory data of partner suppliers to identify out-of-stock ingredients. For example, it might identify a situation where tomatoes are in stock but chicken is in short supply.

[0386] Step 12:

[0387] The server generates meal menus considering the user's preferences, nutritional balance, and emotional state. If the user is stressed, it suggests a menu that includes ingredients that help alleviate stress. For example, if the user is stressed, it might suggest "tomato and chicken pasta."

[0388] Step 13:

[0389] The server suggests purchasing the missing ingredient (in this case, chicken) from the most suitable retailer. It considers coupon information from partner suppliers to select the store that offers the best deal for the user. For example, it might say, "A coupon for 30% off chicken is available at Retailer B."

[0390] Step 14:

[0391] The server sends the generated menu and purchase store information to the user's terminal via API.

[0392] Step 15:

[0393] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include suggested menus, a list of necessary ingredients, store locations, and available coupon information.

[0394] Step 16:

[0395] The user checks the notification and purchases any missing ingredients to create the suggested menu. For example, the user purchases chicken from retailer B.

[0396] Step 17:

[0397] After a purchase, the user updates the inventory status in the app and sends that information back to the server. This ensures that the latest inventory information is reflected in the next offer.

[0398] This system allows users to easily manage available ingredients and obtain optimal meal menus tailored to their emotional state and preferences. Furthermore, partner businesses can enhance the effectiveness of their targeted advertising and contribute to reducing food waste.

[0399] (Example 2)

[0400] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0401] Traditional purchase history and inventory management systems have been unable to make suggestions that take into account the user's emotional state, making it difficult to increase consumer satisfaction. Furthermore, systems that suggest meal menus considering consumer preferences and nutritional balance are limited, making it difficult to support food waste reduction and efficient purchasing behavior. Therefore, there is a need for a system that suggests optimal meal menus that reflect the user's emotional state and effectively promotes the purchase of necessary ingredients.

[0402] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting purchase history data from the user, means for collecting the user's inventory data, means for collecting advertisements, coupon information and inventory data from partner companies, means for acquiring the user's emotional data, means for integrating the purchase history data, inventory data and emotional data to analyze the user's preferences and past purchasing patterns, means for comparing the user's inventory data with the partner company's inventory data to identify out-of-stock ingredients, means for generating meal menus considering the user's preferences, nutritional balance and emotional state, means for suggesting ingredients to be purchased and the stores where they can be purchased, and means for notifying the user of the suggestion results. This makes it possible to suggest optimal meal menus that reflect the user's emotional state and purchasing patterns and to support efficient purchasing behavior.

[0403] "Purchase history data" refers to data containing information about products that a user has purchased in the past. This data includes details such as product name, purchase date and time, store of purchase, and quantity.

[0404] "Inventory data" refers to data containing information about the food and products a user currently owns in their home. This data includes information such as the name of the food item, the quantity, and the expiration date.

[0405] "Advertising" refers to information provided by partner companies to promote specific products or services. This information includes product descriptions, special offers, and promotional details.

[0406] "Coupon information" refers to information that allows you to receive a discount on a specific product or service. This information includes coupon codes, discount rates, terms and conditions, and expiration dates.

[0407] "Partner companies" are businesses such as food manufacturers and retailers that provide data in conjunction with the system.

[0408] "Emotional data" refers to data about a user's emotional state. This data is obtained from the user's facial expressions and voice, and reflects emotional states such as happiness, anxiety, and stress.

[0409] An "emotion engine" is software or hardware that analyzes a user's facial expressions and voice to recognize their emotions and generate emotional data.

[0410] "Data integration" is the process of centrally managing and linking different types of data (such as purchase history data, inventory data, and sentiment data).

[0411] "Data analysis" is the process of analyzing user preferences, past purchasing patterns, food consumption rates, emotional states, and other factors based on integrated data.

[0412] A "meal menu" is a list of recipes and ingredients for creating a specific meal. This list is generated taking into account the user's preferences, nutritional balance, and emotional state.

[0413] "Suggestion results" refer to the suggestions generated by the system, such as meal menus, stores to purchase from, and coupon information.

[0414] A "notification" is an action taken to inform the user of the results of a system suggestion. This includes push notifications, in-app messages, and so on.

[0415] This invention relates to a system that collects user purchase history data, inventory data, advertisements and coupon information from partner companies, and sentiment data, and integrates and analyzes this data to suggest the optimal meal menu based on the user's emotions. The details are described below.

[0416] System Configuration

[0417] 1. User terminal

[0418] User terminals include smartphones, tablets, and personal computers. Using these terminals, users can input purchase history, record inventory data, provide emotional input using an emotion engine, and receive suggestions from the system.

[0419] 2. Server

[0420] The server is a central system that integrates, analyzes, recognizes sentiment, generates menus, creates suggestions, and notifies users. The server is connected to a database that centrally manages user information and data from partner companies.

[0421] 3. Partner companies

[0422] Partner companies include food manufacturers and retailers, and their role is to provide advertising, coupon information, and inventory data to the server.

[0423] 4. Emotional Engine

[0424] An emotion engine is software or hardware that recognizes emotions from a user's facial expressions and voice and generates emotion data. This emotion data reflects the user's mental state, and menu suggestions are made based on it.

[0425] Program Processing Description

[0426] Data collection

[0427] Users input or scan their purchase history through a smartphone app or web portal. For example, scanning a receipt with a smartphone camera allows the app to automatically recognize the date, product name, and store of purchase.

[0428] Users can record their household inventory by taking photos of ingredients with their smartphone camera or manually entering text.

[0429] The device sends the collected purchase history data and inventory data to the server via an API.

[0430] Retrieving external data

[0431] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. This data includes product discounts, special offers, and in-store inventory status.

[0432] The server organizes the acquired data and stores it in the database.

[0433] Acquisition of emotional data

[0434] Users register their emotional states through a smartphone app using facial recognition cameras and voice input. The emotion engine recognizes the user's emotions from these inputs and generates emotion data.

[0435] The device sends the generated emotion data to the server via an API.

[0436] Data Integration and Analysis

[0437] The server integrates and centrally manages purchase history data, inventory data, and sentiment data.

[0438] The server uses machine learning algorithms to analyze the user's past purchasing patterns, food consumption rate, and emotional data.

[0439] The server compares the user's current inventory data with the inventory data of partner suppliers to identify out-of-stock ingredients.

[0440] Menu and store suggestions

[0441] The server generates an optimal meal plan considering the user's preferences, nutritional balance, and emotional state. For example, if the user is feeling stressed, it will suggest a menu that includes ingredients that help alleviate stress.

[0442] The server suggests the best store to purchase any missing ingredients. In doing so, it considers any coupons or special offers provided to select the most beneficial store for the user.

[0443] The server sends the generated menu and purchase store information to the user's terminal via API.

[0444] Notification of results and purchase information

[0445] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include suggested menus, a list of necessary ingredients, stores where to purchase them, and available coupon information.

[0446] The user checks the notification and purchases the ingredients needed to make the suggested menu.

[0447] Specific example

[0448] 1. Data collection:

[0449] User A enters their recent purchase history of tomatoes and chicken into a smartphone app. The app automatically recognizes the product name, date, and store, and digitizes the data.

[0450] The device sends that data to the server.

[0451] 2. Obtaining external data:

[0452] The server retrieves coupon information for "30% off chicken" and inventory data from retailers via API.

[0453] 3. Acquisition of emotional data:

[0454] User A uses the app's facial recognition function to register with the emotion engine that they are feeling stressed.

[0455] The device sends that emotional data to the server.

[0456] 4. Data Integration and Analysis:

[0457] The server identifies from past usage history that user A prefers to use tomatoes and chicken, and analyzes that there is currently a shortage of chicken.

[0458] The server takes into account that user A is experiencing stress and includes suggestions for foods that can help alleviate stress.

[0459] 5. Menu and store suggestions:

[0460] The server generates a menu item called "Tomato and Chicken Pasta" and suggests that the user purchase chicken from a retail store.

[0461] The server displays a coupon from a retail store, offering 30% off chicken.

[0462] 6. Notification of results and purchase information:

[0463] The device notifies user A of the menu item "Tomato and Chicken Pasta" and coupon information.

[0464] User A checks the notification, buys chicken at a retail store, and prepares the suggested menu.

[0465] This processing flow allows users to efficiently manage ingredients and easily receive meal menu suggestions that take nutritional balance and emotional state into consideration. Furthermore, partner companies can effectively implement targeted advertising and contribute to reducing food waste.

[0466] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0467] Step 1: Data Collection

[0468] Users enter their purchase history or scan receipts using a smartphone app. For example, if a user takes a picture of a receipt with their smartphone camera, the app automatically recognizes the date, product name, and store of purchase, and saves this data digitally. This data includes the user ID, product name, quantity, and purchase date.

[0469] Users record their household inventory by taking photos of ingredients with their smartphone camera or manually entering text. This data includes the name of the ingredient, the quantity, and the expiration date.

[0470] The device sends collected purchase history data and inventory data to the server via API. The server stores the received data in a database.

[0471] Step 2: Obtaining external data

[0472] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. This data includes product discounts, special offers, and in-store inventory status.

[0473] The server organizes the acquired external data and stores it in a database. The organized data is then categorized for later analysis and matching.

[0474] Step 3: Acquisition of emotional data

[0475] Users register their emotional states through a smartphone app. For example, by taking a picture of their face with the app's facial recognition camera, the emotion engine analyzes the expression. Alternatively, users can record their emotional states using voice input.

[0476] The emotion engine recognizes the user's emotions from their facial expressions and voice, and generates emotion data such as "happiness," "anxiety," and "stress."

[0477] The device sends the generated emotion data to the server via an API.

[0478] Step 4: Data Integration and Analysis

[0479] The server integrates and centrally manages purchase history data, inventory data, and sentiment data collected from users. This integration process links related data using the user ID as the key.

[0480] The server uses machine learning algorithms to analyze this integrated data. Specifically, it analyzes the user's past purchasing patterns, food consumption rate, and emotional data to predict the user's purchasing behavior and preferences. This analysis results include, for example, the food items the user consumed the most in the past month and the products they purchased the most.

[0481] The server matches the user's current inventory data with that of partner suppliers to identify any ingredients currently lacking in the household. This generates a list of ingredients the user should purchase.

[0482] Step 5: Menu and store suggestions

[0483] The server generates an optimal meal plan considering the user's preferences, nutritional balance, and emotional state. For example, if the user is feeling stressed, a menu including ingredients with relaxing properties will be suggested.

[0484] The server suggests the best stores to purchase any missing ingredients. Based on provided coupons and special offers, it selects the store that will benefit the user the most. For example, it might suggest information such as "Chicken is 30% off at a nearby supermarket."

[0485] The server sends the generated menu and purchase store information to the user's terminal via API.

[0486] Step 6: Notification of results and purchase information

[0487] The device displays suggestions to the user via push notifications and in-app messages. These notifications include suggested menus, a list of necessary ingredients, stores where to purchase them, and available coupon information. Specifically, it might display a recipe for "Tomato and Chicken Pasta" and its required ingredients.

[0488] Users check the notifications and purchase ingredients to create the suggested menu. They use the notified coupon information to purchase the necessary ingredients at their nearest supermarket, thereby reducing costs.

[0489] The above outlines the processing steps of this system. In each step, the user, terminal, and server work together to collect, analyze, and propose data, thereby enabling the suggestion of the optimal meal menu based on the user's emotional state and preferences.

[0490] (Application Example 2)

[0491] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0492] While conventional systems could suggest menus based on user purchase history and inventory data, they failed to consider the user's emotional state. Furthermore, they were inadequate in suggesting which stores to purchase ingredients from if those ingredients were in short supply. This resulted in an inability to suggest meals best suited to the user's mental state and preferences, and also increased the effort required for ingredient purchases.

[0493] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0494] In this invention, the server includes means for collecting purchase history data from users, means for collecting user inventory data, means for collecting advertisements, coupon information and inventory data from partner companies, means for collecting user emotional data, means for integrating the purchase history data, inventory data and emotional data to analyze the user's preferences, past purchase patterns and emotional state, means for comparing the user's inventory data with the partner company's inventory data to identify out-of-stock ingredients, means for generating meal menus considering the user's preferences, nutritional balance and emotional state, means for suggesting ingredients to purchase and where to purchase them, and means for notifying the user of the suggestion results. This makes it possible to suggest an optimal meal menu that takes the user's emotional state into consideration and efficiently guide the user to where to purchase the necessary ingredients.

[0495] "Purchase history data" refers to information about products that a user has purchased in the past, including details such as the date and time, product name, and place of purchase.

[0496] "Inventory data" refers to data showing the current availability of specific food items or products in a user's home or in the stores of partner companies.

[0497] "Advertising" refers to information provided to users for the purpose of promoting the sale of specific products or services offered by partner companies.

[0498] "Coupon information" refers to codes or vouchers issued by partner companies to users to offer discounts or benefits on specific products or services.

[0499] "Emotional data" refers to data that reflects the user's current emotional state, as recognized from their facial expressions and voice.

[0500] "Preference" is a concept that refers to the products, foods, or specific habits and tastes that a user likes.

[0501] "Past purchasing patterns" refer to data that analyzes trends such as the types, frequency, and timing of products that users have purchased in the past.

[0502] "Out-of-stock ingredients" refer to specific ingredients that are not available in the user's home inventory or store inventory, but are necessary for creating a menu.

[0503] "Emotional state" refers to the mental state or mood that a user is currently experiencing, such as stress or happiness.

[0504] "Means for generating menus" refers to a process or system that automatically creates appropriate meal menus, taking into account the user's preferences, nutritional balance, and emotional state.

[0505] "Means of suggesting stores for purchase" refers to a process or system that identifies the best store for a user to purchase the necessary ingredients and presents that information to the user.

[0506] "Means of notifying the results of the proposal" refers to a process or system that provides users with information such as generated menus and purchase options via push notifications or in-app messages.

[0507] The embodiments for carrying out this invention will be described in detail below.

[0508] System Configuration

[0509] 1. User terminal

[0510] User terminals include devices such as smartphones, tablets, and personal computers, which users can use to input purchase history, record inventory data, provide emotional input using an emotion engine, and receive suggestions from the system.

[0511] 2. Server

[0512] The server is the central system responsible for data integration, analysis, sentiment recognition, menu generation, suggestion creation, and user notifications. The database works in conjunction with this server, managing user information and data from partner companies.

[0513] 3. Partner companies

[0514] Partner companies refer to organizations such as food-related businesses and retailers, and these companies provide advertising, coupon information, and inventory data to the server.

[0515] 4. Emotional Engine

[0516] An emotion engine is software or hardware that recognizes emotions from a user's facial expressions and voice and generates emotion data. This emotion data reflects the user's current mental state, and menu suggestions are made based on it.

[0517] Program Processing Description

[0518] Hardware and software to be used

[0519] Hardware: Smartphone (iOS or Android)

[0520] Software: Python, TensorFlow (emotion recognition model), SQLite (database management), RESTful API (data communication)

[0521] 1. Data Collection

[0522] Users input their purchase history and inventory data through a smartphone application. They can also scan product barcodes using their smartphone's camera. The collected data is stored in an SQLite database.

[0523] 2. Acquisition of external data

[0524] The server periodically retrieves advertisements, coupon information, and inventory data from partner servers via a RESTful API and stores this data in an SQLite database.

[0525] 3. Acquisition of emotional data

[0526] When a user opens the app, their facial expressions and voice are analyzed using the smartphone's camera and microphone by an emotion engine (TensorFlow model). The generated emotion data is stored in an SQLite database.

[0527] 4. Data Integration and Analysis

[0528] The server integrates purchase history data, inventory data, and sentiment data stored in an SQLite database, and uses machine learning algorithms to analyze user preferences, past purchasing patterns, and emotional states.

[0529] 5. Menu generation and suggested stores for purchase.

[0530] Based on the analyzed data, the server generates an optimal menu that takes into account the user's preferences, nutritional balance, and emotional state, and identifies the necessary ingredients and where to purchase them. This information is also stored in an SQLite database.

[0531] 6. Notification of Results and Purchase Information

[0532] The generated menu and purchase store information will be sent to the user's device as a push notification or in-app message.

[0533] Specific examples and examples of prompt statement usage

[0534] Specific example

[0535] User B uses their smartphone at a physical store and enters their desire to make "tomato and chicken pasta" into the app.

[0536] The app scans user B's past purchase history and confirms that tomatoes are in stock but chicken is in short supply.

[0537] We retrieve coupon information from our partner suppliers and notify customers that there is a 30% off coupon for chicken.

[0538] Example of a prompt

[0539] "Based on the user's purchase history, please suggest the optimal meal menu that reflects their current emotional state."

[0540] "Use an emotion engine to recognize user emotions and guide them through the grocery purchase process, taking into account current inventory data and coupon information."

[0541] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0542] Step 1:

[0543] Users use a smartphone app to input purchase history and inventory data. Users scan product barcodes using their smartphone camera and enter the information into the app. The input data includes details such as product name, date, purchase location, and quantity. This information is sent from the device to a server and stored in an SQLite database.

[0544] Step 2:

[0545] The server periodically retrieves advertisements, coupon information, and inventory data from partner servers via a RESTful API. The retrieved data includes discount and special offer information, as well as in-store inventory status, transmitted from the partner servers. This data is stored by the server in an SQLite database.

[0546] Step 3:

[0547] The user inputs their emotional data via a smartphone app. The smartphone's camera and microphone are used to analyze facial expressions and voice using an emotion engine (TensorFlow model). The analyzed emotional data reflects the user's current emotional state (e.g., stress, happiness), and is sent from the device to a server and stored in an SQLite database.

[0548] Step 4:

[0549] The server integrates purchase history data, inventory data, and sentiment data stored in an SQLite database. This allows for analysis based on user preferences, past purchasing patterns, and emotional states. Machine learning algorithms are applied using Python scripts to identify specific user preferences and food consumption rates.

[0550] Step 5:

[0551] Based on the analysis results above, the server generates an optimal meal plan that takes into account the user's preferences, nutritional balance, and emotional state. The menu is generated using a Python script, and any missing ingredients are also identified. This missing ingredient information is cross-referenced with inventory data from partner suppliers, and suggestions are generated that include optimal purchasing locations and coupon information.

[0552] Step 6:

[0553] The server sends the generated menu and store information to the user's device. This information includes the suggested menu, a list of required ingredients, the store where to purchase the items, and any available coupons. The user reviews these suggestions within the smartphone app.

[0554] Step 7:

[0555] The user reviews the suggested menu and store information, then visits a physical store to purchase the necessary ingredients. The user uses a smartphone app to manage ingredients according to the suggested menu and refer to recipes. Through these steps, the user's purchasing experience is optimized based on their emotional state.

[0556] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0557] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0558] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0559] [Second Embodiment]

[0560] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0561] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0562] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0563] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0564] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0565] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0566] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0567] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0568] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0569] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0570] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0571] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0572] Embodiments of this invention relate to a system that collects user purchase history data and inventory data, and obtains advertising, coupon information, and inventory data from partner companies. Details are described below.

[0573] System Configuration

[0574] 1. User terminal

[0575] User terminals include devices such as smartphones, tablets, and personal computers, which users can use to input purchase history, record inventory data, and receive suggestions from the system.

[0576] 2. Server

[0577] The server is a central system that integrates and analyzes data, generates menus, creates suggestions, and notifies users. The database works in conjunction with it, managing information from users and data from partner companies.

[0578] 3. Partner companies

[0579] Partners include food manufacturers and retailers, who provide advertising, coupon information, and inventory data to the server.

[0580] Program Processing Description

[0581] 1. Data Collection

[0582] Users enter or scan their purchase history via a smartphone app or web portal. This data includes details such as date, product name, and store of purchase.

[0583] Users can record their household inventory by taking photos of ingredients with their smartphone camera or manually entering text.

[0584] The terminal sends the purchase history data and inventory data entered by the user to the server via an API.

[0585] 2. Acquisition of external data

[0586] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. This data includes product discounts, special offers, and in-store inventory status.

[0587] The server organizes the acquired data and stores it in the database.

[0588] 3. Data Integration and Analysis

[0589] The server integrates and centrally manages purchase history data and inventory data collected for each user.

[0590] The server uses machine learning algorithms to analyze the user's past purchasing patterns and food consumption rate.

[0591] The server compares the user's current inventory data with that of partner suppliers to identify out-of-stock ingredients.

[0592] 4. Menu and store suggestions

[0593] The server generates the optimal meal menu considering the user's preferences and nutritional balance. For example, for a user who has frequently consumed tomatoes and chicken in the past, it will suggest "tomato and chicken pasta."

[0594] The server suggests the most suitable store to purchase ingredients the user is lacking (e.g., chicken). In doing so, it considers any coupons or special offers provided to select the store that is most advantageous to the user.

[0595] The server sends the generated menu and purchase store information to the user's terminal via the API.

[0596] 5. Notification of Results and Purchase Information

[0597] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include meal menus, lists of necessary ingredients, stores where to buy them, and available coupon information.

[0598] The user checks the notification and purchases the necessary ingredients from the suggested store.

[0599] Specific example

[0600] 1. Data collection:

[0601] User A enters their recent purchase history of tomatoes and chicken through a smartphone app.

[0602] The device sends information to the server indicating that there are tomatoes in the household inventory but no chicken.

[0603] 2. Obtaining external data:

[0604] The server retrieves coupon information for "30% off chicken" and inventory data from retailer B via API.

[0605] 3. Data Integration and Analysis:

[0606] The server identifies from past usage history that user A prefers to use tomatoes and chicken, and analyzes that there is currently a shortage of chicken.

[0607] 4. Menu and store suggestions:

[0608] The server generates a menu for "Tomato and Chicken Pasta" and suggests purchasing chicken from retailer B.

[0609] The server will show that you can get a 30% discount by using a coupon from retailer B.

[0610] 5. Notification of results and purchase information:

[0611] The terminal notifies user A of the menu and coupon information for "Tomato and Chicken Pasta".

[0612] User A checks the notification, buys chicken from retailer B, and creates a menu.

[0613] In this way, users can efficiently manage ingredients and easily prepare nutritionally balanced meals. Furthermore, partner companies can effectively deploy targeted advertising and contribute to reducing food waste.

[0614] The following describes the processing flow.

[0615] Step 1:

[0616] Users log in to their accounts via a smartphone app or web portal.

[0617] Step 2:

[0618] Users can manually enter their purchase history or scan loyalty cards or receipts from partner retailers. When doing so, they will enter or scan details such as product name, purchase date, price, and store location.

[0619] Step 3:

[0620] The device sends the entered or scanned purchase history data to the server via an API.

[0621] Step 4:

[0622] Users can record their household inventory by taking photos of ingredients with their smartphone camera or by manually entering text.

[0623] Step 5:

[0624] The terminal sends recorded inventory data to the server via an API. The data includes information such as the type and quantity of ingredients and their expiration dates.

[0625] Step 6:

[0626] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. The retrieved data includes product sale information and inventory status.

[0627] Step 7:

[0628] The server integrates user-specific purchase history and inventory data and stores it in a database. This stored data is used for later analysis.

[0629] Step 8:

[0630] The server uses machine learning algorithms to analyze the user's past purchasing patterns and food consumption rate. In this process, it identifies the user's preferences and frequently purchased items.

[0631] Step 9:

[0632] The server compares the user's current inventory data with the inventory data of partner suppliers to identify out-of-stock ingredients. For example, it might identify a situation where tomatoes are in stock but chicken is in short supply.

[0633] Step 10:

[0634] The server automatically generates meal menus, taking into account the user's preferences and nutritional balance. For example, it might suggest "tomato and chicken pasta" to a user who has previously enjoyed tomatoes and chicken.

[0635] Step 11:

[0636] The server suggests purchasing the missing ingredient (in this case, chicken) from the most suitable retailer. It considers coupon information from partner suppliers to select the most advantageous purchase location for the user. For example, it might say, "A 30% off coupon for chicken is available at Retailer B."

[0637] Step 12:

[0638] The server sends the generated menu and purchase store information to the user's terminal via API.

[0639] Step 13:

[0640] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include suggested menus, a list of necessary ingredients, store locations, and available coupon information.

[0641] Step 14:

[0642] The user checks the notification and purchases any missing ingredients to create the suggested menu. For example, the user purchases chicken from retailer B.

[0643] Step 15:

[0644] After a purchase, the user updates the inventory status in the app and sends that information back to the server. This ensures that the latest inventory information is reflected in the next offer.

[0645] This allows users to easily create nutritionally balanced meal plans, partner businesses to conduct effective targeted advertising, and contribute to reducing food waste.

[0646] (Example 1)

[0647] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0648] Traditionally, it has been difficult for users to manage their household ingredients while preparing nutritionally balanced meals. Furthermore, partner companies have faced challenges in effectively advertising based on user purchasing patterns, making food waste reduction a significant issue. A system was needed to solve these problems, improving user convenience and enhancing the marketing effectiveness of partner companies.

[0649] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0650] In this invention, the server includes means for analyzing purchase history data and inventory data using machine learning algorithms, means for identifying out-of-stock ingredients, and means for suggesting the optimal store for purchase and transmitting that information to the user terminal via an API. This streamlines the user's ingredient management and enables the suggestion of nutritionally balanced meals. Furthermore, partner companies can effectively deploy targeted advertising and contribute to reducing food waste.

[0651] "Purchase history data" refers to data containing information about products that a user has purchased in the past. Specifically, it includes details such as product name, store of purchase, and purchase date.

[0652] "Inventory data" refers to data containing information about the food and products currently in a household. Specifically, it includes details such as the name of the food item, the quantity, and its storage condition.

[0653] "Partner companies" refer to external companies and stores that provide advertising, coupon information, and inventory data in conjunction with the system.

[0654] "Advertising" refers to promotional information for products and services provided by partner companies.

[0655] "Coupon information" refers to information about discounts and benefits offered by partner companies.

[0656] A "machine learning algorithm" refers to computational techniques used to analyze data and find patterns and trends.

[0657] An "API" refers to an interface used to exchange functions between different software programs.

[0658] "Push notification" refers to a function that instantly sends information from the server to the user's device.

[0659] A "database" refers to a system for efficiently storing, searching, and managing large amounts of data.

[0660] "Centralized management" refers to the integrated management of different types of data in a single database or system.

[0661] "Preferences" refer to a user's tastes and preferences. Specifically, this includes the user's preferences for ingredients and products derived from past purchase data.

[0662] "Nutritional balance" refers to a state where the food a user consumes contains the necessary nutrients in appropriate amounts.

[0663] "Meal menu" refers to a list of meal recipes and dishes suggested to the user.

[0664] "Purchase store" refers to the store suggested to the user for purchasing ingredients or other products.

[0665] Embodiments of this invention relate to a system that collects user purchase history data and inventory data, and analyzes this data in combination with advertisements, coupon information, and inventory data from partner companies. This system enables users to manage their household inventory and receive suggestions for nutritionally balanced meal menus.

[0666] System Configuration

[0667] 1. User terminal

[0668] User terminals include devices such as smartphones, tablets, and personal computers. Users can use these devices to input purchase history, record inventory data, and receive suggestions from the system.

[0669] 2. Server

[0670] The server is a central system that integrates and analyzes data, generates menus, creates suggestions, and notifies users. The database works in conjunction with it, managing information from users and data from partner companies.

[0671] 3. Partner companies

[0672] Partners include food manufacturers and retailers, who provide advertising, coupon information, and inventory data to the server.

[0673] Hardware and software to be used

[0674] Hardware: Smartphones, tablets, PCs, servers, network infrastructure

[0675] Software: Smartphone apps, web portals, databases (e.g., MySQL, PostgreSQL), APIs, machine learning algorithms (e.g., Python's Scikit-learn, TensorFlow)

[0676] Data processing and calculations

[0677] Data collection

[0678] Users enter their purchase history through a smartphone app or web portal. This data includes details such as the date, product name, and store of purchase.

[0679] Users record their household inventory by taking photos of ingredients with their smartphone camera or manually entering text.

[0680] The device sends this purchase history data and inventory data to the server via an API.

[0681] Retrieving external data

[0682] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. This data includes product discounts, special offers, and in-store inventory status.

[0683] The server organizes the acquired data and stores it in the database.

[0684] Data Integration and Analysis

[0685] The server integrates and centrally manages purchase history data and inventory data collected for each user.

[0686] The server uses machine learning algorithms to analyze the user's past purchasing patterns and food consumption rate.

[0687] The server compares the user's current inventory data with that of partner suppliers to identify out-of-stock ingredients.

[0688] Menu and store suggestions

[0689] The server generates the optimal meal menu considering the user's preferences and nutritional balance. For example, for a user who frequently consumes tomatoes and chicken, it will suggest "Tomato and Chicken Pasta."

[0690] The server suggests the most suitable store to purchase any ingredients the user is lacking. In doing so, it selects the store that is most advantageous to the user, taking into account any coupons or special offers provided.

[0691] The server sends the generated menu and purchase store information to the user's terminal via an API.

[0692] Notification of results and purchase information

[0693] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include meal menus, lists of necessary ingredients, stores where to buy them, and available coupon information.

[0694] The user checks the notification and purchases the necessary ingredients from the suggested store.

[0695] Specific example

[0696] 1. Data collection:

[0697] User A enters their recent purchase history of tomatoes and chicken through a smartphone app.

[0698] The device sends information to the server indicating that there are tomatoes in the household inventory but no chicken.

[0699] 2. Obtaining external data:

[0700] The server retrieves coupon information for "30% off chicken" and inventory data from retail stores.

[0701] 3. Data Integration and Analysis:

[0702] The server identifies from past usage history that user A prefers to use tomatoes and chicken, and analyzes that there is currently a shortage of chicken.

[0703] 4. Menu and store suggestions:

[0704] The server generates a menu for "Tomato and Chicken Pasta" and suggests purchasing chicken from a retail store.

[0705] The server will show that you can get 30% off by using a retail coupon.

[0706] 5. Notification of results and purchase information:

[0707] The terminal notifies user A of the menu and coupon information for "Tomato and Chicken Pasta".

[0708] User A checks the notification, buys chicken from a retail store, and creates a menu.

[0709] In this way, this system helps users efficiently manage ingredients and easily prepare nutritionally balanced meals. Furthermore, partner businesses can effectively deploy targeted advertising and contribute to reducing food waste.

[0710] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0711] Step 1: Enter the user's purchase history.

[0712] The user launches a smartphone app or web portal and enters their purchase history. For example, they might use the app's barcode scanning function to enter purchase information for tomatoes and chicken.

[0713] Input: Product name, store of purchase, date of purchase

[0714] The device temporarily stores this purchase history data in storage and sends it to the server via an API.

[0715] Output: Purchase history data is sent to the server.

[0716] Step 2: Record household inventory

[0717] The user uses their smartphone camera to take a picture of the food items currently in their household inventory. For example, they might take a picture of tomatoes in their refrigerator.

[0718] Input: Photo of the ingredient, or manually entered name of the ingredient.

[0719] The terminal sends this inventory data to the server via an API.

[0720] Output: Inventory data is sent to the server.

[0721] Step 3: Obtain data from partner companies

[0722] The server periodically sends requests to partner vendors via API to retrieve the latest advertisements, coupon information, and inventory data.

[0723] Input: API request from partner company

[0724] The server retrieves, for example, coupon information for "30% off chicken" and inventory data from partner suppliers.

[0725] Output: Advertisements, coupon information, and inventory data from partner companies are stored on the server.

[0726] Step 4: Data Integration and Processing

[0727] The server performs a join operation to integrate the purchase history data and inventory data collected for each user. For example, it might combine a user's past purchase data and current inventory data into a single table.

[0728] Input: Purchase history data, inventory data

[0729] The server stores integrated data in a database and manages it centrally.

[0730] Output: Integrated purchase history data and inventory data

[0731] Step 5: Data Analysis

[0732] The server uses machine learning algorithms to analyze users' past purchasing patterns and food consumption rates. For example, it analyzes users' purchase history as time-series data to analyze trends in food consumption over certain periods.

[0733] Input: Integrated purchase history data, inventory data

[0734] The server compares the user's current inventory data with that of its partners to identify any out-of-stock ingredients. For example, the server might identify that chicken is currently in short supply.

[0735] Output: Analysis results of ingredient shortage information, purchasing patterns, and consumption speed.

[0736] Step 6: Menu Generation

[0737] The server generates the optimal meal menu considering the user's preferences and nutritional balance. For example, for a user who has frequently consumed tomatoes and chicken in the past, it will suggest "tomato and chicken pasta."

[0738] Input: User preference data, nutritional balance information, out-of-stock information

[0739] The server saves the generated meal menu to a database.

[0740] Output: Optimal meal plan

[0741] Step 7: Suggestion of a store to purchase from

[0742] The server suggests the most suitable store to purchase ingredients the user is lacking. For example, store selection is made considering coupon information and special offers. In this process, information such as a 30% discount on chicken at a retail store will be reflected.

[0743] Input: Out-of-stock information, advertisements and coupon information from partner companies

[0744] The server stores purchase information in a database and sends it to the user's terminal via an API.

[0745] Output: Optimal store information

[0746] Step 8: Notification of Results

[0747] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include meal menus, lists of necessary ingredients, stores where to buy them, and available coupon information. For example, it might notify the user of a "Tomato and Chicken Pasta" menu and coupon information.

[0748] Input: Suggestion results (menu, ingredient list, store where to buy, coupon information)

[0749] Output: Notification content to the user

[0750] Through these steps, users can efficiently manage ingredients and easily prepare nutritionally balanced meals. Furthermore, partner businesses can effectively deploy targeted advertising and contribute to reducing food waste.

[0751] (Application Example 1)

[0752] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0753] In recent years, there has been a growing demand for systems that suggest optimal products and services based on user purchasing behavior and inventory management. However, conventional systems have not adequately provided personalized recommendations tailored to user needs, and the use of coupons and special offers has been limited. Furthermore, there has been a lack of means to centrally manage and effectively analyze purchase history and inventory data. As a result, users have not been able to obtain the optimal purchasing experience, and companies have faced challenges in effective targeting.

[0754] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0755] In this invention, the server includes means for collecting purchase history data from users, means for collecting user inventory data, means for collecting advertisements, coupon information, and inventory data from partner companies, means for integrating the purchase history data and inventory data to analyze user preferences and past purchasing patterns, means for comparing user inventory data with partner company inventory data to identify out-of-stock items, means for generating meal recommendation menus considering user preferences and nutritional balance, means for recommending items to purchase and suggesting stores where to purchase them, and means for sending push notifications to users based on the suggested data. As a result, users can efficiently manage their purchase history and inventory data and receive recommendations for optimal products and menus. Furthermore, companies can implement effective targeted advertising and coupon distribution, leading to improved purchasing experiences and increased sales.

[0756] - A "user" is an individual or group that uses the system to provide purchase history data and inventory data, and receives suggestions for the most suitable products and menus.

[0757] "Purchase history data" refers to detailed information about products and services that a user has purchased in the past, and often includes information such as the date, product name, and store where the purchase was made.

[0758] "Inventory data" refers to information about the current quantity and types of goods and materials owned by households, businesses, etc.

[0759] "Partner companies" refer to companies such as food manufacturers and retailers that provide advertising, coupon information, and inventory data to the system.

[0760] "Advertising" refers to information provided by partner companies for the purpose of promoting the sale of goods or services.

[0761] "Coupon information" refers to information that indicates the right or conditions for purchasing specific products or services at a discounted price.

[0762] A "server" refers to a central system that integrates and analyzes data, generates menus, creates suggestions, and notifies users, and is a computer system that works in conjunction with a database.

[0763] "Push notifications" refer to a function that automatically sends information to smartphones and other devices even when the user does not have the application open.

[0764] "Recommended menu" refers to meal suggestions generated by the server, taking into account the user's preferences and nutritional balance.

[0765] "Purchase location" refers to a specific retail store or online store suggested to the user for purchasing an out-of-stock item.

[0766] "Targeted advertising" refers to advertisements that are customized for specific user groups based on their interests and past behavior.

[0767] An "API" refers to an interface for exchanging data between different software systems, and is used, for example, to send data from a user terminal to a server or to retrieve data from a partner company.

[0768] Modes for carrying out the invention

[0769] Embodiments of this invention are systems that collect user purchase history data and inventory data, and retrieve advertisements, coupon information, and inventory data provided by partner companies. The following details how this system works.

[0770] System Configuration

[0771] 1. User terminal

[0772] User terminals include devices such as smartphones, tablets, and personal computers, which users can use to input purchase history, record inventory data, receive system suggestions, and check push notifications.

[0773] 2. Server

[0774] The server is the central management system at the heart of this system. The server is linked to a database that receives purchase history data and inventory data from users, as well as advertisements, coupon information, and inventory data from partner companies, and then integrates, analyzes, and generates recommendations.

[0775] 3. Partner companies

[0776] Partner companies, such as food manufacturers and retailers, provide advertising, coupon information, and inventory data to the server.

[0777] Program processing

[0778] Data collection

[0779] Users enter their purchase history and record their household inventory through a smartphone app or web portal. Purchase history data includes details such as date, product name, and store of purchase, while inventory data includes the types and quantities of products they have at home. This data is sent to the server via an API.

[0780] Retrieving external data

[0781] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via APIs. This data is organized and stored in the server's database and integrated with user purchase history data and inventory data.

[0782] Data Integration and Analysis

[0783] The server uses integrated data to build machine learning models and analyze user preferences and past purchasing patterns. This allows it to predict what products users currently need and what products they are likely to purchase in the future. Furthermore, it cross-references this data with inventory data provided by partner suppliers to identify out-of-stock items.

[0784] Suggestions for meal menus and stores where to purchase them.

[0785] Based on the analysis results, the server generates meal recommendations that take into account the user's preferences and nutritional balance. For example, for a user who has frequently consumed tomatoes and chicken in the past, it will suggest "Tomato and Chicken Pasta." It will also suggest stores where users can purchase any missing ingredients (e.g., chicken) based on the recommended recipe. At this time, it will consider any provided coupons or special offers to select the store that is most advantageous to the user.

[0786] Notification of results

[0787] The user's device will notify them of the suggestions via push notifications or in-app messages. The notifications will include recommended meal menus, a list of necessary ingredients, suggested stores for purchase, and available coupon information. Users can review these notifications, purchase items at the recommended stores, and create the suggested menu.

[0788] Hardware and software to be used

[0789] Hardware: Smartphones (iOS, Android), tablets, PCs, servers (including cloud-based databases).

[0790] Software: Python (used for data collection and analysis), Requests (HTTP library), JSON (data format), machine learning frameworks (e.g., TensorFlow and Scikit-learn).

[0791] Specific example

[0792] 1. User A enters their recent purchase history of tomatoes and chicken into a smartphone app.

[0793] 2. The terminal sends information to the server indicating that there are tomatoes in the household inventory but no chicken.

[0794] 3. The server retrieves coupon information for "30% off chicken" and inventory data from retailers via API.

[0795] 4. The server identifies from past usage history that user A prefers to use tomatoes and chicken, and analyzes that there is currently a shortage of chicken.

[0796] 5. The server generates a menu for "Tomato and Chicken Pasta" and suggests purchasing chicken from a retail store. The suggestion also includes discount information if a coupon is used.

[0797] 6. The terminal notifies user A of the menu and coupon information for "Tomato and Chicken Pasta".

[0798] 7. User A checks the notification, buys chicken from a retail store, and creates a menu.

[0799] Example of a prompt

[0800] Enter the following prompt into the generative AI model:

[0801] Based on the user's purchase history data and inventory data, please suggest the most suitable products and menus for that user. Please also consider the latest coupon information obtained from partner companies. Please use the following history data and inventory data.

[0802] Purchase history data: Tomatoes, chicken

[0803] Inventory data: Tomatoes: 2, Chicken: 0

[0804] Coupon Information: Chicken: 30% off

[0805] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0806] Step 1:

[0807] Users input or scan purchase history data using a smartphone app. For example, if they purchase tomatoes and chicken, they would enter the date, product names, and store details. The input data is sent to the server via an API.

[0808] Input: Purchase history data (e.g., tomatoes, chicken), date, store of purchase

[0809] Output: Data sent to the server via the API

[0810] Step 2:

[0811] Users record their household inventory data using their smartphones. For example, if they have 2 tomatoes and 0 chickens, they can take a photo or enter the data as text. This data is also sent to the server via an API.

[0812] Input: Inventory data (Example: Tomatoes: 2, Chicken: 0)

[0813] Output: Data sent to the server via the API

[0814] Step 3:

[0815] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies using APIs. For example, this includes coupon information and inventory status for "30% off chicken." This data is stored in the server's database.

[0816] Input: Advertisements, coupon information, and inventory data from partner companies.

[0817] Output: Data stored in the database on the server

[0818] Step 4:

[0819] The server integrates purchase history data, inventory data, and data from partner suppliers, and uses machine learning models to analyze user preferences and past purchasing patterns. This allows it to predict what products users currently need and what products they may purchase in the future.

[0820] Input: Purchase history data, inventory data, advertisements and coupon information from partner companies.

[0821] Output: Analysis results based on user preferences and purchasing patterns

[0822] Step 5:

[0823] The server checks inventory data and identifies out-of-stock items. For example, it might detect that the chicken inventory is zero. Based on this information, it generates recommended menu items.

[0824] Input: Integrated data, inventory data

[0825] Output: Out-of-stock items and recommended menu items

[0826] Step 6:

[0827] The server suggests the best store to purchase recommended meals and any missing items from the user. It also takes into account coupons and special offers provided by partner companies.

[0828] Input: Out-of-stock items, coupon information from partner companies

[0829] Output: Recommended menu items and suggested stores for purchase.

[0830] Step 7:

[0831] The device will send push notifications to the user with recommended menus and store information from the server. The notifications will include recommended meal menus, a list of necessary ingredients, suggested stores, and available coupon information.

[0832] Input: Recommended menu items and purchase store information from the server.

[0833] Output: Push notification to the user

[0834] By executing the above processing steps in order, users can efficiently manage their purchase history and inventory data and receive suggestions for the most suitable products and menus. In addition, partner businesses can effectively promote their products through targeted advertising and coupon distribution.

[0835] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0836] This embodiment of the invention relates to a system that collects user purchase history data and inventory data, and obtains advertising, coupon information, and inventory data from partner companies, and combines this with an emotion engine to suggest the optimal meal menu based on the user's emotions. The details are described below.

[0837] System Configuration

[0838] 1. User terminal

[0839] User terminals include devices such as smartphones, tablets, and personal computers, which users can use to input purchase history, record inventory data, provide emotional input using an emotion engine, and receive suggestions from the system.

[0840] 2. Server

[0841] The server is a central system that integrates, analyzes, recognizes sentiment, generates menus, creates suggestions, and notifies users. The database works in conjunction with it, managing information from users and data from partner companies.

[0842] 3. Partner companies

[0843] Partners include food manufacturers and retailers, who provide advertising, coupon information, and inventory data to the server.

[0844] 4. Emotional Engine

[0845] An emotion engine is software or hardware that recognizes emotions from a user's facial expressions and voice and generates emotion data. This emotion data reflects the user's current mental state, and menu suggestions are made based on it.

[0846] Program Processing Description

[0847] 1. Data Collection

[0848] Users enter or scan their purchase history via a smartphone app or web portal. This data includes details such as date, product name, and store of purchase.

[0849] Users can record their household inventory by taking photos of ingredients with their smartphone camera or manually entering text.

[0850] The device sends the collected purchase history data and inventory data to the server via an API.

[0851] 2. Acquisition of external data

[0852] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. This data includes product discounts, special offers, and in-store inventory status.

[0853] The server organizes the acquired data and stores it in the database.

[0854] 3. Acquisition of emotional data

[0855] Users register their emotional states through a smartphone app using facial recognition cameras and voice input. The emotion engine recognizes the user's emotions from these inputs and generates emotion data.

[0856] The device sends the generated emotion data to the server via an API.

[0857] 4. Data Integration and Analysis

[0858] The server integrates and centrally manages purchase history, inventory data, and sentiment data.

[0859] The server uses machine learning algorithms to analyze the user's past purchasing patterns, food consumption rate, and emotional data.

[0860] The server compares the user's current inventory data with the inventory data of partner suppliers to identify out-of-stock ingredients.

[0861] 5. Menu and store suggestions

[0862] The server generates an optimal meal plan considering the user's preferences, nutritional balance, and emotional state. For example, if the user is feeling stressed, it will suggest a menu that includes ingredients that help alleviate stress.

[0863] The server suggests the best store to purchase any missing ingredients (e.g., chicken). In doing so, it considers any coupons or special offers provided to select the store that is most advantageous to the user.

[0864] The server sends the generated menu and purchase store information to the user's terminal via API.

[0865] 6. Notification of Results and Purchase Information

[0866] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include suggested menus, a list of necessary ingredients, stores where to purchase them, and available coupon information.

[0867] The user checks the notification and purchases the ingredients needed to make the suggested menu.

[0868] Specific example

[0869] 1. Data collection:

[0870] User A enters their recent purchase history of tomatoes and chicken through a smartphone app.

[0871] The device sends information to the server indicating that there are tomatoes in the household inventory but no chicken.

[0872] 2. Obtaining external data:

[0873] The server retrieves coupon information for "30% off chicken" and inventory data from retailers via API.

[0874] 3. Acquisition of emotional data:

[0875] User A uses the app's facial recognition function to register with the emotion engine that they are feeling stressed.

[0876] The device sends emotional data to the server.

[0877] 4. Data Integration and Analysis:

[0878] The server identifies from past usage history that user A prefers to use tomatoes and chicken, and analyzes that there is currently a shortage of chicken.

[0879] The server takes into account that user A is experiencing stress and includes suggestions for foods that can help alleviate stress.

[0880] 5. Menu and store suggestions:

[0881] The server generates a menu item called "Tomato and Chicken Pasta" and suggests purchasing chicken from a retail store.

[0882] The server displays a coupon from a retail store, offering 30% off chicken.

[0883] 6. Notification of results and purchase information:

[0884] The terminal notifies user A of the menu item "Tomato and Chicken Pasta" and coupon information.

[0885] User A checks the notification, buys chicken at a retail store, and prepares the suggested menu.

[0886] In this way, users can efficiently manage ingredients and easily prepare meals that consider nutritional balance and emotional state. Furthermore, partner businesses can effectively conduct targeted advertising and contribute to reducing food waste.

[0887] The following describes the processing flow.

[0888] Step 1:

[0889] Users log in to their accounts via a smartphone app or web portal.

[0890] Step 2:

[0891] Users can manually enter their purchase history or scan loyalty cards or receipts from partner retailers. This involves entering or scanning details such as product name, purchase date, price, and store location.

[0892] Step 3:

[0893] The device sends the entered or scanned purchase history data to the server via an API.

[0894] Step 4:

[0895] Users can record their household inventory by taking photos of ingredients with their smartphone camera or by manually entering text.

[0896] Step 5:

[0897] The terminal sends recorded inventory data to the server via an API. The data includes information such as the type and quantity of ingredients and their expiration dates.

[0898] Step 6:

[0899] Users register their emotional states (stress, joy, sadness, etc.) with the emotion engine using the app's facial recognition and voice input functions.

[0900] Step 7:

[0901] The emotion engine generates recognized emotion data and sends it to the server.

[0902] Step 8:

[0903] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. The retrieved data includes product sale information and inventory status.

[0904] Step 9:

[0905] The server integrates user-specific purchase history data, inventory data, and sentiment data, and stores it in a database. This data is used for later analysis.

[0906] Step 10:

[0907] The server uses machine learning algorithms to analyze the user's past purchasing patterns, food consumption rate, and emotional data. In doing so, it identifies the user's preferences and frequently purchased items.

[0908] Step 11:

[0909] The server compares the user's current inventory data with the inventory data of partner suppliers to identify out-of-stock ingredients. For example, it might identify a situation where tomatoes are in stock but chicken is in short supply.

[0910] Step 12:

[0911] The server generates meal menus considering the user's preferences, nutritional balance, and emotional state. If the user is stressed, it suggests a menu that includes ingredients that help alleviate stress. For example, if the user is stressed, it might suggest "tomato and chicken pasta."

[0912] Step 13:

[0913] The server suggests purchasing the missing ingredient (in this case, chicken) from the most suitable retailer. It considers coupon information from partner suppliers to select the store that offers the best deal for the user. For example, it might say, "A coupon for 30% off chicken is available at Retailer B."

[0914] Step 14:

[0915] The server sends the generated menu and purchase store information to the user's terminal via API.

[0916] Step 15:

[0917] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include suggested menus, a list of necessary ingredients, store locations, and available coupon information.

[0918] Step 16:

[0919] The user checks the notification and purchases any missing ingredients to create the suggested menu. For example, the user purchases chicken from retailer B.

[0920] Step 17:

[0921] After a purchase, the user updates the inventory status in the app and sends that information back to the server. This ensures that the latest inventory information is reflected in the next offer.

[0922] This system allows users to easily manage available ingredients and obtain optimal meal menus tailored to their emotional state and preferences. Furthermore, partner businesses can enhance the effectiveness of their targeted advertising and contribute to reducing food waste.

[0923] (Example 2)

[0924] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0925] Traditional purchase history and inventory management systems have been unable to make suggestions that take into account the user's emotional state, making it difficult to increase consumer satisfaction. Furthermore, systems that suggest meal menus considering consumer preferences and nutritional balance are limited, making it difficult to support food waste reduction and efficient purchasing behavior. Therefore, there is a need for a system that suggests optimal meal menus that reflect the user's emotional state and effectively promotes the purchase of necessary ingredients.

[0926] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting purchase history data from the user, means for collecting the user's inventory data, means for collecting advertisements, coupon information and inventory data from partner companies, means for acquiring the user's emotional data, means for integrating the purchase history data, inventory data and emotional data to analyze the user's preferences and past purchasing patterns, means for comparing the user's inventory data with the partner company's inventory data to identify out-of-stock ingredients, means for generating meal menus considering the user's preferences, nutritional balance and emotional state, means for suggesting ingredients to be purchased and the stores where they can be purchased, and means for notifying the user of the suggestion results. This makes it possible to suggest optimal meal menus that reflect the user's emotional state and purchasing patterns and to support efficient purchasing behavior.

[0927] "Purchase history data" refers to data containing information about products that a user has purchased in the past. This data includes details such as product name, purchase date and time, store of purchase, and quantity.

[0928] "Inventory data" refers to data containing information about the food and products a user currently owns in their home. This data includes information such as the name of the food item, the quantity, and the expiration date.

[0929] "Advertising" refers to information provided by partner companies to promote specific products or services. This information includes product descriptions, special offers, and promotional details.

[0930] "Coupon information" refers to information that allows you to receive a discount on a specific product or service. This information includes coupon codes, discount rates, terms and conditions, and expiration dates.

[0931] "Partner companies" are businesses such as food manufacturers and retailers that provide data in conjunction with the system.

[0932] "Emotional data" refers to data about a user's emotional state. This data is obtained from the user's facial expressions and voice, and reflects emotional states such as happiness, anxiety, and stress.

[0933] An "emotion engine" is software or hardware that analyzes a user's facial expressions and voice to recognize their emotions and generate emotional data.

[0934] "Data integration" is the process of centrally managing and linking different types of data (such as purchase history data, inventory data, and sentiment data).

[0935] "Data analysis" is the process of analyzing user preferences, past purchasing patterns, food consumption rates, emotional states, and other factors based on integrated data.

[0936] A "meal menu" is a list of recipes and ingredients for creating a specific meal. This list is generated taking into account the user's preferences, nutritional balance, and emotional state.

[0937] "Suggestion results" refer to the suggestions generated by the system, such as meal menus, stores to purchase from, and coupon information.

[0938] A "notification" is an action taken to inform the user of the results of a system suggestion. This includes push notifications, in-app messages, and so on.

[0939] This invention relates to a system that collects user purchase history data, inventory data, advertisements and coupon information from partner companies, and sentiment data, and integrates and analyzes this data to suggest the optimal meal menu based on the user's emotions. The details are described below.

[0940] System Configuration

[0941] 1. User terminal

[0942] User terminals include smartphones, tablets, and personal computers. Using these terminals, users can input purchase history, record inventory data, provide emotional input using an emotion engine, and receive suggestions from the system.

[0943] 2. Server

[0944] The server is a central system that integrates, analyzes, recognizes sentiment, generates menus, creates suggestions, and notifies users. The server is connected to a database that centrally manages user information and data from partner companies.

[0945] 3. Partner companies

[0946] Partner companies include food manufacturers and retailers, and their role is to provide advertising, coupon information, and inventory data to the server.

[0947] 4. Emotional Engine

[0948] An emotion engine is software or hardware that recognizes emotions from a user's facial expressions and voice and generates emotion data. This emotion data reflects the user's mental state, and menu suggestions are made based on it.

[0949] Program Processing Description

[0950] Data collection

[0951] Users input or scan their purchase history through a smartphone app or web portal. For example, scanning a receipt with a smartphone camera allows the app to automatically recognize the date, product name, and store of purchase.

[0952] Users can record their household inventory by taking photos of ingredients with their smartphone camera or manually entering text.

[0953] The device sends the collected purchase history data and inventory data to the server via an API.

[0954] Retrieving external data

[0955] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. This data includes product discounts, special offers, and in-store inventory status.

[0956] The server organizes the acquired data and stores it in the database.

[0957] Acquisition of emotional data

[0958] Users register their emotional states through a smartphone app using facial recognition cameras and voice input. The emotion engine recognizes the user's emotions from these inputs and generates emotion data.

[0959] The device sends the generated emotion data to the server via an API.

[0960] Data Integration and Analysis

[0961] The server integrates and centrally manages purchase history data, inventory data, and sentiment data.

[0962] The server uses machine learning algorithms to analyze the user's past purchasing patterns, food consumption rate, and emotional data.

[0963] The server compares the user's current inventory data with the inventory data of partner suppliers to identify out-of-stock ingredients.

[0964] Menu and store suggestions

[0965] The server generates an optimal meal plan considering the user's preferences, nutritional balance, and emotional state. For example, if the user is feeling stressed, it will suggest a menu that includes ingredients that help alleviate stress.

[0966] The server suggests the best store to purchase any missing ingredients. In doing so, it considers any coupons or special offers provided to select the most beneficial store for the user.

[0967] The server sends the generated menu and purchase store information to the user's terminal via API.

[0968] Notification of results and purchase information

[0969] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include suggested menus, a list of necessary ingredients, stores where to purchase them, and available coupon information.

[0970] The user checks the notification and purchases the ingredients needed to make the suggested menu.

[0971] Specific example

[0972] 1. Data collection:

[0973] User A enters their recent purchase history of tomatoes and chicken into a smartphone app. The app automatically recognizes the product name, date, and store, and digitizes the data.

[0974] The device sends that data to the server.

[0975] 2. Obtaining external data:

[0976] The server retrieves coupon information for "30% off chicken" and inventory data from retailers via API.

[0977] 3. Acquisition of emotional data:

[0978] User A uses the app's facial recognition function to register with the emotion engine that they are feeling stressed.

[0979] The device sends that emotional data to the server.

[0980] 4. Data Integration and Analysis:

[0981] The server identifies from past usage history that user A prefers to use tomatoes and chicken, and analyzes that there is currently a shortage of chicken.

[0982] The server takes into account that user A is experiencing stress and includes suggestions for foods that can help alleviate stress.

[0983] 5. Menu and store suggestions:

[0984] The server generates a menu item called "Tomato and Chicken Pasta" and suggests that the user purchase chicken from a retail store.

[0985] The server displays a coupon from a retail store, offering 30% off chicken.

[0986] 6. Notification of results and purchase information:

[0987] The device notifies user A of the menu item "Tomato and Chicken Pasta" and coupon information.

[0988] User A checks the notification, buys chicken at a retail store, and prepares the suggested menu.

[0989] This processing flow allows users to efficiently manage ingredients and easily receive meal menu suggestions that take nutritional balance and emotional state into consideration. Furthermore, partner companies can effectively implement targeted advertising and contribute to reducing food waste.

[0990] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0991] Step 1: Data Collection

[0992] Users enter their purchase history or scan receipts using a smartphone app. For example, if a user takes a picture of a receipt with their smartphone camera, the app automatically recognizes the date, product name, and store of purchase, and saves this data digitally. This data includes the user ID, product name, quantity, and purchase date.

[0993] Users record their household inventory by taking photos of ingredients with their smartphone camera or manually entering text. This data includes the name of the ingredient, the quantity, and the expiration date.

[0994] The device sends collected purchase history data and inventory data to the server via API. The server stores the received data in a database.

[0995] Step 2: Obtaining external data

[0996] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. This data includes product discounts, special offers, and in-store inventory status.

[0997] The server organizes the acquired external data and stores it in a database. The organized data is then categorized for later analysis and matching.

[0998] Step 3: Acquisition of emotional data

[0999] Users register their emotional states through a smartphone app. For example, by taking a picture of their face with the app's facial recognition camera, the emotion engine analyzes the expression. Alternatively, users can record their emotional states using voice input.

[1000] The emotion engine recognizes the user's emotions from their facial expressions and voice, and generates emotion data such as "happiness," "anxiety," and "stress."

[1001] The device sends the generated emotion data to the server via an API.

[1002] Step 4: Data Integration and Analysis

[1003] The server integrates and centrally manages purchase history data, inventory data, and sentiment data collected from users. This integration process links related data using the user ID as the key.

[1004] The server uses machine learning algorithms to analyze this integrated data. Specifically, it analyzes the user's past purchasing patterns, food consumption rate, and emotional data to predict the user's purchasing behavior and preferences. This analysis results include, for example, the food items the user consumed the most in the past month and the products they purchased the most.

[1005] The server matches the user's current inventory data with that of partner suppliers to identify any ingredients currently lacking in the household. This generates a list of ingredients the user should purchase.

[1006] Step 5: Menu and store suggestions

[1007] The server generates an optimal meal plan considering the user's preferences, nutritional balance, and emotional state. For example, if the user is feeling stressed, a menu including ingredients with relaxing properties will be suggested.

[1008] The server suggests the best stores to purchase any missing ingredients. Based on provided coupons and special offers, it selects the store that will benefit the user the most. For example, it might suggest information such as "Chicken is 30% off at a nearby supermarket."

[1009] The server sends the generated menu and purchase store information to the user's terminal via API.

[1010] Step 6: Notification of results and purchase information

[1011] The device displays suggestions to the user via push notifications and in-app messages. These notifications include suggested menus, a list of necessary ingredients, stores where to purchase them, and available coupon information. Specifically, it might display a recipe for "Tomato and Chicken Pasta" and its required ingredients.

[1012] Users check the notifications and purchase ingredients to create the suggested menu. They use the notified coupon information to purchase the necessary ingredients at their nearest supermarket, thereby reducing costs.

[1013] The above outlines the processing steps of this system. In each step, the user, terminal, and server work together to collect, analyze, and propose data, thereby enabling the suggestion of the optimal meal menu based on the user's emotional state and preferences.

[1014] (Application Example 2)

[1015] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[1016] While conventional systems could suggest menus based on user purchase history and inventory data, they failed to consider the user's emotional state. Furthermore, they were inadequate in suggesting which stores to purchase ingredients from if those ingredients were in short supply. This resulted in an inability to suggest meals best suited to the user's mental state and preferences, and also increased the effort required for ingredient purchases.

[1017] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1018] In this invention, the server includes means for collecting purchase history data from users, means for collecting user inventory data, means for collecting advertisements, coupon information and inventory data from partner companies, means for collecting user emotional data, means for integrating the purchase history data, inventory data and emotional data to analyze the user's preferences, past purchase patterns and emotional state, means for comparing the user's inventory data with the partner company's inventory data to identify out-of-stock ingredients, means for generating meal menus considering the user's preferences, nutritional balance and emotional state, means for suggesting ingredients to purchase and where to purchase them, and means for notifying the user of the suggestion results. This makes it possible to suggest an optimal meal menu that takes the user's emotional state into consideration and efficiently guide the user to where to purchase the necessary ingredients.

[1019] "Purchase history data" refers to information about products that a user has purchased in the past, including details such as the date and time, product name, and place of purchase.

[1020] "Inventory data" refers to data showing the current availability of specific food items or products in a user's home or in the stores of partner companies.

[1021] "Advertising" refers to information provided to users for the purpose of promoting the sale of specific products or services offered by partner companies.

[1022] "Coupon information" refers to codes or vouchers issued by partner companies to users to offer discounts or benefits on specific products or services.

[1023] "Emotional data" refers to data that reflects the user's current emotional state, as recognized from their facial expressions and voice.

[1024] "Preference" is a concept that refers to the products, foods, or specific habits and tastes that a user likes.

[1025] "Past purchasing patterns" refer to data that analyzes trends such as the types, frequency, and timing of products that users have purchased in the past.

[1026] "Out-of-stock ingredients" refer to specific ingredients that are not available in the user's home inventory or store inventory, but are necessary for creating a menu.

[1027] "Emotional state" refers to the mental state or mood that a user is currently experiencing, such as stress or happiness.

[1028] "Means for generating menus" refers to a process or system that automatically creates appropriate meal menus, taking into account the user's preferences, nutritional balance, and emotional state.

[1029] "Means of suggesting stores for purchase" refers to a process or system that identifies the best store for a user to purchase the necessary ingredients and presents that information to the user.

[1030] "Means of notifying the results of the proposal" refers to a process or system that provides users with information such as generated menus and purchase options via push notifications or in-app messages.

[1031] The embodiments for carrying out this invention will be described in detail below.

[1032] System Configuration

[1033] 1. User terminal

[1034] User terminals include devices such as smartphones, tablets, and personal computers, which users can use to input purchase history, record inventory data, provide emotional input using an emotion engine, and receive suggestions from the system.

[1035] 2. Server

[1036] The server is the central system responsible for data integration, analysis, sentiment recognition, menu generation, suggestion creation, and user notifications. The database works in conjunction with this server, managing user information and data from partner companies.

[1037] 3. Partner companies

[1038] Partner companies refer to organizations such as food-related businesses and retailers, and these companies provide advertising, coupon information, and inventory data to the server.

[1039] 4. Emotional Engine

[1040] An emotion engine is software or hardware that recognizes emotions from a user's facial expressions and voice and generates emotion data. This emotion data reflects the user's current mental state, and menu suggestions are made based on it.

[1041] Program Processing Description

[1042] Hardware and software to be used

[1043] Hardware: Smartphone (iOS or Android)

[1044] Software: Python, TensorFlow (emotion recognition model), SQLite (database management), RESTful API (data communication)

[1045] 1. Data Collection

[1046] Users input their purchase history and inventory data through a smartphone application. They can also scan product barcodes using their smartphone's camera. The collected data is stored in an SQLite database.

[1047] 2. Acquisition of external data

[1048] The server periodically retrieves advertisements, coupon information, and inventory data from partner servers via a RESTful API and stores this data in an SQLite database.

[1049] 3. Acquisition of emotional data

[1050] When a user opens the app, their facial expressions and voice are analyzed using the smartphone's camera and microphone by an emotion engine (TensorFlow model). The generated emotion data is stored in an SQLite database.

[1051] 4. Data Integration and Analysis

[1052] The server integrates purchase history data, inventory data, and sentiment data stored in an SQLite database, and uses machine learning algorithms to analyze user preferences, past purchasing patterns, and emotional states.

[1053] 5. Menu generation and suggested stores for purchase.

[1054] Based on the analyzed data, the server generates an optimal menu that takes into account the user's preferences, nutritional balance, and emotional state, and identifies the necessary ingredients and where to purchase them. This information is also stored in an SQLite database.

[1055] 6. Notification of Results and Purchase Information

[1056] The generated menu and purchase store information will be sent to the user's device as a push notification or in-app message.

[1057] Specific examples and examples of prompt statement usage

[1058] Specific example

[1059] User B uses their smartphone at a physical store and enters their desire to make "tomato and chicken pasta" into the app.

[1060] The app scans user B's past purchase history and confirms that tomatoes are in stock but chicken is in short supply.

[1061] We retrieve coupon information from our partner suppliers and notify customers that there is a 30% off coupon for chicken.

[1062] Example of a prompt

[1063] "Based on the user's purchase history, please suggest the optimal meal menu that reflects their current emotional state."

[1064] "Use an emotion engine to recognize user emotions and guide them through the grocery purchase process, taking into account current inventory data and coupon information."

[1065] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1066] Step 1:

[1067] Users use a smartphone app to input purchase history and inventory data. Users scan product barcodes using their smartphone camera and enter the information into the app. The input data includes details such as product name, date, purchase location, and quantity. This information is sent from the device to a server and stored in an SQLite database.

[1068] Step 2:

[1069] The server periodically retrieves advertisements, coupon information, and inventory data from partner servers via a RESTful API. The retrieved data includes discount and special offer information, as well as in-store inventory status, transmitted from the partner servers. This data is stored by the server in an SQLite database.

[1070] Step 3:

[1071] The user inputs their emotional data via a smartphone app. The smartphone's camera and microphone are used to analyze facial expressions and voice using an emotion engine (TensorFlow model). The analyzed emotional data reflects the user's current emotional state (e.g., stress, happiness), and is sent from the device to a server and stored in an SQLite database.

[1072] Step 4:

[1073] The server integrates purchase history data, inventory data, and sentiment data stored in an SQLite database. This allows for analysis based on user preferences, past purchasing patterns, and emotional states. Machine learning algorithms are applied using Python scripts to identify specific user preferences and food consumption rates.

[1074] Step 5:

[1075] Based on the analysis results above, the server generates an optimal meal plan that takes into account the user's preferences, nutritional balance, and emotional state. The menu is generated using a Python script, and any missing ingredients are also identified. This missing ingredient information is cross-referenced with inventory data from partner suppliers, and suggestions are generated that include optimal purchasing locations and coupon information.

[1076] Step 6:

[1077] The server sends the generated menu and store information to the user's device. This information includes the suggested menu, a list of required ingredients, the store where to purchase the items, and any available coupons. The user reviews these suggestions within the smartphone app.

[1078] Step 7:

[1079] The user reviews the suggested menu and store information, then visits a physical store to purchase the necessary ingredients. The user uses a smartphone app to manage ingredients according to the suggested menu and refer to recipes. Through these steps, the user's purchasing experience is optimized based on their emotional state.

[1080] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1081] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1082] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[1083] [Third Embodiment]

[1084] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1085] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1086] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1087] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1088] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1089] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1090] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1091] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1092] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1093] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1094] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1095] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1096] Embodiments of this invention relate to a system that collects user purchase history data and inventory data, and obtains advertising, coupon information, and inventory data from partner companies. Details are described below.

[1097] System Configuration

[1098] 1. User terminal

[1099] User terminals include devices such as smartphones, tablets, and personal computers, which users can use to input purchase history, record inventory data, and receive suggestions from the system.

[1100] 2. Server

[1101] The server is a central system that integrates and analyzes data, generates menus, creates suggestions, and notifies users. The database works in conjunction with it, managing information from users and data from partner companies.

[1102] 3. Partner companies

[1103] Partners include food manufacturers and retailers, who provide advertising, coupon information, and inventory data to the server.

[1104] Program Processing Description

[1105] 1. Data Collection

[1106] Users enter or scan their purchase history via a smartphone app or web portal. This data includes details such as date, product name, and store of purchase.

[1107] Users can record their household inventory by taking photos of ingredients with their smartphone camera or manually entering text.

[1108] The terminal sends the purchase history data and inventory data entered by the user to the server via an API.

[1109] 2. Acquisition of external data

[1110] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. This data includes product discounts, special offers, and in-store inventory status.

[1111] The server organizes the acquired data and stores it in the database.

[1112] 3. Data Integration and Analysis

[1113] The server integrates and centrally manages purchase history data and inventory data collected for each user.

[1114] The server uses machine learning algorithms to analyze the user's past purchasing patterns and food consumption rate.

[1115] The server compares the user's current inventory data with that of partner suppliers to identify out-of-stock ingredients.

[1116] 4. Menu and store suggestions

[1117] The server generates the optimal meal menu considering the user's preferences and nutritional balance. For example, for a user who has frequently consumed tomatoes and chicken in the past, it will suggest "tomato and chicken pasta."

[1118] The server suggests the most suitable store to purchase ingredients the user is lacking (e.g., chicken). In doing so, it considers any coupons or special offers provided to select the store that is most advantageous to the user.

[1119] The server sends the generated menu and purchase store information to the user's terminal via the API.

[1120] 5. Notification of Results and Purchase Information

[1121] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include meal menus, lists of necessary ingredients, stores where to buy them, and available coupon information.

[1122] The user checks the notification and purchases the necessary ingredients from the suggested store.

[1123] Specific example

[1124] 1. Data collection:

[1125] User A enters their recent purchase history of tomatoes and chicken through a smartphone app.

[1126] The device sends information to the server indicating that there are tomatoes in the household inventory but no chicken.

[1127] 2. Obtaining external data:

[1128] The server retrieves coupon information for "30% off chicken" and inventory data from retailer B via API.

[1129] 3. Data Integration and Analysis:

[1130] The server identifies from past usage history that user A prefers to use tomatoes and chicken, and analyzes that there is currently a shortage of chicken.

[1131] 4. Menu and store suggestions:

[1132] The server generates a menu for "Tomato and Chicken Pasta" and suggests purchasing chicken from retailer B.

[1133] The server will show that you can get a 30% discount by using a coupon from retailer B.

[1134] 5. Notification of results and purchase information:

[1135] The terminal notifies user A of the menu and coupon information for "Tomato and Chicken Pasta".

[1136] User A checks the notification, buys chicken from retailer B, and creates a menu.

[1137] In this way, users can efficiently manage ingredients and easily prepare nutritionally balanced meals. Furthermore, partner companies can effectively deploy targeted advertising and contribute to reducing food waste.

[1138] The following describes the processing flow.

[1139] Step 1:

[1140] Users log in to their accounts via a smartphone app or web portal.

[1141] Step 2:

[1142] Users can manually enter their purchase history or scan loyalty cards or receipts from partner retailers. When doing so, they will enter or scan details such as product name, purchase date, price, and store location.

[1143] Step 3:

[1144] The device sends the entered or scanned purchase history data to the server via an API.

[1145] Step 4:

[1146] Users can record their household inventory by taking photos of ingredients with their smartphone camera or by manually entering text.

[1147] Step 5:

[1148] The terminal sends recorded inventory data to the server via an API. The data includes information such as the type and quantity of ingredients and their expiration dates.

[1149] Step 6:

[1150] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. The retrieved data includes product sale information and inventory status.

[1151] Step 7:

[1152] The server integrates user-specific purchase history and inventory data and stores it in a database. This stored data is used for later analysis.

[1153] Step 8:

[1154] The server uses machine learning algorithms to analyze the user's past purchasing patterns and food consumption rate. In this process, it identifies the user's preferences and frequently purchased items.

[1155] Step 9:

[1156] The server compares the user's current inventory data with the inventory data of partner suppliers to identify out-of-stock ingredients. For example, it might identify a situation where tomatoes are in stock but chicken is in short supply.

[1157] Step 10:

[1158] The server automatically generates meal menus, taking into account the user's preferences and nutritional balance. For example, it might suggest "tomato and chicken pasta" to a user who has previously enjoyed tomatoes and chicken.

[1159] Step 11:

[1160] The server suggests purchasing the missing ingredient (in this case, chicken) from the most suitable retailer. It considers coupon information from partner suppliers to select the most advantageous purchase location for the user. For example, it might say, "A 30% off coupon for chicken is available at Retailer B."

[1161] Step 12:

[1162] The server sends the generated menu and purchase store information to the user's terminal via API.

[1163] Step 13:

[1164] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include suggested menus, a list of necessary ingredients, store locations, and available coupon information.

[1165] Step 14:

[1166] The user checks the notification and purchases any missing ingredients to create the suggested menu. For example, the user purchases chicken from retailer B.

[1167] Step 15:

[1168] After a purchase, the user updates the inventory status in the app and sends that information back to the server. This ensures that the latest inventory information is reflected in the next offer.

[1169] This allows users to easily create nutritionally balanced meal plans, partner businesses to conduct effective targeted advertising, and contribute to reducing food waste.

[1170] (Example 1)

[1171] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1172] Traditionally, it has been difficult for users to manage their household ingredients while preparing nutritionally balanced meals. Furthermore, partner companies have faced challenges in effectively advertising based on user purchasing patterns, making food waste reduction a significant issue. A system was needed to solve these problems, improving user convenience and enhancing the marketing effectiveness of partner companies.

[1173] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1174] In this invention, the server includes means for analyzing purchase history data and inventory data using machine learning algorithms, means for identifying out-of-stock ingredients, and means for suggesting the optimal store for purchase and transmitting that information to the user terminal via an API. This streamlines the user's ingredient management and enables the suggestion of nutritionally balanced meals. Furthermore, partner companies can effectively deploy targeted advertising and contribute to reducing food waste.

[1175] "Purchase history data" refers to data containing information about products that a user has purchased in the past. Specifically, it includes details such as product name, store of purchase, and purchase date.

[1176] "Inventory data" refers to data containing information about the food and products currently in a household. Specifically, it includes details such as the name of the food item, the quantity, and its storage condition.

[1177] "Partner companies" refer to external companies and stores that provide advertising, coupon information, and inventory data in conjunction with the system.

[1178] "Advertising" refers to promotional information for products and services provided by partner companies.

[1179] "Coupon information" refers to information about discounts and benefits offered by partner companies.

[1180] A "machine learning algorithm" refers to computational techniques used to analyze data and find patterns and trends.

[1181] An "API" refers to an interface used to exchange functions between different software programs.

[1182] "Push notification" refers to a function that instantly sends information from the server to the user's device.

[1183] A "database" refers to a system for efficiently storing, searching, and managing large amounts of data.

[1184] "Centralized management" refers to the integrated management of different types of data in a single database or system.

[1185] "Preferences" refer to a user's tastes and preferences. Specifically, this includes the user's preferences for ingredients and products derived from past purchase data.

[1186] "Nutritional balance" refers to a state where the food a user consumes contains the necessary nutrients in appropriate amounts.

[1187] "Meal menu" refers to a list of meal recipes and dishes suggested to the user.

[1188] "Purchase store" refers to the store suggested to the user for purchasing ingredients or other products.

[1189] Embodiments of this invention relate to a system that collects user purchase history data and inventory data, and analyzes this data in combination with advertisements, coupon information, and inventory data from partner companies. This system enables users to manage their household inventory and receive suggestions for nutritionally balanced meal menus.

[1190] System Configuration

[1191] 1. User terminal

[1192] User terminals include devices such as smartphones, tablets, and personal computers. Users can use these devices to input purchase history, record inventory data, and receive suggestions from the system.

[1193] 2. Server

[1194] The server is a central system that integrates and analyzes data, generates menus, creates suggestions, and notifies users. The database works in conjunction with it, managing information from users and data from partner companies.

[1195] 3. Partner companies

[1196] Partners include food manufacturers and retailers, who provide advertising, coupon information, and inventory data to the server.

[1197] Hardware and software to be used

[1198] Hardware: Smartphones, tablets, PCs, servers, network infrastructure

[1199] Software: Smartphone apps, web portals, databases (e.g., MySQL, PostgreSQL), APIs, machine learning algorithms (e.g., Python's Scikit-learn, TensorFlow)

[1200] Data processing and calculations

[1201] Data collection

[1202] Users enter their purchase history through a smartphone app or web portal. This data includes details such as the date, product name, and store of purchase.

[1203] Users record their household inventory by taking photos of ingredients with their smartphone camera or manually entering text.

[1204] The device sends this purchase history data and inventory data to the server via an API.

[1205] Retrieving external data

[1206] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. This data includes product discounts, special offers, and in-store inventory status.

[1207] The server organizes the acquired data and stores it in the database.

[1208] Data Integration and Analysis

[1209] The server integrates and centrally manages purchase history data and inventory data collected for each user.

[1210] The server uses machine learning algorithms to analyze the user's past purchasing patterns and food consumption rate.

[1211] The server compares the user's current inventory data with that of partner suppliers to identify out-of-stock ingredients.

[1212] Menu and store suggestions

[1213] The server generates the optimal meal menu considering the user's preferences and nutritional balance. For example, for a user who frequently consumes tomatoes and chicken, it will suggest "Tomato and Chicken Pasta."

[1214] The server suggests the most suitable store to purchase any ingredients the user is lacking. In doing so, it selects the store that is most advantageous to the user, taking into account any coupons or special offers provided.

[1215] The server sends the generated menu and purchase store information to the user's terminal via an API.

[1216] Notification of results and purchase information

[1217] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include meal menus, lists of necessary ingredients, stores where to buy them, and available coupon information.

[1218] The user checks the notification and purchases the necessary ingredients from the suggested store.

[1219] Specific example

[1220] 1. Data collection:

[1221] User A enters their recent purchase history of tomatoes and chicken through a smartphone app.

[1222] The device sends information to the server indicating that there are tomatoes in the household inventory but no chicken.

[1223] 2. Obtaining external data:

[1224] The server retrieves coupon information for "30% off chicken" and inventory data from retail stores.

[1225] 3. Data Integration and Analysis:

[1226] The server identifies from past usage history that user A prefers to use tomatoes and chicken, and analyzes that there is currently a shortage of chicken.

[1227] 4. Menu and store suggestions:

[1228] The server generates a menu for "Tomato and Chicken Pasta" and suggests purchasing chicken from a retail store.

[1229] The server will show that you can get 30% off by using a retail coupon.

[1230] 5. Notification of results and purchase information:

[1231] The terminal notifies user A of the menu and coupon information for "Tomato and Chicken Pasta".

[1232] User A checks the notification, buys chicken from a retail store, and creates a menu.

[1233] In this way, this system helps users efficiently manage ingredients and easily prepare nutritionally balanced meals. Furthermore, partner businesses can effectively deploy targeted advertising and contribute to reducing food waste.

[1234] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1235] Step 1: Enter the user's purchase history.

[1236] The user launches a smartphone app or web portal and enters their purchase history. For example, they might use the app's barcode scanning function to enter purchase information for tomatoes and chicken.

[1237] Input: Product name, store of purchase, date of purchase

[1238] The device temporarily stores this purchase history data in storage and sends it to the server via an API.

[1239] Output: Purchase history data is sent to the server.

[1240] Step 2: Record household inventory

[1241] The user uses their smartphone camera to take a picture of the food items currently in their household inventory. For example, they might take a picture of tomatoes in their refrigerator.

[1242] Input: Photo of the ingredient, or manually entered name of the ingredient.

[1243] The terminal sends this inventory data to the server via an API.

[1244] Output: Inventory data is sent to the server.

[1245] Step 3: Obtain data from partner companies

[1246] The server periodically sends requests to partner vendors via API to retrieve the latest advertisements, coupon information, and inventory data.

[1247] Input: API request from partner company

[1248] The server retrieves, for example, coupon information for "30% off chicken" and inventory data from partner suppliers.

[1249] Output: Advertisements, coupon information, and inventory data from partner companies are stored on the server.

[1250] Step 4: Data Integration and Processing

[1251] The server performs a join operation to integrate the purchase history data and inventory data collected for each user. For example, it might combine a user's past purchase data and current inventory data into a single table.

[1252] Input: Purchase history data, inventory data

[1253] The server stores integrated data in a database and manages it centrally.

[1254] Output: Integrated purchase history data and inventory data

[1255] Step 5: Data Analysis

[1256] The server uses machine learning algorithms to analyze users' past purchasing patterns and food consumption rates. For example, it analyzes users' purchase history as time-series data to analyze trends in food consumption over certain periods.

[1257] Input: Integrated purchase history data, inventory data

[1258] The server compares the user's current inventory data with that of its partners to identify any out-of-stock ingredients. For example, the server might identify that chicken is currently in short supply.

[1259] Output: Analysis results of ingredient shortage information, purchasing patterns, and consumption speed.

[1260] Step 6: Menu Generation

[1261] The server generates the optimal meal menu considering the user's preferences and nutritional balance. For example, for a user who has frequently consumed tomatoes and chicken in the past, it will suggest "tomato and chicken pasta."

[1262] Input: User preference data, nutritional balance information, out-of-stock information

[1263] The server saves the generated meal menu to a database.

[1264] Output: Optimal meal plan

[1265] Step 7: Suggestion of a store to purchase from

[1266] The server suggests the most suitable store to purchase ingredients the user is lacking. For example, store selection is made considering coupon information and special offers. In this process, information such as a 30% discount on chicken at a retail store will be reflected.

[1267] Input: Out-of-stock information, advertisements and coupon information from partner companies

[1268] The server stores purchase information in a database and sends it to the user's terminal via an API.

[1269] Output: Optimal store information

[1270] Step 8: Notification of Results

[1271] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include meal menus, lists of necessary ingredients, stores where to buy them, and available coupon information. For example, it might notify the user of a "Tomato and Chicken Pasta" menu and coupon information.

[1272] Input: Suggestion results (menu, ingredient list, store where to buy, coupon information)

[1273] Output: Notification content to the user

[1274] Through these steps, users can efficiently manage ingredients and easily prepare nutritionally balanced meals. Furthermore, partner businesses can effectively deploy targeted advertising and contribute to reducing food waste.

[1275] (Application Example 1)

[1276] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1277] In recent years, there has been a growing demand for systems that suggest optimal products and services based on user purchasing behavior and inventory management. However, conventional systems have not adequately provided personalized recommendations tailored to user needs, and the use of coupons and special offers has been limited. Furthermore, there has been a lack of means to centrally manage and effectively analyze purchase history and inventory data. As a result, users have not been able to obtain the optimal purchasing experience, and companies have faced challenges in effective targeting.

[1278] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1279] In this invention, the server includes means for collecting purchase history data from users, means for collecting user inventory data, means for collecting advertisements, coupon information, and inventory data from partner companies, means for integrating the purchase history data and inventory data to analyze user preferences and past purchasing patterns, means for comparing user inventory data with partner company inventory data to identify out-of-stock items, means for generating meal recommendation menus considering user preferences and nutritional balance, means for recommending items to purchase and suggesting stores where to purchase them, and means for sending push notifications to users based on the suggested data. As a result, users can efficiently manage their purchase history and inventory data and receive recommendations for optimal products and menus. Furthermore, companies can implement effective targeted advertising and coupon distribution, leading to improved purchasing experiences and increased sales.

[1280] - A "user" is an individual or group that uses the system to provide purchase history data and inventory data, and receives suggestions for the most suitable products and menus.

[1281] "Purchase history data" refers to detailed information about products and services that a user has purchased in the past, and often includes information such as the date, product name, and store where the purchase was made.

[1282] "Inventory data" refers to information about the current quantity and types of goods and materials owned by households, businesses, etc.

[1283] "Partner companies" refer to companies such as food manufacturers and retailers that provide advertising, coupon information, and inventory data to the system.

[1284] "Advertising" refers to information provided by partner companies for the purpose of promoting the sale of goods or services.

[1285] "Coupon information" refers to information that indicates the right or conditions for purchasing specific products or services at a discounted price.

[1286] A "server" refers to a central system that integrates and analyzes data, generates menus, creates suggestions, and notifies users, and is a computer system that works in conjunction with a database.

[1287] "Push notifications" refer to a function that automatically sends information to smartphones and other devices even when the user does not have the application open.

[1288] "Recommended menu" refers to meal suggestions generated by the server, taking into account the user's preferences and nutritional balance.

[1289] "Purchase location" refers to a specific retail store or online store suggested to the user for purchasing an out-of-stock item.

[1290] "Targeted advertising" refers to advertisements that are customized for specific user groups based on their interests and past behavior.

[1291] An "API" refers to an interface for exchanging data between different software systems, and is used, for example, to send data from a user terminal to a server or to retrieve data from a partner company.

[1292] Modes for carrying out the invention

[1293] Embodiments of this invention are systems that collect user purchase history data and inventory data, and retrieve advertisements, coupon information, and inventory data provided by partner companies. The following details how this system works.

[1294] System Configuration

[1295] 1. User terminal

[1296] User terminals include devices such as smartphones, tablets, and personal computers, which users can use to input purchase history, record inventory data, receive system suggestions, and check push notifications.

[1297] 2. Server

[1298] The server is the central management system at the heart of this system. The server is linked to a database that receives purchase history data and inventory data from users, as well as advertisements, coupon information, and inventory data from partner companies, and then integrates, analyzes, and generates recommendations.

[1299] 3. Partner companies

[1300] Partner companies, such as food manufacturers and retailers, provide advertising, coupon information, and inventory data to the server.

[1301] Program processing

[1302] Data collection

[1303] Users enter their purchase history and record their household inventory through a smartphone app or web portal. Purchase history data includes details such as date, product name, and store of purchase, while inventory data includes the types and quantities of products they have at home. This data is sent to the server via an API.

[1304] Retrieving external data

[1305] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via APIs. This data is organized and stored in the server's database and integrated with user purchase history data and inventory data.

[1306] Data Integration and Analysis

[1307] The server uses integrated data to build machine learning models and analyze user preferences and past purchasing patterns. This allows it to predict what products users currently need and what products they are likely to purchase in the future. Furthermore, it cross-references this data with inventory data provided by partner suppliers to identify out-of-stock items.

[1308] Suggestions for meal menus and stores where to purchase them.

[1309] Based on the analysis results, the server generates meal recommendations that take into account the user's preferences and nutritional balance. For example, for a user who has frequently consumed tomatoes and chicken in the past, it will suggest "Tomato and Chicken Pasta." It will also suggest stores where users can purchase any missing ingredients (e.g., chicken) based on the recommended recipe. At this time, it will consider any provided coupons or special offers to select the store that is most advantageous to the user.

[1310] Notification of results

[1311] The user's device will notify them of the suggestions via push notifications or in-app messages. The notifications will include recommended meal menus, a list of necessary ingredients, suggested stores for purchase, and available coupon information. Users can review these notifications, purchase items at the recommended stores, and create the suggested menu.

[1312] Hardware and software to be used

[1313] Hardware: Smartphones (iOS, Android), tablets, PCs, servers (including cloud-based databases).

[1314] Software: Python (used for data collection and analysis), Requests (HTTP library), JSON (data format), machine learning frameworks (e.g., TensorFlow and Scikit-learn).

[1315] Specific example

[1316] 1. User A enters their recent purchase history of tomatoes and chicken into a smartphone app.

[1317] 2. The terminal sends information to the server indicating that there are tomatoes in the household inventory but no chicken.

[1318] 3. The server retrieves coupon information for "30% off chicken" and inventory data from retailers via API.

[1319] 4. The server identifies from past usage history that user A prefers to use tomatoes and chicken, and analyzes that there is currently a shortage of chicken.

[1320] 5. The server generates a menu for "Tomato and Chicken Pasta" and suggests purchasing chicken from a retail store. The suggestion also includes discount information if a coupon is used.

[1321] 6. The terminal notifies user A of the menu and coupon information for "Tomato and Chicken Pasta".

[1322] 7. User A checks the notification, buys chicken from a retail store, and creates a menu.

[1323] Example of a prompt

[1324] Enter the following prompt into the generative AI model:

[1325] Based on the user's purchase history and inventory data, please suggest the most suitable products and menu items for that user. Please also consider the latest coupon information obtained from partner companies. Please use the following history and inventory data.

[1326] Purchase history data: Tomatoes, chicken

[1327] Inventory data: Tomatoes: 2, Chicken: 0

[1328] Coupon information: Chicken: 30% off

[1329] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1330] Step 1:

[1331] Users input or scan purchase history data using a smartphone app. For example, if they purchase tomatoes and chicken, they input the date, product names, and store details. The input data is sent to the server via an API.

[1332] Input: Purchase history data (e.g., tomatoes, chicken), date, store of purchase

[1333] Output: Data sent to the server via the API

[1334] Step 2:

[1335] Users record their household inventory data using their smartphones. For example, if they have 2 tomatoes and 0 chickens, they can take a photo or enter the data as text. This data is also sent to the server via an API.

[1336] Input: Inventory data (Example: Tomatoes: 2, Chicken: 0)

[1337] Output: Data sent to the server via the API

[1338] Step 3:

[1339] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies using APIs. For example, this includes coupon information and inventory status for "30% off chicken." This data is stored in the server's database.

[1340] Input: Advertisements, coupon information, and inventory data from partner companies.

[1341] Output: Data stored in the database on the server

[1342] Step 4:

[1343] The server integrates purchase history data, inventory data, and data from partner suppliers, and uses machine learning models to analyze user preferences and past purchasing patterns. This allows it to predict what products users currently need and what products they may purchase in the future.

[1344] Input: Purchase history data, inventory data, advertisements and coupon information from partner companies.

[1345] Output: Analysis results based on user preferences and purchasing patterns

[1346] Step 5:

[1347] The server checks inventory data and identifies out-of-stock items. For example, it might detect that the chicken inventory is zero. Based on this information, it generates recommended menu items.

[1348] Input: Integrated data, inventory data

[1349] Output: Out-of-stock items and recommended menu items

[1350] Step 6:

[1351] The server suggests the best store to purchase recommended meals and any missing items from the user. It also takes into account coupons and special offers provided by partner companies.

[1352] Input: Out-of-stock items, coupon information from partner companies

[1353] Output: Recommended menu items and suggested stores for purchase.

[1354] Step 7:

[1355] The device will send push notifications to the user with recommended menus and store information from the server. The notifications will include recommended meal menus, a list of necessary ingredients, suggested stores, and available coupon information.

[1356] Input: Recommended menu items and purchase store information from the server.

[1357] Output: Push notification to the user

[1358] By executing the above processing steps in order, users can efficiently manage their purchase history and inventory data and receive suggestions for the most suitable products and menus. In addition, partner businesses can effectively promote their products through targeted advertising and coupon distribution.

[1359] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1360] This embodiment of the invention relates to a system that collects user purchase history data and inventory data, and obtains advertising, coupon information, and inventory data from partner companies, and combines this with an emotion engine to suggest the optimal meal menu based on the user's emotions. The details are described below.

[1361] System Configuration

[1362] 1. User terminal

[1363] User terminals include devices such as smartphones, tablets, and personal computers, which users can use to input purchase history, record inventory data, provide emotional input using an emotion engine, and receive suggestions from the system.

[1364] 2. Server

[1365] The server is a central system that integrates, analyzes, recognizes sentiment, generates menus, creates suggestions, and notifies users. The database works in conjunction with it, managing information from users and data from partner companies.

[1366] 3. Partner companies

[1367] Partners include food manufacturers and retailers, who provide advertising, coupon information, and inventory data to the server.

[1368] 4. Emotional Engine

[1369] An emotion engine is software or hardware that recognizes emotions from a user's facial expressions and voice and generates emotion data. This emotion data reflects the user's current mental state, and menu suggestions are made based on it.

[1370] Program Processing Description

[1371] 1. Data Collection

[1372] Users enter or scan their purchase history via a smartphone app or web portal. This data includes details such as date, product name, and store of purchase.

[1373] Users can record their household inventory by taking photos of ingredients with their smartphone camera or manually entering text.

[1374] The terminal sends the collected purchase history data and inventory data to the server via API.

[1375] 2. Acquisition of external data

[1376] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. This data includes product discounts, special offers, and in-store inventory status.

[1377] The server organizes the acquired data and stores it in the database.

[1378] 3. Acquisition of emotional data

[1379] Users register their emotional states through a smartphone app using facial recognition cameras and voice input. The emotion engine recognizes the user's emotions from these inputs and generates emotion data.

[1380] The device sends the generated emotion data to the server via an API.

[1381] 4. Data Integration and Analysis

[1382] The server integrates and centrally manages purchase history, inventory data, and sentiment data.

[1383] The server uses machine learning algorithms to analyze the user's past purchasing patterns, food consumption rate, and emotional data.

[1384] The server compares the user's current inventory data with the inventory data of partner suppliers to identify out-of-stock ingredients.

[1385] 5. Menu and store suggestions

[1386] The server generates an optimal meal plan considering the user's preferences, nutritional balance, and emotional state. For example, if the user is feeling stressed, it will suggest a menu that includes ingredients that help alleviate stress.

[1387] The server suggests the best store to purchase any missing ingredients (e.g., chicken). In doing so, it considers any coupons or special offers provided to select the store that is most advantageous to the user.

[1388] The server sends the generated menu and purchase store information to the user's terminal via API.

[1389] 6. Notification of Results and Purchase Information

[1390] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include suggested menus, a list of necessary ingredients, stores where to purchase them, and available coupon information.

[1391] The user checks the notification and purchases the ingredients needed to make the suggested menu.

[1392] Specific example

[1393] 1. Data collection:

[1394] User A enters their recent purchase history of tomatoes and chicken through a smartphone app.

[1395] The device sends information to the server indicating that there are tomatoes in the household inventory but no chicken.

[1396] 2. Obtaining external data:

[1397] The server retrieves coupon information for "30% off chicken" and inventory data from retailers via API.

[1398] 3. Acquisition of emotional data:

[1399] User A uses the app's facial recognition function to register with the emotion engine that they are feeling stressed.

[1400] The device sends emotional data to the server.

[1401] 4. Data Integration and Analysis:

[1402] The server identifies from past usage history that user A prefers to use tomatoes and chicken, and analyzes that there is currently a shortage of chicken.

[1403] The server takes into account that user A is experiencing stress and includes suggestions for foods that can help alleviate stress.

[1404] 5. Menu and store suggestions:

[1405] The server generates a menu item called "Tomato and Chicken Pasta" and suggests that the user purchase chicken from a retail store.

[1406] The server displays a coupon from a retail store, offering 30% off chicken.

[1407] 6. Notification of results and purchase information:

[1408] The terminal notifies user A of the menu item "Tomato and Chicken Pasta" and coupon information.

[1409] User A checks the notification, buys chicken at a retail store, and prepares the suggested menu.

[1410] In this way, users can efficiently manage ingredients and easily prepare meals that consider nutritional balance and emotional state. Furthermore, partner businesses can effectively conduct targeted advertising and contribute to reducing food waste.

[1411] The following describes the processing flow.

[1412] Step 1:

[1413] Users log in to their accounts via a smartphone app or web portal.

[1414] Step 2:

[1415] Users can manually enter their purchase history or scan loyalty cards or receipts from partner retailers. When doing so, they will enter or scan details such as product name, purchase date, price, and store location.

[1416] Step 3:

[1417] The device sends the entered or scanned purchase history data to the server via an API.

[1418] Step 4:

[1419] Users can record their household inventory by taking photos of ingredients with their smartphone camera or by manually entering text.

[1420] Step 5:

[1421] The terminal sends recorded inventory data to the server via an API. The data includes information such as the type and quantity of ingredients and their expiration dates.

[1422] Step 6:

[1423] Users register their emotional states (stress, joy, sadness, etc.) with the emotion engine using the app's facial recognition and voice input functions.

[1424] Step 7:

[1425] The emotion engine generates recognized emotion data and sends it to the server.

[1426] Step 8:

[1427] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. The retrieved data includes product sale information and inventory status.

[1428] Step 9:

[1429] The server integrates user-specific purchase history data, inventory data, and sentiment data, and stores it in a database. This data is used for later analysis.

[1430] Step 10:

[1431] The server uses machine learning algorithms to analyze the user's past purchasing patterns, food consumption rate, and emotional data. In doing so, it identifies the user's preferences and frequently purchased items.

[1432] Step 11:

[1433] The server compares the user's current inventory data with the inventory data of partner suppliers to identify out-of-stock ingredients. For example, it might identify a situation where tomatoes are in stock but chicken is in short supply.

[1434] Step 12:

[1435] The server generates meal menus considering the user's preferences, nutritional balance, and emotional state. If the user is stressed, it suggests a menu that includes ingredients that help alleviate stress. For example, if the user is stressed, it might suggest "tomato and chicken pasta."

[1436] Step 13:

[1437] The server suggests purchasing the missing ingredient (in this case, chicken) from the most suitable retailer. It considers coupon information from partner suppliers to select the store that offers the best deal for the user. For example, it might say, "A coupon for 30% off chicken is available at Retailer B."

[1438] Step 14:

[1439] The server sends the generated menu and purchase store information to the user's terminal via API.

[1440] Step 15:

[1441] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include suggested menus, a list of necessary ingredients, store locations, and available coupon information.

[1442] Step 16:

[1443] The user checks the notification and purchases any missing ingredients to create the suggested menu. For example, the user purchases chicken from retailer B.

[1444] Step 17:

[1445] After a purchase, the user updates the inventory status in the app and sends that information back to the server. This ensures that the latest inventory information is reflected in the next offer.

[1446] This system allows users to easily manage available ingredients and obtain optimal meal menus tailored to their emotional state and preferences. Furthermore, partner businesses can enhance the effectiveness of their targeted advertising and contribute to reducing food waste.

[1447] (Example 2)

[1448] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1449] Traditional purchase history and inventory management systems have been unable to make suggestions that take into account the user's emotional state, making it difficult to increase consumer satisfaction. Furthermore, systems that suggest meal menus considering consumer preferences and nutritional balance are limited, making it difficult to support food waste reduction and efficient purchasing behavior. Therefore, there is a need for a system that suggests optimal meal menus that reflect the user's emotional state and effectively promotes the purchase of necessary ingredients.

[1450] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting purchase history data from the user, means for collecting the user's inventory data, means for collecting advertisements, coupon information and inventory data from partner companies, means for acquiring the user's emotional data, means for integrating the purchase history data, inventory data and emotional data to analyze the user's preferences and past purchasing patterns, means for comparing the user's inventory data with the partner company's inventory data to identify out-of-stock ingredients, means for generating meal menus considering the user's preferences, nutritional balance and emotional state, means for suggesting ingredients to be purchased and the stores where they can be purchased, and means for notifying the user of the suggestion results. This makes it possible to suggest optimal meal menus that reflect the user's emotional state and purchasing patterns and to support efficient purchasing behavior.

[1451] "Purchase history data" refers to data containing information about products that a user has purchased in the past. This data includes details such as product name, purchase date and time, store of purchase, and quantity.

[1452] "Inventory data" refers to data containing information about the food and products a user currently owns in their home. This data includes information such as the name of the food item, the quantity, and the expiration date.

[1453] "Advertising" refers to information provided by partner companies to promote specific products or services. This information includes product descriptions, special offers, and promotional details.

[1454] "Coupon information" refers to information that allows you to receive a discount on a specific product or service. This information includes coupon codes, discount rates, terms and conditions, and expiration dates.

[1455] "Partner companies" are businesses such as food manufacturers and retailers that provide data in conjunction with the system.

[1456] "Emotional data" refers to data about a user's emotional state. This data is obtained from the user's facial expressions and voice, and reflects emotional states such as happiness, anxiety, and stress.

[1457] An "emotion engine" is software or hardware that analyzes a user's facial expressions and voice to recognize their emotions and generate emotional data.

[1458] "Data integration" is the process of centrally managing and linking different types of data (such as purchase history data, inventory data, and sentiment data).

[1459] "Data analysis" is the process of analyzing user preferences, past purchasing patterns, food consumption rates, emotional states, and other factors based on integrated data.

[1460] A "meal menu" is a list of recipes and ingredients for creating a specific meal. This list is generated taking into account the user's preferences, nutritional balance, and emotional state.

[1461] "Suggestion results" refer to the suggestions generated by the system, such as meal menus, stores to purchase from, and coupon information.

[1462] A "notification" is an action taken to inform the user of the results of a system suggestion. This includes push notifications, in-app messages, and so on.

[1463] This invention relates to a system that collects user purchase history data, inventory data, advertisements and coupon information from partner companies, and sentiment data, and integrates and analyzes this data to suggest the optimal meal menu based on the user's emotions. The details are described below.

[1464] System Configuration

[1465] 1. User terminal

[1466] User terminals include smartphones, tablets, and personal computers. Using these terminals, users can input purchase history, record inventory data, provide emotional input using an emotion engine, and receive suggestions from the system.

[1467] 2. Server

[1468] The server is a central system that integrates, analyzes, recognizes sentiment, generates menus, creates suggestions, and notifies users. The server is connected to a database that centrally manages user information and data from partner companies.

[1469] 3. Partner companies

[1470] Partner companies include food manufacturers and retailers, and their role is to provide advertising, coupon information, and inventory data to the server.

[1471] 4. Emotional Engine

[1472] An emotion engine is software or hardware that recognizes emotions from a user's facial expressions and voice and generates emotion data. This emotion data reflects the user's mental state, and menu suggestions are made based on it.

[1473] Program Processing Description

[1474] Data collection

[1475] Users input or scan their purchase history through a smartphone app or web portal. For example, scanning a receipt with a smartphone camera allows the app to automatically recognize the date, product name, and store of purchase.

[1476] Users can record their household inventory by taking photos of ingredients with their smartphone camera or manually entering text.

[1477] The terminal sends the collected purchase history data and inventory data to the server via API.

[1478] Retrieving external data

[1479] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. This data includes product discounts, special offers, and in-store inventory status.

[1480] The server organizes the acquired data and stores it in the database.

[1481] Acquisition of emotional data

[1482] Users register their emotional states through a smartphone app using facial recognition cameras and voice input. The emotion engine recognizes the user's emotions from these inputs and generates emotion data.

[1483] The device sends the generated emotion data to the server via an API.

[1484] Data Integration and Analysis

[1485] The server integrates and centrally manages purchase history data, inventory data, and sentiment data.

[1486] The server uses machine learning algorithms to analyze the user's past purchasing patterns, food consumption rate, and emotional data.

[1487] The server compares the user's current inventory data with the inventory data of partner suppliers to identify out-of-stock ingredients.

[1488] Menu and store suggestions

[1489] The server generates an optimal meal plan considering the user's preferences, nutritional balance, and emotional state. For example, if the user is feeling stressed, it will suggest a menu that includes ingredients that help alleviate stress.

[1490] The server suggests the best store to purchase any missing ingredients. In doing so, it considers any coupons or special offers provided to select the most beneficial store for the user.

[1491] The server sends the generated menu and purchase store information to the user's terminal via API.

[1492] Notification of results and purchase information

[1493] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include suggested menus, a list of necessary ingredients, stores where to purchase them, and available coupon information.

[1494] The user checks the notification and purchases the ingredients needed to make the suggested menu.

[1495] Specific example

[1496] 1. Data collection:

[1497] User A enters their recent purchase history of tomatoes and chicken into a smartphone app. The app automatically recognizes the product name, date, and store, and digitizes the data.

[1498] The device sends that data to the server.

[1499] 2. Obtaining external data:

[1500] The server retrieves coupon information for "30% off chicken" and inventory data from retailers via API.

[1501] 3. Acquisition of emotional data:

[1502] User A uses the app's facial recognition function to register with the emotion engine that they are feeling stressed.

[1503] The device sends that emotional data to the server.

[1504] 4. Data Integration and Analysis:

[1505] The server identifies from past usage history that user A prefers to use tomatoes and chicken, and analyzes that there is currently a shortage of chicken.

[1506] The server takes into account that user A is experiencing stress and includes suggestions for foods that can help alleviate stress.

[1507] 5. Menu and store suggestions:

[1508] The server generates a menu item called "Tomato and Chicken Pasta" and suggests that the user purchase chicken from a retail store.

[1509] The server displays a coupon from a retail store, offering 30% off chicken.

[1510] 6. Notification of results and purchase information:

[1511] The device notifies user A of the menu item "Tomato and Chicken Pasta" and coupon information.

[1512] User A checks the notification, buys chicken at a retail store, and prepares the suggested menu.

[1513] This processing flow allows users to efficiently manage ingredients and easily receive meal menu suggestions that take nutritional balance and emotional state into consideration. Furthermore, partner companies can effectively implement targeted advertising and contribute to reducing food waste.

[1514] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1515] Step 1: Data Collection

[1516] Users enter their purchase history or scan receipts using a smartphone app. For example, if a user takes a picture of a receipt with their smartphone camera, the app automatically recognizes the date, product name, and store of purchase, and saves this data digitally. This data includes the user ID, product name, quantity, and purchase date.

[1517] Users record their household inventory by taking photos of ingredients with their smartphone camera or manually entering text. This data includes the name of the ingredient, the quantity, and the expiration date.

[1518] The device sends collected purchase history data and inventory data to the server via API. The server stores the received data in a database.

[1519] Step 2: Obtaining external data

[1520] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. This data includes product discounts, special offers, and in-store inventory status.

[1521] The server organizes the acquired external data and stores it in a database. The organized data is then categorized for later analysis and matching.

[1522] Step 3: Acquisition of emotional data

[1523] Users register their emotional states through a smartphone app. For example, by taking a picture of their face with the app's facial recognition camera, the emotion engine analyzes the expression. Alternatively, users can record their emotional states using voice input.

[1524] The emotion engine recognizes the user's emotions from their facial expressions and voice, and generates emotion data such as "happiness," "anxiety," and "stress."

[1525] The device sends the generated emotion data to the server via an API.

[1526] Step 4: Data Integration and Analysis

[1527] The server integrates and centrally manages purchase history data, inventory data, and sentiment data collected from users. This integration process links related data using the user ID as the key.

[1528] The server uses machine learning algorithms to analyze this integrated data. Specifically, it analyzes the user's past purchasing patterns, food consumption rate, and emotional data to predict the user's purchasing behavior and preferences. This analysis results include, for example, the food items the user consumed the most in the past month and the products they purchased the most.

[1529] The server matches the user's current inventory data with that of partner suppliers to identify any ingredients currently lacking in the household. This generates a list of ingredients the user should purchase.

[1530] Step 5: Menu and store suggestions

[1531] The server generates an optimal meal plan considering the user's preferences, nutritional balance, and emotional state. For example, if the user is feeling stressed, a menu including ingredients with relaxing properties will be suggested.

[1532] The server suggests the best store to purchase any missing ingredients. Based on provided coupons and special offers, it selects the store that will benefit the user the most. For example, it might suggest information such as "Chicken is 30% off at a nearby supermarket."

[1533] The server sends the generated menu and purchase store information to the user's terminal via API.

[1534] Step 6: Notification of results and purchase information

[1535] The device displays suggestions to the user via push notifications and in-app messages. These notifications include suggested menus, a list of necessary ingredients, stores where to purchase them, and available coupon information. Specifically, it displays a recipe for "Tomato and Chicken Pasta" and its required ingredients.

[1536] Users check the notification and purchase ingredients to create the suggested menu. They reduce costs by using the notified coupon information to purchase the necessary ingredients at their nearest supermarket.

[1537] The above outlines the processing steps of this system. In each step, the user, terminal, and server work together to collect, analyze, and propose data, thereby enabling the suggestion of the optimal meal menu based on the user's emotional state and preferences.

[1538] (Application Example 2)

[1539] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1540] While conventional systems could suggest menus based on user purchase history and inventory data, they failed to consider the user's emotional state. Furthermore, they were inadequate in suggesting which stores to purchase ingredients from if those ingredients were in short supply. This resulted in an inability to suggest meals best suited to the user's mental state and preferences, and also increased the effort required for ingredient purchases.

[1541] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1542] In this invention, the server includes means for collecting purchase history data from users, means for collecting user inventory data, means for collecting advertisements, coupon information and inventory data from partner companies, means for collecting user emotional data, means for integrating the purchase history data, inventory data and emotional data to analyze the user's preferences, past purchase patterns and emotional state, means for comparing the user's inventory data with the partner company's inventory data to identify out-of-stock ingredients, means for generating meal menus considering the user's preferences, nutritional balance and emotional state, means for suggesting ingredients to purchase and where to purchase them, and means for notifying the user of the suggestion results. This makes it possible to suggest an optimal meal menu that takes the user's emotional state into consideration and efficiently guide the user to where to purchase the necessary ingredients.

[1543] "Purchase history data" refers to information about products that a user has purchased in the past, including details such as the date and time, product name, and place of purchase.

[1544] "Inventory data" refers to data showing the current availability of specific food items or products in a user's home or in the stores of partner companies.

[1545] "Advertising" refers to information provided to users for the purpose of promoting the sale of specific products or services offered by partner companies.

[1546] "Coupon information" refers to codes or vouchers issued by partner companies to users to offer discounts or benefits on specific products or services.

[1547] "Emotional data" refers to data that reflects the user's current emotional state, as recognized from their facial expressions and voice.

[1548] "Preferences" is a concept that refers to the products, foods, or specific habits and tastes that a user likes.

[1549] "Past purchasing patterns" refer to data that analyzes trends such as the types, frequency, and timing of products that users have purchased in the past.

[1550] "Out-of-stock ingredients" refer to specific ingredients that are not available in the user's home inventory or store inventory, but are necessary for creating a menu.

[1551] "Emotional state" refers to the mental state or mood that a user is currently experiencing, such as stress or happiness.

[1552] "Means for generating menus" refers to a process or system that automatically creates appropriate meal menus, taking into account the user's preferences, nutritional balance, and emotional state.

[1553] "Means of suggesting stores for purchase" refers to a process or system that identifies the best store for a user to purchase the necessary ingredients and presents that information to the user.

[1554] "Means of notifying the results of the proposal" refers to a process or system that provides users with information such as generated menus and purchase options via push notifications or in-app messages.

[1555] The embodiments for carrying out this invention will be described in detail below.

[1556] System Configuration

[1557] 1. User terminal

[1558] User terminals include devices such as smartphones, tablets, and personal computers, which users can use to input purchase history, record inventory data, provide emotional input using an emotion engine, and receive suggestions from the system.

[1559] 2. Server

[1560] The server is the central system responsible for data integration, analysis, sentiment recognition, menu generation, suggestion creation, and user notifications. The database works in conjunction with this server, managing user information and data from partner companies.

[1561] 3. Partner companies

[1562] Partner companies refer to organizations such as food-related businesses and retailers, and these companies provide advertising, coupon information, and inventory data to the server.

[1563] 4. Emotional Engine

[1564] An emotion engine is software or hardware that recognizes emotions from a user's facial expressions and voice and generates emotion data. This emotion data reflects the user's current mental state, and menu suggestions are made based on this data.

[1565] Program Processing Description

[1566] Hardware and software to be used

[1567] Hardware: Smartphone (iOS or Android)

[1568] Software: Python, TensorFlow (emotion recognition model), SQLite (database management), RESTful API (data communication)

[1569] 1. Data Collection

[1570] Users input their purchase history and inventory data through a smartphone application. They can also scan product barcodes using their smartphone's camera. The collected data is stored in an SQLite database.

[1571] 2. Acquisition of external data

[1572] The server periodically retrieves advertisements, coupon information, and inventory data from partner servers via a RESTful API and stores this data in an SQLite database.

[1573] 3. Acquisition of emotional data

[1574] When a user opens the app, their facial expressions and voice are analyzed using the smartphone's camera and microphone by an emotion engine (TensorFlow model). The generated emotion data is stored in an SQLite database.

[1575] 4. Data Integration and Analysis

[1576] The server integrates purchase history data, inventory data, and sentiment data stored in an SQLite database, and uses machine learning algorithms to analyze user preferences, past purchasing patterns, and emotional states.

[1577] 5. Menu generation and suggested stores for purchase.

[1578] Based on the analyzed data, the server generates an optimal menu that takes into account the user's preferences, nutritional balance, and emotional state, and identifies the necessary ingredients and where to purchase them. This information is also stored in an SQLite database.

[1579] 6. Notification of Results and Purchase Information

[1580] The generated menu and purchase store information will be sent to the user's device as a push notification or in-app message.

[1581] Examples and usage examples of prompt statements

[1582] Specific example

[1583] User B uses their smartphone at a physical store and enters their desire to make "tomato and chicken pasta" into the app.

[1584] The app scans user B's past purchase history and confirms that tomatoes are in stock but chicken is in short supply.

[1585] We retrieve coupon information from our partner suppliers and notify customers that there is a 30% off coupon for chicken.

[1586] Example of a prompt

[1587] "Based on the user's purchase history, please suggest the optimal meal menu that reflects their current emotional state."

[1588] "Use an emotion engine to recognize user emotions and guide them through the grocery purchase process, taking into account current inventory data and coupon information."

[1589] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1590] Step 1:

[1591] Users use a smartphone app to input purchase history and inventory data. Users scan product barcodes using their smartphone camera and enter the information into the app. The input data includes details such as product name, date, purchase location, and quantity. This information is sent from the device to a server and stored in an SQLite database.

[1592] Step 2:

[1593] The server periodically retrieves advertisements, coupon information, and inventory data from partner servers via a RESTful API. The retrieved data includes discount and special offer information, as well as in-store inventory status, transmitted from the partner servers. This data is stored by the server in an SQLite database.

[1594] Step 3:

[1595] The user inputs their emotional data via a smartphone app. The smartphone's camera and microphone are used to analyze facial expressions and voice using an emotion engine (TensorFlow model). The analyzed emotional data reflects the user's current emotional state (e.g., stress, happiness), and is sent from the device to a server and stored in an SQLite database.

[1596] Step 4:

[1597] The server integrates purchase history data, inventory data, and sentiment data stored in an SQLite database. This allows for analysis based on user preferences, past purchasing patterns, and emotional states. Machine learning algorithms are applied using Python scripts to identify specific user preferences and food consumption rates.

[1598] Step 5:

[1599] Based on the analysis results above, the server generates an optimal meal plan that takes into account the user's preferences, nutritional balance, and emotional state. The menu is generated using a Python script, and any missing ingredients are also identified. This missing ingredient information is cross-referenced with inventory data from partner suppliers, and suggestions are generated that include optimal purchasing locations and coupon information.

[1600] Step 6:

[1601] The server sends the generated menu and store information to the user's device. This information includes the suggested menu, a list of required ingredients, the store where to purchase the items, and any available coupons. The user reviews these suggestions within the smartphone app.

[1602] Step 7:

[1603] The user reviews the suggested menu and store information, then visits a physical store to purchase the necessary ingredients. The user uses a smartphone app to manage ingredients according to the suggested menu and refer to recipes. Through these steps, the user's purchasing experience is optimized based on their emotional state.

[1604] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1605] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1606] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1607] [Fourth Embodiment]

[1608] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1609] As shown in Figure 7, the 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.

[1610] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1611] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1612] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1613] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1614] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1615] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1616] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1617] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1618] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1619] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1620] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1621] Embodiments of this invention relate to a system that collects user purchase history data and inventory data, and obtains advertising, coupon information, and inventory data from partner companies. Details are described below.

[1622] System Configuration

[1623] 1. User terminal

[1624] User terminals include devices such as smartphones, tablets, and personal computers, which users can use to input purchase history, record inventory data, and receive suggestions from the system.

[1625] 2. Server

[1626] The server is a central system that integrates and analyzes data, generates menus, creates suggestions, and notifies users. The database works in conjunction with it, managing information from users and data from partner companies.

[1627] 3. Partner companies

[1628] Partners include food manufacturers and retailers, who provide advertising, coupon information, and inventory data to the server.

[1629] Program Processing Description

[1630] 1. Data Collection

[1631] Users enter or scan their purchase history via a smartphone app or web portal. This data includes details such as date, product name, and store of purchase.

[1632] Users can record their household inventory by taking photos of ingredients with their smartphone camera or manually entering text.

[1633] The terminal sends the purchase history data and inventory data entered by the user to the server via an API.

[1634] 2. Acquisition of external data

[1635] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. This data includes product discounts, special offers, and in-store inventory status.

[1636] The server organizes the acquired data and stores it in the database.

[1637] 3. Data Integration and Analysis

[1638] The server integrates and centrally manages purchase history data and inventory data collected for each user.

[1639] The server uses machine learning algorithms to analyze the user's past purchasing patterns and food consumption rate.

[1640] The server compares the user's current inventory data with that of partner suppliers to identify out-of-stock ingredients.

[1641] 4. Menu and store suggestions

[1642] The server generates the optimal meal menu considering the user's preferences and nutritional balance. For example, for a user who has frequently consumed tomatoes and chicken in the past, it will suggest "tomato and chicken pasta."

[1643] The server suggests the most suitable store to purchase ingredients the user is lacking (e.g., chicken). In doing so, it considers any coupons or special offers provided to select the store that is most advantageous to the user.

[1644] The server sends the generated menu and purchase store information to the user's terminal via the API.

[1645] 5. Notification of Results and Purchase Information

[1646] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include meal menus, lists of necessary ingredients, stores where to buy them, and available coupon information.

[1647] The user checks the notification and purchases the necessary ingredients from the suggested store.

[1648] Specific example

[1649] 1. Data collection:

[1650] User A enters their recent purchase history of tomatoes and chicken through a smartphone app.

[1651] The device sends information to the server indicating that there are tomatoes in the household inventory but no chicken.

[1652] 2. Obtaining external data:

[1653] The server retrieves coupon information for "30% off chicken" and inventory data from retailer B via API.

[1654] 3. Data Integration and Analysis:

[1655] The server identifies from past usage history that user A prefers to use tomatoes and chicken, and analyzes that there is currently a shortage of chicken.

[1656] 4. Menu and store suggestions:

[1657] The server generates a menu for "Tomato and Chicken Pasta" and suggests purchasing chicken from retailer B.

[1658] The server will show that you can get a 30% discount by using a coupon from retailer B.

[1659] 5. Notification of results and purchase information:

[1660] The terminal notifies user A of the menu and coupon information for "Tomato and Chicken Pasta".

[1661] User A checks the notification, buys chicken from retailer B, and creates a menu.

[1662] In this way, users can efficiently manage ingredients and easily prepare nutritionally balanced meals. Furthermore, partner companies can effectively deploy targeted advertising and contribute to reducing food waste.

[1663] The following describes the processing flow.

[1664] Step 1:

[1665] Users log in to their accounts via a smartphone app or web portal.

[1666] Step 2:

[1667] Users can manually enter their purchase history or scan loyalty cards or receipts from partner retailers. When doing so, they will enter or scan details such as product name, purchase date, price, and store location.

[1668] Step 3:

[1669] The device sends the entered or scanned purchase history data to the server via an API.

[1670] Step 4:

[1671] Users can record their household inventory by taking photos of ingredients with their smartphone camera or by manually entering text.

[1672] Step 5:

[1673] The terminal sends recorded inventory data to the server via an API. The data includes information such as the type and quantity of ingredients and their expiration dates.

[1674] Step 6:

[1675] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. The retrieved data includes product sale information and inventory status.

[1676] Step 7:

[1677] The server integrates user-specific purchase history and inventory data and stores it in a database. This stored data is used for later analysis.

[1678] Step 8:

[1679] The server uses machine learning algorithms to analyze the user's past purchasing patterns and food consumption rate. In this process, it identifies the user's preferences and frequently purchased items.

[1680] Step 9:

[1681] The server compares the user's current inventory data with the inventory data of partner suppliers to identify out-of-stock ingredients. For example, it might identify a situation where tomatoes are in stock but chicken is in short supply.

[1682] Step 10:

[1683] The server automatically generates meal menus, taking into account the user's preferences and nutritional balance. For example, it might suggest "tomato and chicken pasta" to a user who has previously enjoyed tomatoes and chicken.

[1684] Step 11:

[1685] The server suggests purchasing the missing ingredient (in this case, chicken) from the most suitable retailer. It considers coupon information from partner suppliers to select the most advantageous purchase location for the user. For example, it might say, "A 30% off coupon for chicken is available at Retailer B."

[1686] Step 12:

[1687] The server sends the generated menu and purchase store information to the user's terminal via API.

[1688] Step 13:

[1689] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include suggested menus, a list of necessary ingredients, store locations, and available coupon information.

[1690] Step 14:

[1691] The user checks the notification and purchases any missing ingredients to create the suggested menu. For example, the user purchases chicken from retailer B.

[1692] Step 15:

[1693] After a purchase, the user updates the inventory status in the app and sends that information back to the server. This ensures that the latest inventory information is reflected in the next offer.

[1694] This allows users to easily create nutritionally balanced meal plans, partner businesses to conduct effective targeted advertising, and contribute to reducing food waste.

[1695] (Example 1)

[1696] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1697] Traditionally, it has been difficult for users to manage their household ingredients while preparing nutritionally balanced meals. Furthermore, partner companies have faced challenges in effectively advertising based on user purchasing patterns, making food waste reduction a significant issue. A system was needed to solve these problems, improving user convenience and enhancing the marketing effectiveness of partner companies.

[1698] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1699] In this invention, the server includes means for analyzing purchase history data and inventory data using machine learning algorithms, means for identifying out-of-stock ingredients, and means for suggesting the optimal store for purchase and transmitting that information to the user terminal via an API. This streamlines the user's ingredient management and enables the suggestion of nutritionally balanced meals. Furthermore, partner companies can effectively deploy targeted advertising and contribute to reducing food waste.

[1700] "Purchase history data" refers to data containing information about products that a user has purchased in the past. Specifically, it includes details such as product name, store of purchase, and purchase date.

[1701] "Inventory data" refers to data containing information about the food and products currently in a household. Specifically, it includes details such as the name of the food item, the quantity, and its storage condition.

[1702] "Partner companies" refer to external companies and stores that provide advertising, coupon information, and inventory data in conjunction with the system.

[1703] "Advertising" refers to promotional information for products and services provided by partner companies.

[1704] "Coupon information" refers to information about discounts and benefits offered by partner companies.

[1705] A "machine learning algorithm" refers to computational techniques used to analyze data and find patterns and trends.

[1706] An "API" refers to an interface used to exchange functions between different software programs.

[1707] "Push notification" refers to a function that instantly sends information from the server to the user's device.

[1708] A "database" refers to a system for efficiently storing, searching, and managing large amounts of data.

[1709] "Centralized management" refers to the integrated management of different types of data in a single database or system.

[1710] "Preferences" refer to a user's tastes and preferences. Specifically, this includes the user's preferences for ingredients and products derived from past purchase data.

[1711] "Nutritional balance" refers to a state where the food a user consumes contains the necessary nutrients in appropriate amounts.

[1712] "Meal menu" refers to a list of meal recipes and dishes suggested to the user.

[1713] "Purchase store" refers to the store suggested to the user for purchasing ingredients or other products.

[1714] Embodiments of this invention relate to a system that collects user purchase history data and inventory data, and analyzes this data in combination with advertisements, coupon information, and inventory data from partner companies. This system enables users to manage their household inventory and receive suggestions for nutritionally balanced meal menus.

[1715] System Configuration

[1716] 1. User terminal

[1717] User terminals include devices such as smartphones, tablets, and personal computers. Users can use these devices to input purchase history, record inventory data, and receive suggestions from the system.

[1718] 2. Server

[1719] The server is a central system that integrates and analyzes data, generates menus, creates suggestions, and notifies users. The database works in conjunction with it, managing information from users and data from partner companies.

[1720] 3. Partner companies

[1721] Partners include food manufacturers and retailers, who provide advertising, coupon information, and inventory data to the server.

[1722] Hardware and software to be used

[1723] Hardware: Smartphones, tablets, PCs, servers, network infrastructure

[1724] Software: Smartphone apps, web portals, databases (e.g., MySQL, PostgreSQL), APIs, machine learning algorithms (e.g., Python's Scikit-learn, TensorFlow)

[1725] Data processing and calculations

[1726] Data collection

[1727] Users enter their purchase history through a smartphone app or web portal. This data includes details such as the date, product name, and store of purchase.

[1728] Users record their household inventory by taking photos of ingredients with their smartphone camera or manually entering text.

[1729] The device sends this purchase history data and inventory data to the server via an API.

[1730] Retrieving external data

[1731] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. This data includes product discounts, special offers, and in-store inventory status.

[1732] The server organizes the acquired data and stores it in the database.

[1733] Data Integration and Analysis

[1734] The server integrates and centrally manages purchase history data and inventory data collected for each user.

[1735] The server uses machine learning algorithms to analyze the user's past purchasing patterns and food consumption rate.

[1736] The server compares the user's current inventory data with that of partner suppliers to identify out-of-stock ingredients.

[1737] Menu and store suggestions

[1738] The server generates the optimal meal menu considering the user's preferences and nutritional balance. For example, for a user who frequently consumes tomatoes and chicken, it will suggest "Tomato and Chicken Pasta."

[1739] The server suggests the most suitable store to purchase any ingredients the user is lacking. In doing so, it selects the store that is most advantageous to the user, taking into account any coupons or special offers provided.

[1740] The server sends the generated menu and purchase store information to the user's terminal via an API.

[1741] Notification of results and purchase information

[1742] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include meal menus, lists of necessary ingredients, stores where to buy them, and available coupon information.

[1743] The user checks the notification and purchases the necessary ingredients from the suggested store.

[1744] Specific example

[1745] 1. Data collection:

[1746] User A enters their recent purchase history of tomatoes and chicken through a smartphone app.

[1747] The device sends information to the server indicating that there are tomatoes in the household inventory but no chicken.

[1748] 2. Obtaining external data:

[1749] The server retrieves coupon information for "30% off chicken" and inventory data from retail stores.

[1750] 3. Data Integration and Analysis:

[1751] The server identifies from past usage history that user A prefers to use tomatoes and chicken, and analyzes that there is currently a shortage of chicken.

[1752] 4. Menu and store suggestions:

[1753] The server generates a menu for "Tomato and Chicken Pasta" and suggests purchasing chicken from a retail store.

[1754] The server will show that you can get 30% off by using a retail coupon.

[1755] 5. Notification of results and purchase information:

[1756] The terminal notifies user A of the menu and coupon information for "Tomato and Chicken Pasta".

[1757] User A checks the notification, buys chicken from a retail store, and creates a menu.

[1758] In this way, this system helps users efficiently manage ingredients and easily prepare nutritionally balanced meals. Furthermore, partner businesses can effectively deploy targeted advertising and contribute to reducing food waste.

[1759] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1760] Step 1: Enter the user's purchase history.

[1761] The user launches a smartphone app or web portal and enters their purchase history. For example, they might use the app's barcode scanning function to enter purchase information for tomatoes and chicken.

[1762] Input: Product name, store of purchase, date of purchase

[1763] The device temporarily stores this purchase history data in storage and sends it to the server via an API.

[1764] Output: Purchase history data is sent to the server.

[1765] Step 2: Record household inventory

[1766] The user uses their smartphone camera to take a picture of the food items currently in their household inventory. For example, they might take a picture of tomatoes in their refrigerator.

[1767] Input: Photo of the ingredient, or manually entered name of the ingredient.

[1768] The terminal sends this inventory data to the server via an API.

[1769] Output: Inventory data is sent to the server.

[1770] Step 3: Obtain data from partner companies

[1771] The server periodically sends requests to partner vendors via API to retrieve the latest advertisements, coupon information, and inventory data.

[1772] Input: API request from partner company

[1773] The server retrieves, for example, coupon information for "30% off chicken" and inventory data from partner suppliers.

[1774] Output: Advertisements, coupon information, and inventory data from partner companies are stored on the server.

[1775] Step 4: Data Integration and Processing

[1776] The server performs a join operation to integrate the purchase history data and inventory data collected for each user. For example, it might combine a user's past purchase data and current inventory data into a single table.

[1777] Input: Purchase history data, inventory data

[1778] The server stores integrated data in a database and manages it centrally.

[1779] Output: Integrated purchase history data and inventory data

[1780] Step 5: Data Analysis

[1781] The server uses machine learning algorithms to analyze users' past purchasing patterns and food consumption rates. For example, it analyzes users' purchase history as time-series data to analyze trends in food consumption over certain periods.

[1782] Input: Integrated purchase history data, inventory data

[1783] The server compares the user's current inventory data with that of its partners to identify any out-of-stock ingredients. For example, the server might identify that chicken is currently in short supply.

[1784] Output: Analysis results of ingredient shortage information, purchasing patterns, and consumption speed.

[1785] Step 6: Menu Generation

[1786] The server generates the optimal meal menu considering the user's preferences and nutritional balance. For example, for a user who has frequently consumed tomatoes and chicken in the past, it will suggest "tomato and chicken pasta."

[1787] Input: User preference data, nutritional balance information, out-of-stock information

[1788] The server saves the generated meal menu to a database.

[1789] Output: Optimal meal plan

[1790] Step 7: Suggestion of a store to purchase from

[1791] The server suggests the most suitable store to purchase ingredients the user is lacking. For example, store selection is made considering coupon information and special offers. In this process, information such as a 30% discount on chicken at a retail store will be reflected.

[1792] Input: Out-of-stock information, advertisements and coupon information from partner companies

[1793] The server stores purchase information in a database and sends it to the user's terminal via an API.

[1794] Output: Optimal store information

[1795] Step 8: Notification of Results

[1796] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include meal menus, lists of necessary ingredients, stores where to buy them, and available coupon information. For example, it might notify the user of a "Tomato and Chicken Pasta" menu and coupon information.

[1797] Input: Suggestion results (menu, ingredient list, store where to buy, coupon information)

[1798] Output: Notification content to the user

[1799] Through these steps, users can efficiently manage ingredients and easily prepare nutritionally balanced meals. Furthermore, partner businesses can effectively deploy targeted advertising and contribute to reducing food waste.

[1800] (Application Example 1)

[1801] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1802] In recent years, there has been a growing demand for systems that suggest optimal products and services based on user purchasing behavior and inventory management. However, conventional systems have not adequately provided personalized recommendations tailored to user needs, and the use of coupons and special offers has been limited. Furthermore, there has been a lack of means to centrally manage and effectively analyze purchase history and inventory data. As a result, users have not been able to obtain the optimal purchasing experience, and companies have faced challenges in effective targeting.

[1803] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1804] In this invention, the server includes means for collecting purchase history data from users, means for collecting user inventory data, means for collecting advertisements, coupon information, and inventory data from partner companies, means for integrating the purchase history data and inventory data to analyze user preferences and past purchasing patterns, means for comparing user inventory data with partner company inventory data to identify out-of-stock items, means for generating meal recommendation menus considering user preferences and nutritional balance, means for recommending items to purchase and suggesting stores where to purchase them, and means for sending push notifications to users based on the suggested data. As a result, users can efficiently manage their purchase history and inventory data and receive recommendations for optimal products and menus. Furthermore, companies can implement effective targeted advertising and coupon distribution, leading to improved purchasing experiences and increased sales.

[1805] - A "user" is an individual or group that uses the system to provide purchase history data and inventory data, and receives suggestions for the most suitable products and menus.

[1806] "Purchase history data" refers to detailed information about products and services that a user has purchased in the past, and often includes information such as the date, product name, and store where the purchase was made.

[1807] "Inventory data" refers to information about the current quantity and types of goods and materials owned by households, businesses, etc.

[1808] "Partner companies" refer to companies such as food manufacturers and retailers that provide advertising, coupon information, and inventory data to the system.

[1809] "Advertising" refers to information provided by partner companies for the purpose of promoting the sale of goods or services.

[1810] "Coupon information" refers to information that indicates the right or conditions for purchasing specific products or services at a discounted price.

[1811] A "server" refers to a central system that integrates and analyzes data, generates menus, creates suggestions, and notifies users, and is a computer system that works in conjunction with a database.

[1812] "Push notifications" refer to a function that automatically sends information to smartphones and other devices even when the user does not have the application open.

[1813] "Recommended menu" refers to meal suggestions generated by the server, taking into account the user's preferences and nutritional balance.

[1814] "Purchase location" refers to a specific retail store or online store suggested to the user for purchasing an out-of-stock item.

[1815] "Targeted advertising" refers to advertisements that are customized for specific user groups based on their interests and past behavior.

[1816] An "API" refers to an interface for exchanging data between different software systems, and is used, for example, to send data from a user terminal to a server or to retrieve data from a partner company.

[1817] Modes for carrying out the invention

[1818] Embodiments of this invention are systems that collect user purchase history data and inventory data, and retrieve advertisements, coupon information, and inventory data provided by partner companies. The following details how this system works.

[1819] System Configuration

[1820] 1. User terminal

[1821] User terminals include devices such as smartphones, tablets, and personal computers, which users can use to input purchase history, record inventory data, receive system suggestions, and check push notifications.

[1822] 2. Server

[1823] The server is the central management system at the heart of this system. The server is linked to a database that receives purchase history data and inventory data from users, as well as advertisements, coupon information, and inventory data from partner companies, and then integrates, analyzes, and generates recommendations.

[1824] 3. Partner companies

[1825] Partner companies, such as food manufacturers and retailers, provide advertising, coupon information, and inventory data to the server.

[1826] Program processing

[1827] Data collection

[1828] Users enter their purchase history and record their household inventory through a smartphone app or web portal. Purchase history data includes details such as date, product name, and store of purchase, while inventory data includes the types and quantities of products they have at home. This data is sent to the server via an API.

[1829] Retrieving external data

[1830] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via APIs. This data is organized and stored in the server's database and integrated with user purchase history data and inventory data.

[1831] Data Integration and Analysis

[1832] The server uses integrated data to build machine learning models and analyze user preferences and past purchasing patterns. This allows it to predict what products users currently need and what products they are likely to purchase in the future. Furthermore, it cross-references this data with inventory data provided by partner suppliers to identify out-of-stock items.

[1833] Suggestions for meal menus and stores where to purchase them.

[1834] Based on the analysis results, the server generates meal recommendations that take into account the user's preferences and nutritional balance. For example, for a user who has frequently consumed tomatoes and chicken in the past, it will suggest "Tomato and Chicken Pasta." It will also suggest stores where users can purchase any missing ingredients (e.g., chicken) based on the recommended recipe. At this time, it will consider any provided coupons or special offers to select the store that is most advantageous to the user.

[1835] Notification of results

[1836] The user's device will notify them of the suggestions via push notifications or in-app messages. The notifications will include recommended meal menus, a list of necessary ingredients, suggested stores for purchase, and available coupon information. Users can review these notifications, purchase items at the recommended stores, and create the suggested menu.

[1837] Hardware and software to be used

[1838] Hardware: Smartphones (iOS, Android), tablets, PCs, servers (including cloud-based databases).

[1839] Software: Python (used for data collection and analysis), Requests (HTTP library), JSON (data format), machine learning frameworks (e.g., TensorFlow and Scikit-learn).

[1840] Specific example

[1841] 1. User A enters their recent purchase history of tomatoes and chicken into a smartphone app.

[1842] 2. The terminal sends information to the server indicating that there are tomatoes in the household inventory but no chicken.

[1843] 3. The server retrieves coupon information for "30% off chicken" and inventory data from retailers via API.

[1844] 4. The server identifies from past usage history that user A prefers to use tomatoes and chicken, and analyzes that there is currently a shortage of chicken.

[1845] 5. The server generates a menu for "Tomato and Chicken Pasta" and suggests purchasing chicken from a retail store. The suggestion also includes discount information if a coupon is used.

[1846] 6. The terminal notifies user A of the menu and coupon information for "Tomato and Chicken Pasta".

[1847] 7. User A checks the notification, buys chicken from a retail store, and creates a menu.

[1848] Example of a prompt

[1849] Enter the following prompt into the generative AI model:

[1850] Based on the user's purchase history and inventory data, please suggest the most suitable products and menu items for that user. Please also consider the latest coupon information obtained from partner companies. Please use the following history and inventory data.

[1851] Purchase history data: Tomatoes, chicken

[1852] Inventory data: Tomatoes: 2, Chicken: 0

[1853] Coupon information: Chicken: 30% off

[1854] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1855] Step 1:

[1856] Users input or scan purchase history data using a smartphone app. For example, if they purchase tomatoes and chicken, they input the date, product names, and store details. The input data is sent to the server via an API.

[1857] Input: Purchase history data (e.g., tomatoes, chicken), date, store of purchase

[1858] Output: Data sent to the server via the API

[1859] Step 2:

[1860] Users record their household inventory data using their smartphones. For example, if they have 2 tomatoes and 0 chickens, they can take a photo or enter the data as text. This data is also sent to the server via an API.

[1861] Input: Inventory data (Example: Tomatoes: 2, Chicken: 0)

[1862] Output: Data sent to the server via the API

[1863] Step 3:

[1864] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies using APIs. For example, this includes coupon information and inventory status for "30% off chicken." This data is stored in the server's database.

[1865] Input: Advertisements, coupon information, and inventory data from partner companies.

[1866] Output: Data stored in the database on the server

[1867] Step 4:

[1868] The server integrates purchase history data, inventory data, and data from partner suppliers, and uses machine learning models to analyze user preferences and past purchasing patterns. This allows it to predict what products users currently need and what products they may purchase in the future.

[1869] Input: Purchase history data, inventory data, advertisements and coupon information from partner companies.

[1870] Output: Analysis results based on user preferences and purchasing patterns

[1871] Step 5:

[1872] The server checks inventory data and identifies out-of-stock items. For example, it might detect that the chicken inventory is zero. Based on this information, it generates recommended menu items.

[1873] Input: Integrated data, inventory data

[1874] Output: Out-of-stock items and recommended menu items

[1875] Step 6:

[1876] The server suggests the best store to purchase recommended meals and any missing items from the user. It also takes into account coupons and special offers provided by partner companies.

[1877] Input: Out-of-stock items, coupon information from partner companies

[1878] Output: Recommended menu items and suggested stores for purchase.

[1879] Step 7:

[1880] The device will send push notifications to the user with recommended menus and store information from the server. The notifications will include recommended meal menus, a list of necessary ingredients, suggested stores, and available coupon information.

[1881] Input: Recommended menu items and purchase store information from the server.

[1882] Output: Push notification to the user

[1883] By executing the above processing steps in order, users can efficiently manage their purchase history and inventory data and receive suggestions for the most suitable products and menus. In addition, partner businesses can effectively promote their products through targeted advertising and coupon distribution.

[1884] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1885] This embodiment of the invention relates to a system that collects user purchase history data and inventory data, and obtains advertising, coupon information, and inventory data from partner companies, and combines this with an emotion engine to suggest the optimal meal menu based on the user's emotions. The details are described below.

[1886] System Configuration

[1887] 1. User terminal

[1888] User terminals include devices such as smartphones, tablets, and personal computers, which users can use to input purchase history, record inventory data, provide emotional input using an emotion engine, and receive suggestions from the system.

[1889] 2. Server

[1890] The server is a central system that integrates, analyzes, recognizes sentiment, generates menus, creates suggestions, and notifies users. The database works in conjunction with it, managing information from users and data from partner companies.

[1891] 3. Partner companies

[1892] Partners include food manufacturers and retailers, who provide advertising, coupon information, and inventory data to the server.

[1893] 4. Emotional Engine

[1894] An emotion engine is software or hardware that recognizes emotions from a user's facial expressions and voice and generates emotion data. This emotion data reflects the user's current mental state, and menu suggestions are made based on it.

[1895] Program Processing Description

[1896] 1. Data Collection

[1897] Users enter or scan their purchase history via a smartphone app or web portal. This data includes details such as date, product name, and store of purchase.

[1898] Users can record their household inventory by taking photos of ingredients with their smartphone camera or manually entering text.

[1899] The terminal sends the collected purchase history data and inventory data to the server via API.

[1900] 2. Acquisition of external data

[1901] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. This data includes product discounts, special offers, and in-store inventory status.

[1902] The server organizes the acquired data and stores it in the database.

[1903] 3. Acquisition of emotional data

[1904] Users register their emotional states through a smartphone app using facial recognition cameras and voice input. The emotion engine recognizes the user's emotions from these inputs and generates emotion data.

[1905] The device sends the generated emotion data to the server via an API.

[1906] 4. Data Integration and Analysis

[1907] The server integrates and centrally manages purchase history, inventory data, and sentiment data.

[1908] The server uses machine learning algorithms to analyze the user's past purchasing patterns, food consumption rate, and emotional data.

[1909] The server compares the user's current inventory data with the inventory data of partner suppliers to identify out-of-stock ingredients.

[1910] 5. Menu and store suggestions

[1911] The server generates an optimal meal plan considering the user's preferences, nutritional balance, and emotional state. For example, if the user is feeling stressed, it will suggest a menu that includes ingredients that help alleviate stress.

[1912] The server suggests the best store to purchase any missing ingredients (e.g., chicken). In doing so, it considers any coupons or special offers provided to select the store that is most advantageous to the user.

[1913] The server sends the generated menu and purchase store information to the user's terminal via API.

[1914] 6. Notification of Results and Purchase Information

[1915] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include suggested menus, a list of necessary ingredients, stores where to purchase them, and available coupon information.

[1916] The user checks the notification and purchases the ingredients needed to make the suggested menu.

[1917] Specific example

[1918] 1. Data collection:

[1919] User A enters their recent purchase history of tomatoes and chicken through a smartphone app.

[1920] The device sends information to the server indicating that there are tomatoes in the household inventory but no chicken.

[1921] 2. Obtaining external data:

[1922] The server retrieves coupon information for "30% off chicken" and inventory data from retailers via API.

[1923] 3. Acquisition of emotional data:

[1924] User A uses the app's facial recognition function to register with the emotion engine that they are feeling stressed.

[1925] The device sends emotional data to the server.

[1926] 4. Data Integration and Analysis:

[1927] The server identifies from past usage history that user A prefers to use tomatoes and chicken, and analyzes that there is currently a shortage of chicken.

[1928] The server takes into account that user A is experiencing stress and includes suggestions for foods that can help alleviate stress.

[1929] 5. Menu and store suggestions:

[1930] The server generates a menu item called "Tomato and Chicken Pasta" and suggests that the user purchase chicken from a retail store.

[1931] The server displays a coupon from a retail store, offering 30% off chicken.

[1932] 6. Notification of results and purchase information:

[1933] The terminal notifies user A of the menu item "Tomato and Chicken Pasta" and coupon information.

[1934] User A checks the notification, buys chicken at a retail store, and prepares the suggested menu.

[1935] In this way, users can efficiently manage ingredients and easily prepare meals that consider nutritional balance and emotional state. Furthermore, partner businesses can effectively conduct targeted advertising and contribute to reducing food waste.

[1936] The following describes the processing flow.

[1937] Step 1:

[1938] Users log in to their accounts via a smartphone app or web portal.

[1939] Step 2:

[1940] Users can manually enter their purchase history or scan loyalty cards or receipts from partner retailers. When doing so, they will enter or scan details such as product name, purchase date, price, and store location.

[1941] Step 3:

[1942] The device sends the entered or scanned purchase history data to the server via an API.

[1943] Step 4:

[1944] Users can record their household inventory by taking photos of ingredients with their smartphone camera or by manually entering text.

[1945] Step 5:

[1946] The terminal sends recorded inventory data to the server via an API. The data includes information such as the type and quantity of ingredients and their expiration dates.

[1947] Step 6:

[1948] Users register their emotional states (stress, joy, sadness, etc.) with the emotion engine using the app's facial recognition and voice input functions.

[1949] Step 7:

[1950] The emotion engine generates recognized emotion data and sends it to the server.

[1951] Step 8:

[1952] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. The retrieved data includes product sale information and inventory status.

[1953] Step 9:

[1954] The server integrates user-specific purchase history data, inventory data, and sentiment data, and stores it in a database. This data is used for later analysis.

[1955] Step 10:

[1956] The server uses machine learning algorithms to analyze the user's past purchasing patterns, food consumption rate, and emotional data. In doing so, it identifies the user's preferences and frequently purchased items.

[1957] Step 11:

[1958] The server compares the user's current inventory data with the inventory data of partner suppliers to identify out-of-stock ingredients. For example, it might identify a situation where tomatoes are in stock but chicken is in short supply.

[1959] Step 12:

[1960] The server generates meal menus considering the user's preferences, nutritional balance, and emotional state. If the user is stressed, it suggests a menu that includes ingredients that help alleviate stress. For example, if the user is stressed, it might suggest "tomato and chicken pasta."

[1961] Step 13:

[1962] The server suggests purchasing the missing ingredient (in this case, chicken) from the most suitable retailer. It considers coupon information from partner suppliers to select the store that offers the best deal for the user. For example, it might say, "A coupon for 30% off chicken is available at Retailer B."

[1963] Step 14:

[1964] The server sends the generated menu and purchase store information to the user's terminal via API.

[1965] Step 15:

[1966] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include suggested menus, a list of necessary ingredients, store locations, and available coupon information.

[1967] Step 16:

[1968] The user checks the notification and purchases any missing ingredients to create the suggested menu. For example, the user purchases chicken from retailer B.

[1969] Step 17:

[1970] After a purchase, the user updates the inventory status in the app and sends that information back to the server. This ensures that the latest inventory information is reflected in the next offer.

[1971] This system allows users to easily manage available ingredients and obtain optimal meal menus tailored to their emotional state and preferences. Furthermore, partner businesses can enhance the effectiveness of their targeted advertising and contribute to reducing food waste.

[1972] (Example 2)

[1973] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1974] Traditional purchase history and inventory management systems have been unable to make suggestions that take into account the user's emotional state, making it difficult to increase consumer satisfaction. Furthermore, systems that suggest meal menus considering consumer preferences and nutritional balance are limited, making it difficult to support food waste reduction and efficient purchasing behavior. Therefore, there is a need for a system that suggests optimal meal menus that reflect the user's emotional state and effectively promotes the purchase of necessary ingredients.

[1975] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting purchase history data from the user, means for collecting the user's inventory data, means for collecting advertisements, coupon information and inventory data from partner companies, means for acquiring the user's emotional data, means for integrating the purchase history data, inventory data and emotional data to analyze the user's preferences and past purchasing patterns, means for comparing the user's inventory data with the partner company's inventory data to identify out-of-stock ingredients, means for generating meal menus considering the user's preferences, nutritional balance and emotional state, means for suggesting ingredients to be purchased and the stores where they can be purchased, and means for notifying the user of the suggestion results. This makes it possible to suggest optimal meal menus that reflect the user's emotional state and purchasing patterns and to support efficient purchasing behavior.

[1976] "Purchase history data" refers to data containing information about products that a user has purchased in the past. This data includes details such as product name, purchase date and time, store of purchase, and quantity.

[1977] "Inventory data" refers to data containing information about the food and products a user currently owns in their home. This data includes information such as the name of the food item, the quantity, and the expiration date.

[1978] "Advertising" refers to information provided by partner companies to promote specific products or services. This information includes product descriptions, special offers, and promotional details.

[1979] "Coupon information" refers to information that allows you to receive a discount on a specific product or service. This information includes coupon codes, discount rates, terms and conditions, and expiration dates.

[1980] "Partner companies" are businesses such as food manufacturers and retailers that provide data in conjunction with the system.

[1981] "Emotional data" refers to data about a user's emotional state. This data is obtained from the user's facial expressions and voice, and reflects emotional states such as happiness, anxiety, and stress.

[1982] An "emotion engine" is software or hardware that analyzes a user's facial expressions and voice to recognize their emotions and generate emotional data.

[1983] "Data integration" is the process of centrally managing and linking different types of data (such as purchase history data, inventory data, and sentiment data).

[1984] "Data analysis" is the process of analyzing user preferences, past purchasing patterns, food consumption rates, emotional states, and other factors based on integrated data.

[1985] A "meal menu" is a list of recipes and ingredients for creating a specific meal. This list is generated taking into account the user's preferences, nutritional balance, and emotional state.

[1986] "Suggestion results" refer to the suggestions generated by the system, such as meal menus, stores to purchase from, and coupon information.

[1987] A "notification" is an action taken to inform the user of the results of a system suggestion. This includes push notifications, in-app messages, and so on.

[1988] This invention relates to a system that collects user purchase history data, inventory data, advertisements and coupon information from partner companies, and sentiment data, and integrates and analyzes this data to suggest the optimal meal menu based on the user's emotions. The details are described below.

[1989] System Configuration

[1990] 1. User terminal

[1991] User terminals include smartphones, tablets, and personal computers. Using these terminals, users can input purchase history, record inventory data, provide emotional input using an emotion engine, and receive suggestions from the system.

[1992] 2. Server

[1993] The server is a central system that integrates, analyzes, recognizes sentiment, generates menus, creates suggestions, and notifies users. The server is connected to a database that centrally manages user information and data from partner companies.

[1994] 3. Partner companies

[1995] Partner companies include food manufacturers and retailers, and their role is to provide advertising, coupon information, and inventory data to the server.

[1996] 4. Emotional Engine

[1997] An emotion engine is software or hardware that recognizes emotions from a user's facial expressions and voice and generates emotion data. This emotion data reflects the user's mental state, and menu suggestions are made based on it.

[1998] Program Processing Description

[1999] Data collection

[2000] Users input or scan their purchase history through a smartphone app or web portal. For example, scanning a receipt with a smartphone camera allows the app to automatically recognize the date, product name, and store of purchase.

[2001] Users can record their household inventory by taking photos of ingredients with their smartphone camera or manually entering text.

[2002] The terminal sends the collected purchase history data and inventory data to the server via API.

[2003] Retrieving external data

[2004] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. This data includes product discounts, special offers, and in-store inventory status.

[2005] The server organizes the acquired data and stores it in the database.

[2006] Acquisition of emotional data

[2007] Users register their emotional states through a smartphone app using facial recognition cameras and voice input. The emotion engine recognizes the user's emotions from these inputs and generates emotion data.

[2008] The device sends the generated emotion data to the server via an API.

[2009] Data Integration and Analysis

[2010] The server integrates and centrally manages purchase history data, inventory data, and sentiment data.

[2011] The server uses machine learning algorithms to analyze the user's past purchasing patterns, food consumption rate, and emotional data.

[2012] The server compares the user's current inventory data with the inventory data of partner suppliers to identify out-of-stock ingredients.

[2013] Menu and store suggestions

[2014] The server generates an optimal meal plan considering the user's preferences, nutritional balance, and emotional state. For example, if the user is feeling stressed, it will suggest a menu that includes ingredients that help alleviate stress.

[2015] The server suggests the best store to purchase any missing ingredients. In doing so, it considers any coupons or special offers provided to select the most beneficial store for the user.

[2016] The server sends the generated menu and purchase store information to the user's terminal via API.

[2017] Notification of results and purchase information

[2018] The device displays suggestions to the user via push notifications or in-app messages. These suggestions include suggested menus, a list of necessary ingredients, stores where to purchase them, and available coupon information.

[2019] The user checks the notification and purchases the ingredients needed to make the suggested menu.

[2020] Specific example

[2021] 1. Data collection:

[2022] User A enters their recent purchase history of tomatoes and chicken into a smartphone app. The app automatically recognizes the product name, date, and store, and digitizes the data.

[2023] The device sends that data to the server.

[2024] 2. Obtaining external data:

[2025] The server retrieves coupon information for "30% off chicken" and inventory data from retailers via API.

[2026] 3. Acquisition of emotional data:

[2027] User A uses the app's facial recognition function to register with the emotion engine that they are feeling stressed.

[2028] The device sends that emotional data to the server.

[2029] 4. Data Integration and Analysis:

[2030] The server identifies from past usage history that user A prefers to use tomatoes and chicken, and analyzes that there is currently a shortage of chicken.

[2031] The server takes into account that user A is experiencing stress and includes suggestions for foods that can help alleviate stress.

[2032] 5. Menu and store suggestions:

[2033] The server generates a menu item called "Tomato and Chicken Pasta" and suggests that the user purchase chicken from a retail store.

[2034] The server displays a coupon from a retail store, offering 30% off chicken.

[2035] 6. Notification of results and purchase information:

[2036] The device notifies user A of the menu item "Tomato and Chicken Pasta" and coupon information.

[2037] User A checks the notification, buys chicken at a retail store, and prepares the suggested menu.

[2038] This processing flow allows users to efficiently manage ingredients and easily receive meal menu suggestions that take nutritional balance and emotional state into consideration. Furthermore, partner companies can effectively implement targeted advertising and contribute to reducing food waste.

[2039] The flow of the specific processing in Example 2 will be explained using Figure 13.

[2040] Step 1: Data Collection

[2041] Users enter their purchase history or scan receipts using a smartphone app. For example, if a user takes a picture of a receipt with their smartphone camera, the app automatically recognizes the date, product name, and store of purchase, and saves this data digitally. This data includes the user ID, product name, quantity, and purchase date.

[2042] Users record their household inventory by taking photos of ingredients with their smartphone camera or manually entering text. This data includes the name of the ingredient, the quantity, and the expiration date.

[2043] The device sends collected purchase history data and inventory data to the server via API. The server stores the received data in a database.

[2044] Step 2: Obtaining external data

[2045] The server periodically retrieves advertisements, coupon information, and inventory data from partner companies via API. This data ...

Claims

1. A means of collecting purchase history data from users, Means for collecting user inventory data, Means for collecting advertising, coupon information, and inventory data from partner companies, A means for integrating the aforementioned purchase history data and inventory data to analyze user preferences and past purchase patterns, A method for identifying out-of-stock ingredients by comparing user inventory data with partner supplier inventory data, A means of generating meal menus that take into account user preferences and nutritional balance, A means of suggesting which ingredients to buy and where to buy them, A means for notifying the user of the aforementioned proposal results, A system that includes this.

2. The system according to claim 1, further comprising means for recording the proposed meal menu and information on the store where it was purchased.

3. The system according to claim 1, further comprising means for automatically applying available coupons based on proposed store purchase information.

Images