System

Abstract

A system is provided.SOLUTION: A system comprising: means for analyzing store inventory information to identify items predicted to be unsold; means for generating information for selling unsold items at a discounted price; means for registering information about an item desired by a user and transmitting a notification when the item is at a discounted price; and means for receiving discount information for an item registered by a user and purchasing the item.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In traditional retail and restaurant industries, products often go unsold, resulting in food waste, which is a problem. Additionally, consumers face challenges in their daily diet, such as forgetting to buy products, overbuying, and nutritional imbalances. These challenges hinder the realization of a sustainable food environment and place a burden both economically and environmentally. A system that can comprehensively solve these issues is needed. [Means for solving the problem]

[0005] This invention provides a system that includes a means for analyzing store inventory information to identify products that are expected to remain unsold, a means for generating information for selling unsold products at discounted prices, a means for registering information about products desired by users and sending notifications when those products become available at discounted prices, and a means for receiving discount information about products registered by users and purchasing the products. The system also includes a means for analyzing the user's food records and photos of the contents of the refrigerator to provide advice to prevent forgetting to buy or overbuying, and a means for individually recommending suitable meals and products based on the user's preferences, nutritional balance, calorie information, and order history, thereby solving the problems of food waste and nutritional imbalance in the home and realizing a sustainable food environment.

[0006] "Inventory information" is data about the current quantity, type, and status of products in a store or restaurant.

[0007] "Products predicted to remain unsold" are products that the AI ​​model predicts, based on past sales data and trends, are likely to remain in inventory and not be sold in the future.

[0008] A "discount price" is a special price lower than the normal selling price, and is set for the purpose of clearance or special sales promotion.

[0009] The "products desired by the user" are products that the user has previously purchased or shown interest in, and are based on information registered in the system.

[0010] "Notifications" are messages or alerts sent to a user's device to inform them of discounted prices or other important information.

[0011] A "food record" is data that includes details of the foods a user consumes on a daily basis, including the amount, time, and nutritional information.

[0012] "Photos of the inside of the refrigerator" are images showing the current state of the inside of the refrigerator in the user's home, and are an information source provided to the system.

[0013] "Preferences" refers to information about a user's personal preferences, such as their favorite foods, flavors, cooking methods, and ingredients.

[0014] "Nutritional balance" refers to the balance of nutrients such as protein, lipids, carbohydrates, vitamins, and minerals in appropriate amounts to maintain and promote the user's health.

[0015] "Calorie information" is data that indicates the amount of energy in a food or meal, and is usually expressed in kilocalories (kcal).

[0016] "Order History" is a record of the products and services a user has previously purchased, which is useful for future recommendations and inventory management.

[0017] "Means for providing advice" refers to the mechanism by which the system provides appropriate information and suggestions to the user.

[0018] The "means of recommendation" is a mechanism by which the system takes into account the user's preferences and nutritional needs to suggest appropriate foods and products. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6]FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] This invention is a system that reduces food waste and supports users' eating habits. The main purpose of this system is to identify products that are predicted to remain unsold and sell them at a discount. Furthermore, the system analyzes the user's food records and the contents of the refrigerator, provides advice to prevent forgetting to buy or overbuying, and makes personalized meal and product recommendations to the user.

[0041] 1. Reducing food waste

[0042] Inventory Data Collection

[0043] Server: Connects to the inventory systems of supermarkets and restaurants to collect inventory data in real time. This includes obtaining inventory information for each store via API. Inventory data includes product name, category, quantity, price, etc.

[0044] Unsold items forecast

[0045] Server: Uses AI models to analyze collected inventory data and identify products that are predicted to remain unsold, based on historical sales data and seasonal trends.

[0046] Discount information generation

[0047] Server: Based on the list of predicted unsold items, the server sets discount prices and generates discount price information on the online platform. For example, a 20% discount off the regular price is applied to items predicted to be unsold.

[0048] 2. Optimizing individual consumption

[0049] Collecting user's food records and refrigerator information

[0050] Users use a smartphone app to upload food logs and photos of their refrigerators, including the types and amounts of food they eat and images of the food in their refrigerators.

[0051] Analysis of food records and refrigerator information

[0052] Server: AI analyzes the user's food records and refrigerator photos to understand current inventory status and consumption trends. Food records are broken down through text analysis, and refrigerator photos are digitized using image analysis technology.

[0053] 3. Personalized meal suggestions

[0054] Proposals that take into account individual preferences and nutritional balance

[0055] Server: Provides personalized meal suggestions based on user preferences, nutritional balance, calorie information, and order history. This provides meal plans and recipes tailored to the user's tastes and health status.

[0056] 4. Real-time notifications

[0057] Discount information notification

[0058] Device: When a product the user wants becomes discounted, the user is notified via a smartphone app. The user's desired product information is registered in advance, and an immediate notification is sent when the product becomes discounted.

[0059] Specific examples

[0060] For example, suppose Supermarket A has a large inventory of a certain product, but sales trends suggest that some items will remain unsold. The system first collects this inventory data, analyzes it using an AI model, and predicts that the product is likely to remain unsold. Next, it sets the price of the product at a 20% discount and generates discount information.

[0061] If the product is included in User B's desired product list that he or she has registered in advance, a notification of the discount information will be sent to User B's device. User B will receive the notification and can purchase the product at the discounted price through the smartphone app and pick it up at a nearby store.

[0062] Furthermore, User B enters his / her daily food records into the app and uploads photos of his / her refrigerator. The system analyzes these and makes suggestions to User B about the foods he / she needs and how to achieve an appropriate nutritional balance. It also provides personalized recipes and meal plans based on User B's preferences and nutritional needs. In this way, the system of the present invention helps reduce food waste and support users in leading healthy eating habits.

[0063] The processing flow will be explained below.

[0064] 1. Reducing food waste

[0065] Step 1.1: Collect inventory data

[0066] 1. Server: Connects to the inventory systems of supermarkets and restaurants and collects inventory data in real time.

[0067] Specific operation: Send an API request to obtain inventory information (product name, category, quantity, price, etc.) for each store.

[0068] Step 1.2: Unsold items forecast

[0069] 2. Server: Uses AI models to analyze collected inventory data and identify products that are predicted to remain unsold.

[0070] Specific operation: The acquired inventory data is input into an AI model, and unsold items are predicted based on past sales data and seasonal trends.

[0071] Step 1.3: Generate discount information

[0072] 3. Server: Based on the list of predicted unsold items, set discount prices and generate discount price information on the online platform.

[0073] Specific operation: Apply a 20% discount off the regular price to products predicted to remain unsold, and generate discount information.

[0074] 2. Optimizing individual consumption

[0075] Step 2.1: Collecting user's food log and refrigerator information

[0076] 1. User: Uses a smartphone app to upload food records and photos of the refrigerator.

[0077] Specific actions: Use the in-app form to enter your food record and take and upload a photo of your refrigerator using your smartphone camera.

[0078] Step 2.2: Analyze food logs and refrigerator information

[0079] 2. Server: AI analyzes the user's meal records and refrigerator photos to understand current inventory status and consumption trends.

[0080] Specific operation: Image analysis technology is used to recognize food in the refrigerator, and food records are broken down and digitized through text analysis.

[0081] 3. Personalized meal suggestions

[0082] Step 3.1: Recommendations based on individual preferences and nutritional balance

[0083] 1. Server: Provides personalized meal suggestions based on the user's preferences, nutritional balance, calorie information, and order history.

[0084] What it does: It uses a database of users and an algorithm to generate meal plans and recipes and display them to the user.

[0085] 4. Real-time notifications

[0086] Step 4.1: Discount Notification

[0087] 1. Device: When a product the user wants is discounted, the user is notified via a smartphone app.

[0088] Specific operation: Receive discount information from the server and notify the user of the information via push notification.

[0089] Specific examples

[0090] For example, suppose Supermarket A has a large inventory of a certain product, but sales trends suggest that some items will remain unsold. The system first collects this inventory data, analyzes it using an AI model, and predicts that the product is likely to remain unsold. Next, it sets the price of the product at a 20% discount and generates discount information.

[0091] If the product is included in User B's desired product list that he or she has registered in advance, a notification of the discount information will be sent to User B's device. User B will receive the notification and can purchase the product at the discounted price through the smartphone app and pick it up at a nearby store.

[0092] Furthermore, User B enters his / her daily food records into the app and uploads photos of his / her refrigerator. The system analyzes these and makes suggestions to User B about the foods he / she needs and how to achieve an appropriate nutritional balance. It also provides personalized recipes and meal plans based on User B's preferences and nutritional needs. In this way, the system of the present invention helps reduce food waste and support users in leading healthy eating habits.

[0093] Example 1

[0094] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0095] Food waste is a major problem in modern society, with unsold products commonly being discarded. This problem wastes resources, puts a strain on the environment, and results in economic losses. Furthermore, due to inadequate food management in refrigerators, users often forget to buy food or overbuy. Furthermore, it is difficult to provide meals and products that are suited to each individual user.

[0096] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0097] In this invention, the server includes a means for analyzing store inventory information and predicting unsold items, a means for generating discount prices for unsold items, and a means for registering product information desired by users and sending notifications when the relevant products become discounted. This allows for discount sales of unsold items and efficient user purchasing. Furthermore, the server analyzes food records and refrigerator information to provide advice to prevent forgetting to buy or overbuying, and recommends meals and products that are individually suited to the user based on the user's preferences, nutritional balance, calorie information, and order history, thereby supporting the user's healthy and efficient eating habits.

[0098] "Store inventory information" refers to data such as product type, quantity, price, and category in stores such as supermarkets and restaurants.

[0099] "Unsold product prediction" refers to identifying products that are likely to remain unsold within a certain period of time based on past sales data and seasonal trends.

[0100] "Generating discount prices" refers to applying a certain discount rate to products that are predicted to remain unsold and setting a new selling price.

[0101] "User's desired product information" refers to the data registered in advance by the user regarding the product they wish to purchase. This data includes the product name, category, etc.

[0102] "Means for sending notifications" refers to the ability to send notifications to users about specific events (e.g., when a discount price is applied) via a smartphone app, email, etc.

[0103] "Meal records" refers to data that records the type, amount, and time of meals consumed by a user.

[0104] "Refrigerator information" refers to data including the type, quantity, expiration date, etc. of food currently stored in the user's refrigerator.

[0105] "Advice to prevent forgetting to buy or overbuying" refers to suggestions and notifications to help users purchase the food they need at the right time and avoid overbuying.

[0106] "Preferences" refers to a user's personal tastes and eating habits, including preferences for certain ingredients and dishes.

[0107] "Nutritional balance" refers to the proper ratio of nutrients that a user needs to stay healthy and in optimal physical condition.

[0108] "Calorie information" refers to data indicating the energy content of a food or meal, usually expressed in kilocalories (kcal).

[0109] "Order History" refers to a record of the products a user has purchased in the past. This data is used to analyze user purchasing trends and preferences.

[0110] "Individually recommending meals and products" means individually suggesting optimal meal plans and products based on the user's preferences and health condition.

[0111] This invention is a system that reduces food waste and supports users' eating habits. The system aims to identify products that are predicted to remain unsold and sell them at discounted prices. Furthermore, the system analyzes the user's food records and refrigerator information to provide advice on preventing forgetting to buy or overbuying, and to recommend meals and products personalized to the user.

[0112] Inventory Data Collection

[0113] The server connects to the store's inventory system via API and collects inventory data in real time. This inventory data includes product name, category, quantity, price, etc. Specifically, it sends an HTTP request to the store's endpoint, parses the JSON response, and stores it in a database.

[0114] Unsold items forecast

[0115] The server uses the collected inventory data to identify products that are predicted to remain unsold using an AI model (for example, a machine learning model using TensorFlow). This prediction is based on inputs such as past sales data and seasonal trends. Feature engineering is performed to increase the likelihood of remaining unsold items, and the model is trained and evaluated accordingly.

[0116] Discount information generation

[0117] The server sets discount prices and generates discount information based on the list of predicted unsold items. This discount information is updated in real time on websites and smartphone apps. The set discount prices are linked to inventory information through a database update process.

[0118] Collecting user's food records and refrigerator information

[0119] Users upload food records and photos of their refrigerators through a smartphone app. Food records are entered as text and photos of the refrigerator are uploaded as images. This allows the user's consumption data to be collected.

[0120] Analysis of food records and refrigerator information

[0121] The server analyzes the food records using natural language processing (NLP) technology and the photos of the refrigerator using image analysis technology (such as OpenCV or Google Cloud Vision API). This analysis allows the server to understand the user's current inventory status and consumption trends.

[0122] Optimizing individual consumption

[0123] The server then recommends meal plans and products that are tailored to the user based on their preferences, nutritional balance, calorie information, and order history, resulting in personalized suggestions for the user.

[0124] Real-time notifications

[0125] When the device (smartphone) receives discount information for a desired product, it immediately notifies the user via push notification, making it easy for the user to purchase the desired product at the discounted price.

[0126] Specific examples

[0127] For example, if a store has a large stock of tomatoes and predicts that some will remain unsold, the server first collects inventory data. It then analyzes this data using an AI model and predicts that the tomatoes are likely to remain unsold. The server then sets the price of the tomatoes at a 20% discount from the regular price and generates discount information. This information is instantly reflected on the website and smartphone app.

[0128] If User B has registered tomatoes from this store as a purchase preference, they will receive a discount notification on their smartphone and be able to purchase tomatoes at a discounted price through the app. Additionally, User B can enter their daily food records in text and upload photos of their refrigerator. The server analyzes this information and provides personalized meal plans and recipes based on User B's preferences and nutritional balance.

[0129] Prompt Sentence Examples

[0130] "In order to reduce food waste, please design a system that analyzes data on products that are predicted to remain unsold in stores and generates discount information. Furthermore, please include a function that analyzes when users upload their food records and refrigerator information and makes suggestions based on necessary foods and nutritional balance."

[0131] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0132] Step 1: Collect inventory data

[0133] The server connects to the store's inventory system via API and collects inventory data in real time. It sends an HTTP request using the store's endpoint URL and API key as input. In response, it receives inventory data in JSON format (product name, category, quantity, price, etc.). It stores this data in an internal database and converts it into a format that can be used in the next step.

[0134] Step 2: Unsold items forecast

[0135] The server uses the collected inventory data to identify products that are predicted to remain unsold using an AI model (using TensorFlow). As input, the inventory data and past sales data are fed into the AI ​​model. The model performs feature engineering, extracts important features, and starts making predictions. As output, the server gets a list of products predicted to remain unsold, along with their probabilities.

[0136] Step 3: Generate discount information

[0137] The server sets discount prices and generates discount information based on the predicted unsold items list. As input, it uses the list of predicted unsold items and their regular prices. As output, it calculates the discount price (e.g., 20% off the regular price) and generates discount information. This information is stored in a database and updated in real time on the website and smartphone app.

[0138] Step 4: Collect food records and fridge information

[0139] Users use a smartphone app to upload their meal records and photos of their refrigerator. As input, they enter the details of their meals in text and take and upload photos of the inside of their refrigerator. This data is sent to a server and analyzed.

[0140] Step 5: Analyze your food log and refrigerator information

[0141] The server uses AI technology to analyze the received meal records and refrigerator photos. Text data and image data from the user are used as input. The text data is analyzed using natural language processing (NLP), and the image data is analyzed using image analysis technology (OpenCV and Google Cloud Vision API). The output is data that identifies current inventory status and consumption trends.

[0142] Step 6: Optimize individual consumption

[0143] The server makes personalized meal plans and product recommendations based on the user's preferences, nutritional balance, calorie information, and order history. It uses the user's profile information and analysis results as input. The recommendation engine calculates the optimal meal plans and products and generates personalized suggestions as output.

[0144] Step 7: Discount Notification

[0145] When the device (smartphone) receives information about a discounted product that the user wants, it immediately notifies the user via push notification. As input, it receives discount information from the server. As output, it sends a push notification to the user and displays the discount information.

[0146] The above are the specific processing steps and flow of the system program.

[0147] (Application example 1)

[0148] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0149] Food waste has become a serious problem in today's consumer society. Unsold food leads to increased waste, resulting in environmental impact and economic losses. Users also have difficulty keeping track of their food records and the state of their refrigerators, which can lead to buying excess food. Furthermore, the lack of recommendations for meals and products tailored to individual tastes makes it difficult to maintain a proper nutritional balance.

[0150] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0151] In this invention, the server includes means for analyzing inventory information to identify products that are expected to remain unsold, means for generating information for selling unsold products at discounted prices, means for sending notifications of discounted products based on the user's purchasing history and preferences, means for receiving discount information for products registered by the user and purchasing the applicable products, and means for managing the refrigerator status and providing advice on foods to purchase, thereby enabling the reduction of food waste and the optimization of the user's eating habits.

[0152] "Inventory information" is a collection of data about the quantity and condition of products in stores and warehouses.

[0153] "Unsold goods prediction" is the process of identifying products that are likely to remain unsold in the future based on past sales data and current inventory data.

[0154] A "discount price" is a special price that is discounted from the regular selling price.

[0155] "Discount Notifications" are messages or alerts that inform users of discount information based on specific times or events.

[0156] "User purchase history" refers to a record of products purchased by a user in the past.

[0157] "Individually suitable meals" and "individually suitable product recommendations" are suggestions for optimal meals and products selected based on the user's preferences, nutritional balance, and calorie information.

[0158] "Refrigerator status" refers to data about the types and quantities of food in the refrigerator, their expiration dates, and so on.

[0159] "Food waste" refers to the amount and value of food that is discarded without being consumed.

[0160] This invention is a system that identifies products that are predicted to remain unsold and offers them to users at discounted prices, thereby reducing food waste and improving the user's purchasing experience. Furthermore, the system analyzes the user's food records and refrigerator status to provide personalized purchasing advice and meal suggestions. A system that realizes this application example is described in detail below.

[0161] Hardware and Software

[0162] This system mainly uses the following hardware and software:

[0163] Hardware used: Smartphone, server

[0164] Software used: Python (API calls, data analysis, user notifications), Sklearn (linear regression model), Requests (API communication), image recognition library

[0165] Data collection and analysis

[0166] The server uses APIs to retrieve inventory data, including product names, categories, quantities, and prices, in order to collect real-time inventory information from stores and warehouses.

[0167] The server uses an AI model to predict leftover items, which uses Sklearn's linear regression to analyze past sales data and current inventory data to identify items that are likely to remain unsold in the future.

[0168] Discount information generation and notification

[0169] The server sets discount prices for products that are predicted to remain unsold and generates the discount information. The generated discount information is notified to users in a personalized format based on their purchasing history and preferences. The notification is sent in real time via a smartphone app.

[0170] Refrigerator management and meal suggestions

[0171] Users upload photos of their refrigerators using a smartphone app. These photos are analyzed using an image recognition library on the server. The analysis results are stored in a database, and the status of the user's refrigerator is managed.

[0172] The server analyzes the refrigerator's contents and the user's food records, provides advice on how to avoid forgetting to buy or overbuying, and generates optimal meal suggestions and recipes based on the user's preferences and nutritional balance.

[0173] Specific examples

[0174] For example, if a user wants to manage their shopping at a supermarket, they first use a smartphone app to check the supermarket's inventory information. At this time, the server predicts unsold items based on past sales data and generates discount price information. If there are any discounted items in the user's desired product list, a notification is sent to the smartphone.

[0175] Next, to manage their home refrigerator, users upload a photo of their refrigerator. The server analyzes the photo and determines the inventory status of the refrigerator. The system automatically advises users on what they should buy more of or what they have bought more than they needed.

[0176] Example prompt sentence:

[0177] "It collects inventory data in real time, predicts unsold items, and generates discount information. It sends discount notifications to users and analyzes photos of refrigerators to make meal suggestions."

[0178] This allows users to shop efficiently, reduce food waste and maintain a healthy diet.

[0179] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0180] Step 1:

[0181] The server collects inventory information from stores and warehouses via API. It uses the API endpoint as input and obtains inventory data (product name, category, quantity, price, etc.) as output. Specifically, it uses the Requests library to send a request to the API, parses the returned JSON data, and stores it in an internal database.

[0182] Step 2:

[0183] The server analyzes the acquired inventory data using an AI model (linear regression model). It uses past sales data and current inventory data as input and generates a list of products that are predicted to remain unsold as output. Specifically, it uses Sklearn's linear regression module to predict unsold items using this data.

[0184] Step 3:

[0185] The server sets discount prices for products predicted to remain unsold and generates the discount information. It uses a list of predicted unsold products as input and generates discount price information as output. Specifically, it calculates the price by discounting a certain percentage (for example, 20%) from the regular price and lists the discount information.

[0186] Step 4:

[0187] The server takes into account the user's purchasing history and preferences to send notifications of discounted products. It uses the user's purchasing history and preference data as input and sends discount notifications for the relevant products as output. Specifically, it extracts relevant discount information based on the user's profile information and sends notifications to the smartphone.

[0188] Step 5:

[0189] A user uploads a photo of the refrigerator using a smartphone app. The photo data of the refrigerator is used as input, and image data is sent to the server as output. Specifically, the user takes a photo using the app's camera function and sends the photo to the server.

[0190] Step 6:

[0191] The server analyzes the uploaded photo of the refrigerator. It uses the received image data as input and generates an inventory list of the refrigerator as output. Specifically, it uses an image recognition library to identify the food items in the photo and store it as structured data.

[0192] Step 7:

[0193] The server analyzes the refrigerator inventory list and the user's food record to generate advice to prevent forgetting to buy or overbuying. It uses the refrigerator inventory list and food record data as input and generates advice information as output. Specifically, it queries the database and provides advice based on the user's consumption habits.

[0194] Step 8:

[0195] The server generates personalized meal suggestions and recipes based on the user's preferences and nutritional balance. It uses the user's preference data, nutritional information, and calorie information as input, and generates meal suggestions and recipe information as output. Specifically, it comprehensively analyzes this data and proposes the optimal meal plan for the user.

[0196] Through these processing steps, the system can reduce food waste and optimize users' diets.

[0197] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0198] This invention relates to a food waste reduction and dietary lifestyle support system that combines a system that identifies products that are predicted to remain unsold and sells them at discounted prices with an emotion engine that recognizes user emotions. This system can adjust the content of product recommendations and notifications based on the user's emotions, providing a more personalized service.

[0199] 1. Reducing food waste

[0200] Inventory Data Collection

[0201] Server: Connects to the inventory systems of supermarkets and restaurants to collect inventory data in real time, obtaining data such as product name, category, quantity, and price through API requests.

[0202] Unsold items forecast

[0203] Server: Uses AI models to analyze collected inventory data and identify items that are predicted to remain unsold, taking into account historical sales data and seasonal trends.

[0204] Discount information generation

[0205] Server: Based on the predicted list of unsold items, set a discount price and generate discount information on the online platform, for example, set a price 20% off the regular price.

[0206] 2. Optimizing individual consumption

[0207] Collecting user's food records and refrigerator information

[0208] Users use a smartphone app to upload daily food records and photos of their refrigerators. Food records include food types, portions, and calorie information.

[0209] Analysis of food records and refrigerator information

[0210] Server: AI analyzes the food records and refrigerator photos provided by the user. Image analysis technology is used to recognize the food in the refrigerator, and food records are converted into data through text analysis.

[0211] 3. Personalized meal suggestions

[0212] Proposals that take into account individual preferences and nutritional balance

[0213] Server: Provides personalized meal suggestions based on user preferences, nutritional balance, calorie information, and order history, resulting in meal plans and recipes tailored to the user.

[0214] Emotion engine integration

[0215] Server: Integrates an emotion engine that recognizes the user's emotions and collects emotional data from the user's voice, facial expressions, behavior, etc. This allows the current emotional state to be understood.

[0216] 4. Real-time notifications

[0217] Discount information notification

[0218] Device: When a product desired by the user is discounted, the system sends a notification via a smartphone app. The timing and content of the notification are adjusted based on data from the emotion engine.

[0219] Tailoring suggestions based on emotions

[0220] Server: Analyzes the user's emotional data and recommends meals and products based on their emotional state. For example, if a user is feeling depressed, it will suggest meals and products that will lift their spirits.

[0221] Specific examples

[0222] For example, suppose Supermarket A has a large inventory of a certain product, but sales trends suggest that it will remain unsold. This system first collects inventory data, analyzes it with an AI model, and predicts that the product is likely to remain unsold. It then sets the price of the product at a 20% discount from the regular price and generates discount information.

[0223] If the product is included in User B's wish list that he or she registered in advance, a notification of the discount information will be sent to User B's device. When sending the notification, the emotion engine detects User B's emotional state, and if, for example, User B is feeling stressed, the notification will include a message to help them relax.

[0224] Furthermore, User B enters his / her daily food record into the app and uploads photos of his / her refrigerator. The system analyzes this and provides User B with advice that takes into account the foods he / she needs and nutritional balance. The emotion engine also suggests recipes and meal plans based on User B's emotional state. For example, if User B is tired, it recommends meals suitable for restoring energy. In this way, the system of the present invention reduces food waste and supports healthy eating habits that take into account the user's emotional state.

[0225] The processing flow will be explained below.

[0226] Overall process flow for recruitment and purchasing

[0227] Step 1. Collect and analyze store data

[0228] Step 1.1:

[0229] Server: Connects to the supermarket or restaurant inventory system and sends API requests to collect inventory data, including product name, category, quantity, and price.

[0230] Step 1.2:

[0231] Server: Collected inventory data is input into the AI ​​model, which then predicts unsold items based on past sales data and seasonal trends. The AI ​​model uses machine learning to identify the items most likely to remain unsold.

[0232] Step 1.3:

[0233] Server: Sets discount prices based on the list of products predicted to remain unsold. For example, generates discount information for 20% off the regular price and registers the information on the online platform.

[0234] User Behavior and Analytics

[0235] Step 2. Collecting and analyzing user data

[0236] Step 2.1:

[0237] User: Using a smartphone app, users upload daily food records and photos of their refrigerator, including the types and amounts of food consumed and images of the food stored in the refrigerator.

[0238] Step 2.2:

[0239] Server: Analyzes photos of refrigerators uploaded by users using image analysis technology to determine current inventory status. At the same time, analyzes text from food records to digitize users' eating habits.

[0240] Step 2.3:

[0241] Server: Based on the user's refrigerator inventory and food records, the server provides advice to prevent forgetting to buy or overbuying. This advice includes a list of necessary foods and ways to save money.

[0242] Personalized offers and notifications

[0243] Step 3. Optimize meal suggestions and notifications

[0244] Step 3.1:

[0245] Server: Analyzes user preferences, nutritional balance, calorie information, and order history to suggest personalized meal plans and recipes based on the user's health and individual nutritional needs.

[0246] Step 3.2:

[0247] Server: Uses the emotion engine to collect emotional data from the user's voice, facial expressions, and behavior, thereby understanding the user's current emotional state.

[0248] Step 3.3:

[0249] Server: Analyzes the user's emotional data and recommends meals and products based on their emotional state. For example, if a user is feeling depressed, it will suggest foods and recipes that will improve their mood.

[0250] Step 4. Real-time notification of discount information

[0251] Step 4.1:

[0252] Device: Real-time notifications are sent to users' devices when discounted items become available. The content and timing of notifications are also adjusted based on the emotion engine.

[0253] Running a concrete example

[0254] Example: Supermarket A's product inventory and user B's behavior

[0255] Step 5.1:

[0256] Server: Collects data from Supermarket A's inventory system and analyzes it with an AI model. Specific products are listed as items that are predicted to remain unsold.

[0257] Step 5.2:

[0258] Server: Apply a 20% discount to the product and generate the discount information.

[0259] Step 5.3:

[0260] User B: If the product is on their wish list, a notification about the discount will be sent to their device. If User B is feeling stressed, a notification will be sent with a message to help them relax.

[0261] Step 5.4:

[0262] User: Enters daily food records into the app and uploads photos of the refrigerator, allowing the system to understand the user's eating habits and refrigerator inventory.

[0263] Step 5.5:

[0264] Server: Based on the emotion engine, it proposes recipes and meal plans that take into account User B's emotional state. For example, if User B is tired, it recommends meals that will help restore energy.

[0265] Through the above steps, the system of the present invention reduces food waste and supports healthy eating habits that take into account the user's emotional state.

[0266] Example 2

[0267] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0268] Food waste has become a serious problem in modern society, resulting in many products remaining unsold and discarded. Furthermore, suggestions tailored to individual user dietary needs are not provided, making it difficult to provide healthy and balanced meals. Furthermore, there is a lack of personalized services that take into account the user's emotional state. These circumstances are contributing to increased food waste and a decline in user satisfaction.

[0269] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0270] In this invention, the server includes: means for collecting store inventory information; means for analyzing the collected inventory information and using an artificial intelligence model to identify products predicted to remain unsold; means for generating discount price information based on the list of unsold products; means for publishing the generated discount price information on an online platform; means for using a terminal to register information about products desired by the user and receive notifications when the products are discounted; means for the user to receive the notifications and purchase the target products; means for using image analysis technology to analyze the user's food log and images of the contents of the refrigerator; means for providing advice based on the analysis results to prevent forgetting to buy or overbuying; means for recommending meals and products that are individually suited to the user's preferences, nutritional balance, calorie information, and order history; means for collecting and analyzing emotional data from the user's voice, facial expressions, and behavior; and means for adjusting the recommendations based on the collected emotional data. This enables food waste reduction and personalized dietary support tailored to the user's emotional state.

[0271] "Inventory information" is data about products held by stores and restaurants, such as product names, categories, quantities, and prices.

[0272] An "artificial intelligence model" is an algorithm that learns from past data and trends and makes predictions and classifications based on new data.

[0273] "Discount price information" is price information set lower than the regular price for products that are expected to remain unsold.

[0274] An "online platform" is a digital space for providing product information and discount information via the Internet.

[0275] A "terminal" is an electronic device, such as a smartphone or tablet, that allows a user to receive and operate information.

[0276] "Food records" are data that include detailed information such as the types, amounts, and calories of the foods a user consumes.

[0277] "Image analysis technology" is a technology that processes image data and extracts meaningful information.

[0278] "Means for providing advice" refers to functions or methods that provide useful information or suggestions to users based on the analysis results.

[0279] "Preferences" is data that refers to a user's preferred foods and flavors.

[0280] "Nutritional balance" is data that indicates the proportions of necessary nutrients such as protein, lipids, carbohydrates, vitamins, and minerals.

[0281] "Calorie information" is data that indicates the amount of energy ingested from food or meals.

[0282] "Order History" is a record of products and services a User has previously purchased.

[0283] "Emotional data" is information that indicates the psychological state of a user, collected from their voice, facial expressions, behavior, etc.

[0284] The "emotion engine" is a system that analyzes collected emotional data and evaluates the user's state based on the results.

[0285] The present invention relates to a food waste reduction and dietary lifestyle support system that combines a system that identifies unsold products and sells them at discounted prices with an emotion engine that recognizes user emotions. This system is implemented using a specific combination of hardware and software.

[0286] Specifically, the server performs the following processes: First, it collects inventory information from stores and restaurants. To do this, it uses API requests to obtain data such as product name, category, quantity, and price. Next, it inputs the collected inventory information into an AI model to identify products that are predicted to remain unsold. This AI model uses machine learning libraries such as TensorFlow and PyTorch. It then generates discount price information based on the list of unsold products and publishes it on an online platform.

[0287] Users use a smartphone app to upload their daily food records and images of their refrigerator. The food records include information on the type, amount, and calories of food. The server analyzes the uploaded data and uses image analysis technology (such as OpenCV or TensorFlow) to recognize the foods in the refrigerator, and converts the food records into data using text analysis.

[0288] To provide personalized meal suggestions, the server considers the user's preferences, nutritional balance, calorie information, and order history. This allows it to propose personalized meal plans and recipes. It also integrates an emotion engine that collects and analyzes emotional data from the user's voice, facial expressions, and behavior. Based on the analysis results, it adjusts the content of suggestions and the timing of notifications.

[0289] When a discount is offered on a product the user wants, the system will send a notification via the smartphone app. The content and timing of the notification will be adjusted based on data from the emotion engine.

[0290] For example, if supermarket A has a large stock of a particular product and sales trends indicate that it will remain unsold, the server collects inventory data, analyzes it using an AI model, and predicts that the product is likely to remain unsold. The server then sets the price of the product at a 20% discount from the normal price and generates discount information. If the product is included in User B's desired product list that he or she previously registered, a notification of the discount information is sent to User B's device. When the notification is sent, the emotion engine detects User B's emotional state; for example, if User B is feeling stressed, the notification will include a message to help them relax.

[0291] Furthermore, User B enters their daily food records into the app and uploads photos of their refrigerator. The server analyzes this and provides advice on the foods User B needs and nutritional balance. The emotion engine also suggests recipes and meal plans based on User B's emotional state. For example, if User B is tired, it will recommend meals suitable for restoring energy.

[0292] Example prompt sentence:

[0293] "Please tell me how to specifically design a system that uses an emotion engine to recognize the emotional state of a particular user and then makes product or meal recommendations based on that emotion."

[0294] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0295] Step 1:

[0296] Inventory data collection

[0297] Server: Connects to the store or restaurant inventory system and collects inventory data such as product name, category, quantity, and price through API requests. Specifically, it accesses the API endpoint and obtains real-time inventory information.

[0298] Input: API response data from a store or restaurant inventory system.

[0299] Output: An inventory dataset containing product name, category, quantity, and price.

[0300] Step 2:

[0301] Unsold items forecast

[0302] Server: Collected inventory data is input into the AI ​​model to identify products that are predicted to remain unsold. Taking into account past sales data and seasonal trends, predictions are made using machine learning models using TensorFlow and PyTorch.

[0303] Input: Collected inventory dataset.

[0304] Output: A list of items that are predicted to remain unsold.

[0305] Step 3:

[0306] Generate discount information

[0307] Server: Based on the list of unsold items, the server sets a price 20% off the regular price and generates discount information. The generated discount information is published on the online platform.

[0308] Input: A list of unsold items.

[0309] Output: Discount information including discount price and product information.

[0310] Step 4:

[0311] Food records and refrigerator information collection

[0312] User: Using a smartphone app, users upload daily food records and photos of their refrigerator. Food records include food types, portions, and calorie information.

[0313] Input: User-uploaded food logs and photos of the refrigerator.

[0314] Output: Food records and photo data stored in cloud storage.

[0315] Step 5:

[0316] Analysis of food records and refrigerator information

[0317] Server: Analyzes the uploaded data, recognizes the food in the refrigerator using image analysis technology, and converts the food records into data using text analysis. Tools such as OpenCV and TensorFlow are used.

[0318] Input: Saved food records and photo data.

[0319] Output: Text data of the food record and a list of recognized foods in the refrigerator.

[0320] Step 6:

[0321] Personalized meal suggestions

[0322] Server: Providing personalized meal recommendations based on user preferences, nutritional balance, calorie information, and order history. Using user data to provide optimal meal plans and recipes.

[0323] Input: Text data of food records, list of recognized foods in the refrigerator, user preferences, nutritional information, and order history.

[0324] Output: A list of meal plans and recipe suggestions suitable for the user.

[0325] Step 7:

[0326] Emotion engine integration

[0327] Server: Collects and analyzes emotional data from the user's voice, facial expressions, and behavior. Tailors suggestions based on the user's emotional state. This is achieved using emotion analysis technologies such as DeepFace.

[0328] Input: User's voice, facial expression, and behavior data.

[0329] Output: User's emotional state data and suggestion information based on it.

[0330] Step 8:

[0331] Discount information notification

[0332] Device: A smartphone app sends notifications when a desired product becomes discounted. The timing and content of notifications are adjusted based on data from the emotion engine.

[0333] Input: Discount information and user emotional state data.

[0334] Output: A message notifying you of the discount.

[0335] Step 9:

[0336] Tailoring suggestions based on emotions

[0337] Server: Analyzes emotional data and recommends meals and products based on the user's emotional state. If the user is feeling down, it will make suggestions to lift their spirits.

[0338] Input: User emotional state data.

[0339] Output: A list of food and product suggestions corresponding to your emotional state.

[0340] (Application example 2)

[0341] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0342] In today's world, where food waste is a serious problem, there is a need to efficiently identify products that are predicted to remain unsold and sell them at appropriate discount prices. Furthermore, a system is needed to make personalized suggestions to users and send timely and appropriate product notifications to increase their purchasing motivation. Furthermore, it is also a challenge to provide passengers in autonomous vehicles with food and beverages that match their emotional state, thereby providing a comfortable travel experience.

[0343] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0344] In this invention, the server includes means for analyzing inventory information to identify products that are predicted to remain unsold, means for generating information for selling unsold products at discounted prices, means for registering information about products desired by users and sending notifications when the products become available at discounted prices, means for receiving discount information about products registered by users and purchasing the target products, and means for adjusting the content and timing of notifications using an emotion engine that analyzes user emotions. This enables efficient identification and sale of unsold products, personalized notifications to users, and emotional provision of food and beverages to passengers during travel.

[0345] "Inventory information" refers to data relating to the quantity, type, location, etc. of products in a commercial facility or storage facility.

[0346] "Discount pricing" means that a product is offered at a price lower than its normal selling price.

[0347] The "emotion engine" is a system that collects and analyzes emotional data from the user's voice, facial expressions, behavior, etc. to understand the user's emotional state.

[0348] A "notification" is a message or alarm sent to a communication device such as a smartphone or tablet to inform the user of specific information.

[0349] "Food records" are data recorded by users that includes daily meal contents, meal amounts, nutritional information, etc.

[0350] "Video inside storage facilities" refers to images or video data taken with a camera of the inside of storage facilities such as refrigerators and pantries.

[0351] "Preferences" refers to information about a user's likes, dislikes, and preferences.

[0352] "Nutritional balance" refers to a state in which the nutrients in the food consumed by the user are appropriately distributed.

[0353] "Calorie information" is data that indicates the energy content of foods and drinks, and is usually expressed in "kilocalories (kcal)."

[0354] "Order history" refers to recorded data of products that a user has purchased or ordered in the past.

[0355] This invention combines a system that identifies unsold products and sells them at discounted prices with an emotion engine that recognizes user emotions to reduce food waste and support dietary habits. The system operates in anticipation of personalized food and beverage delivery to passengers in autonomous vehicles.

[0356] The server includes the following means:

[0357] 1. Means for analyzing inventory information: This system works in conjunction with the inventory management system of the storage equipment installed in the autonomous vehicle to collect inventory data in real time. The server obtains information such as product name, category, quantity, and price through the implemented API. Data collection and management are performed using Python.

[0358] 2. Discount price generation method: Based on the collected inventory data, an AI model is used to predict unsold items. This model includes a function that uses TensorFlow to perform predictive analysis taking into account past sales data and seasonal trends. The server sets discount prices based on the predicted list of unsold items and generates discount information on the online platform.

[0359] 3. Means of integrating emotion engine: Using a camera and microphone, the user's facial expressions, voice, and behavior are analyzed in real time to grasp the user's emotional state. The emotion engine analyzes emotions using facial recognition and voice analysis technologies using TensorFlow and OpenCV. Emotion data is reflected in food and drink recommendations based on the user's emotional fluctuations.

[0360] The device (smartphone or tablet) has the following features:

[0361] 1. Notification method: Based on data from the emotion engine, food and drink recommendations and discount information tailored to the passenger's state are sent. These notifications are sent in real time, and the content and timing of the notifications are adjusted according to the passenger's emotional state.

[0362] The user (passenger) performs the following operations:

[0363] 1. Uploading food records and footage of the storage facility: Food records and footage of the storage facility are uploaded to the server via a smartphone app. The server analyzes the data and provides advice to prevent forgetting to buy things or overbuying. For example, if the user is tired, it will suggest a drink that will help restore energy.

[0364] To illustrate, consider the following scenario:

[0365] Scenario: Passenger A is traveling in an autonomous vehicle and is detected as tired by the emotion engine.

[0366] Example prompt: "I sense that Passenger A is tired. Would you like to offer him a refreshment drink?"

[0367] In this way, the system of the present invention enables efficient identification and sale of unsold merchandise, personalized notifications to users, and emotion-based food and beverage offerings to passengers during travel.

[0368] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0369] Step 1:

[0370] Inventory Data Collection

[0371] The server collects real-time inventory information from the storage facilities installed in the autonomous vehicles, obtaining data such as product name, category, quantity, and price through API requests. This data is collected using a Python script and stored in a database.

[0372] Input: Inventory information from storage facilities (product name, category, quantity, price)

[0373] Output: Stock information is saved in the database

[0374] Step 2:

[0375] Unsold items forecast

[0376] The server uses AI models based on collected inventory data to identify products that are likely to remain unsold, and TensorFlow is used to perform predictive analysis that takes into account past sales data and seasonal trends.

[0377] Input: Past sales data, current inventory data

[0378] Output: Unsold items prediction result (list of items predicted to be unsold)

[0379] Step 3:

[0380] Discount information generation

[0381] The server sets discount prices based on the predicted list of unsold items and generates discount information on the online platform. Specifically, it uses a Python script to calculate the discount price for each item and stores the information in a database.

[0382] Input: Unsold items prediction result (list of items predicted to be unsold)

[0383] Output: Discount information (list of products with discounted prices)

[0384] Step 4:

[0385] Emotion data collection and analysis

[0386] The device (smartphone or tablet) uses a camera and microphone to collect the user's facial expressions, voice, and behavior in real time. Using TensorFlow and OpenCV, this data is analyzed to understand the user's emotional state.

[0387] Input: User's facial expression data, voice data, behavior data

[0388] Output: User's emotional state (emotion type and intensity)

[0389] Step 5:

[0390] Tailoring and sending notifications

[0391] The server adjusts the content and timing of notifications based on the emotion engine data and discount information, then sends the notifications to the device. A Python script is used to generate an appropriate message tailored to the user's current emotional state.

[0392] Input: User's emotional state, discount information

[0393] Output: Tailored notification content (message based on emotional state)

[0394] Step 6:

[0395] Uploading food records and footage of storage facilities

[0396] Users upload their daily food records and footage of the storage facility to a server via a smartphone app, which then analyzes the data and provides advice on how to avoid forgetting to buy things or overbuying.

[0397] Input: Meal record data, video data inside storage facilities

[0398] Output: Consumption advice (advice to prevent forgetting to buy or overspending)

[0399] Step 7:

[0400] Personalized suggestions

[0401] The server integrates the user's emotional state, food log, and inventory data to suggest suitable foods and drinks to the user, and uses a Python script to generate an appropriate item list based on health status and preferences.

[0402] Input: User's emotional state, food log, inventory data

[0403] Output: Personalized food and drink suggestions (list of suggested foods and drinks)

[0404] In this way, the system of the present invention effectively provides discount sales of unsold items and personalized food and beverage offerings based on the user's emotional state through real-time data collection and analysis.

[0405] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0406] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0407] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0408] [Second embodiment]

[0409] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0410] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0411] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0412] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0413] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0414] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0415] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0416] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0417] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0418] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0419] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0420] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0421] This invention is a system that reduces food waste and supports users' eating habits. The main purpose of this system is to identify products that are predicted to remain unsold and sell them at a discount. Furthermore, the system analyzes the user's food records and the contents of the refrigerator, provides advice to prevent forgetting to buy or overbuying, and makes personalized meal and product recommendations to the user.

[0422] 1. Reducing food waste

[0423] Inventory Data Collection

[0424] Server: Connects to the inventory systems of supermarkets and restaurants to collect inventory data in real time. This includes obtaining inventory information for each store via API. Inventory data includes product name, category, quantity, price, etc.

[0425] Unsold items forecast

[0426] Server: Uses AI models to analyze collected inventory data and identify products that are predicted to remain unsold, based on historical sales data and seasonal trends.

[0427] Discount information generation

[0428] Server: Based on the list of predicted unsold items, the server sets discount prices and generates discount price information on the online platform. For example, a 20% discount off the regular price is applied to items predicted to be unsold.

[0429] 2. Optimizing individual consumption

[0430] Collecting user's food records and refrigerator information

[0431] Users use a smartphone app to upload food logs and photos of their refrigerators, including the types and amounts of food they eat and images of the food in their refrigerators.

[0432] Analysis of food records and refrigerator information

[0433] Server: AI analyzes the user's food records and refrigerator photos to understand current inventory status and consumption trends. Food records are broken down through text analysis, and refrigerator photos are digitized using image analysis technology.

[0434] 3. Personalized meal suggestions

[0435] Proposals that take into account individual preferences and nutritional balance

[0436] Server: Provides personalized meal suggestions based on user preferences, nutritional balance, calorie information, and order history. This provides meal plans and recipes tailored to the user's tastes and health status.

[0437] 4. Real-time notifications

[0438] Discount information notification

[0439] Device: When a product the user wants becomes discounted, the user is notified via a smartphone app. The user's desired product information is registered in advance, and an immediate notification is sent when the product becomes discounted.

[0440] Specific examples

[0441] For example, suppose Supermarket A has a large inventory of a certain product, but sales trends suggest that some items will remain unsold. The system first collects this inventory data, analyzes it using an AI model, and predicts that the product is likely to remain unsold. Next, it sets the price of the product at a 20% discount and generates discount information.

[0442] If the product is included in User B's desired product list that he or she has registered in advance, a notification of the discount information will be sent to User B's device. User B will receive the notification and can purchase the product at the discounted price through the smartphone app and pick it up at a nearby store.

[0443] Furthermore, User B enters his / her daily food records into the app and uploads photos of his / her refrigerator. The system analyzes these and makes suggestions to User B about the foods he / she needs and how to achieve an appropriate nutritional balance. It also provides personalized recipes and meal plans based on User B's preferences and nutritional needs. In this way, the system of the present invention helps reduce food waste and support users in leading healthy eating habits.

[0444] The processing flow will be explained below.

[0445] 1. Reducing food waste

[0446] Step 1.1: Collect inventory data

[0447] 1. Server: Connects to the inventory systems of supermarkets and restaurants and collects inventory data in real time.

[0448] Specific operation: Send an API request to obtain inventory information (product name, category, quantity, price, etc.) for each store.

[0449] Step 1.2: Unsold items forecast

[0450] 2. Server: Uses AI models to analyze collected inventory data and identify products that are predicted to remain unsold.

[0451] Specific operation: The acquired inventory data is input into an AI model, and unsold items are predicted based on past sales data and seasonal trends.

[0452] Step 1.3: Generate discount information

[0453] 3. Server: Based on the list of predicted unsold items, set discount prices and generate discount price information on the online platform.

[0454] Specific operation: Apply a 20% discount off the regular price to products predicted to remain unsold, and generate discount information.

[0455] 2. Optimizing individual consumption

[0456] Step 2.1: Collecting user's food log and refrigerator information

[0457] 1. User: Uses a smartphone app to upload food records and photos of the refrigerator.

[0458] Specific actions: Use the in-app form to enter your food record and take and upload a photo of your refrigerator using your smartphone camera.

[0459] Step 2.2: Analyze food logs and refrigerator information

[0460] 2. Server: AI analyzes the user's meal records and refrigerator photos to understand current inventory status and consumption trends.

[0461] Specific operation: Image analysis technology is used to recognize food in the refrigerator, and food records are broken down and digitized through text analysis.

[0462] 3. Personalized meal suggestions

[0463] Step 3.1: Recommendations based on individual preferences and nutritional balance

[0464] 1. Server: Provides personalized meal suggestions based on the user's preferences, nutritional balance, calorie information, and order history.

[0465] What it does: It uses a database of users and an algorithm to generate meal plans and recipes and display them to the user.

[0466] 4. Real-time notifications

[0467] Step 4.1: Discount Notification

[0468] 1. Device: When a product the user wants is discounted, the user is notified via a smartphone app.

[0469] Specific operation: Receive discount information from the server and notify the user of the information via push notification.

[0470] Specific examples

[0471] For example, suppose Supermarket A has a large inventory of a certain product, but sales trends suggest that some items will remain unsold. The system first collects this inventory data, analyzes it using an AI model, and predicts that the product is likely to remain unsold. Next, it sets the price of the product at a 20% discount and generates discount information.

[0472] If the product is included in User B's desired product list that he or she has registered in advance, a notification of the discount information will be sent to User B's device. User B will receive the notification and can purchase the product at the discounted price through the smartphone app and pick it up at a nearby store.

[0473] Furthermore, User B enters his / her daily food records into the app and uploads photos of his / her refrigerator. The system analyzes these and makes suggestions to User B about the foods he / she needs and how to achieve an appropriate nutritional balance. It also provides personalized recipes and meal plans based on User B's preferences and nutritional needs. In this way, the system of the present invention helps reduce food waste and support users in leading healthy eating habits.

[0474] Example 1

[0475] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0476] Food waste is a major problem in modern society, with unsold products commonly being discarded. This problem wastes resources, puts a strain on the environment, and results in economic losses. Furthermore, due to inadequate food management in refrigerators, users often forget to buy food or overbuy. Furthermore, it is difficult to provide meals and products that are suited to each individual user.

[0477] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0478] In this invention, the server includes a means for analyzing store inventory information and predicting unsold items, a means for generating discount prices for unsold items, and a means for registering product information desired by users and sending notifications when the relevant products become discounted. This allows for discount sales of unsold items and efficient user purchasing. Furthermore, the server analyzes food records and refrigerator information to provide advice to prevent forgetting to buy or overbuying, and recommends meals and products that are individually suited to the user based on the user's preferences, nutritional balance, calorie information, and order history, thereby supporting the user's healthy and efficient eating habits.

[0479] "Store inventory information" refers to data such as product type, quantity, price, and category in stores such as supermarkets and restaurants.

[0480] "Unsold product prediction" refers to identifying products that are likely to remain unsold within a certain period of time based on past sales data and seasonal trends.

[0481] "Generating discount prices" refers to applying a certain discount rate to products that are predicted to remain unsold and setting a new selling price.

[0482] "User's desired product information" refers to the data registered in advance by the user regarding the product they wish to purchase. This data includes the product name, category, etc.

[0483] "Means for sending notifications" refers to the function of sending notifications to users about specific events (for example, when a discount price is applied) via a smartphone app, email, etc.

[0484] "Meal records" refers to data that records the type, amount, and time of meals consumed by a user.

[0485] "Refrigerator information" refers to data including the type, quantity, expiration date, etc. of food currently stored in the user's refrigerator.

[0486] "Advice to prevent forgetting to buy or overbuying" refers to suggestions and notifications to help users purchase the food they need at the right time and avoid overbuying.

[0487] "Preferences" refers to a user's personal tastes and eating habits, including preferences for certain ingredients and dishes.

[0488] "Nutritional balance" refers to the proper ratio of nutrients that a user needs to stay healthy and in optimal physical condition.

[0489] "Calorie information" refers to data indicating the energy content of a food or meal, usually expressed in kilocalories (kcal).

[0490] "Order History" refers to a record of the products a user has purchased in the past. This data is used to analyze user purchasing trends and preferences.

[0491] "Individually recommending meals and products" means individually suggesting optimal meal plans and products based on the user's preferences and health condition.

[0492] This invention is a system that reduces food waste and supports users' eating habits. The system aims to identify products that are predicted to remain unsold and sell them at discounted prices. Furthermore, the system analyzes the user's food records and refrigerator information to provide advice on preventing forgetting to buy or overbuying, and to recommend meals and products personalized to the user.

[0493] Inventory Data Collection

[0494] The server connects to the store's inventory system via API and collects inventory data in real time. This inventory data includes product name, category, quantity, price, etc. Specifically, it sends an HTTP request to the store's endpoint, parses the JSON response, and stores it in a database.

[0495] Unsold items forecast

[0496] The server uses the collected inventory data to identify products that are predicted to remain unsold using an AI model (for example, a machine learning model using TensorFlow). This prediction is based on inputs such as past sales data and seasonal trends. Feature engineering is performed to increase the likelihood of remaining unsold items, and the model is trained and evaluated accordingly.

[0497] Discount information generation

[0498] The server sets discount prices and generates discount information based on the list of predicted unsold items. This discount information is updated in real time on websites and smartphone apps. The set discount prices are linked to inventory information through a database update process.

[0499] Collecting user's food records and refrigerator information

[0500] Users upload food records and photos of their refrigerators through a smartphone app. Food records are entered as text and photos of the refrigerator are uploaded as images. This allows the user's consumption data to be collected.

[0501] Analysis of food records and refrigerator information

[0502] The server analyzes the food records using natural language processing (NLP) technology and the photos of the refrigerator using image analysis technology (such as OpenCV or Google Cloud Vision API). This analysis allows the server to understand the user's current inventory status and consumption trends.

[0503] Optimizing individual consumption

[0504] The server then recommends meal plans and products that are tailored to the user based on their preferences, nutritional balance, calorie information, and order history, resulting in personalized suggestions for the user.

[0505] Real-time notifications

[0506] When the device (smartphone) receives discount information for a desired product, it immediately notifies the user via push notification, making it easy for the user to purchase the desired product at the discounted price.

[0507] Specific examples

[0508] For example, if a store has a large stock of tomatoes and predicts that some will remain unsold, the server first collects inventory data. It then analyzes this data using an AI model and predicts that the tomatoes are likely to remain unsold. The server then sets the price of the tomatoes at a 20% discount from the regular price and generates discount information. This information is instantly reflected on the website and smartphone app.

[0509] If User B has registered tomatoes from this store as a purchase preference, they will receive a discount notification on their smartphone and be able to purchase tomatoes at a discounted price through the app. Additionally, User B can enter their daily food records in text and upload photos of their refrigerator. The server analyzes this information and provides personalized meal plans and recipes based on User B's preferences and nutritional balance.

[0510] Prompt Sentence Examples

[0511] "In order to reduce food waste, please design a system that analyzes data on products that are predicted to remain unsold in stores and generates discount information. Furthermore, please include a function that analyzes when users upload their food records and refrigerator information and makes suggestions based on necessary foods and nutritional balance."

[0512] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0513] Step 1: Collect inventory data

[0514] The server connects to the store's inventory system via API and collects inventory data in real time. It sends an HTTP request using the store's endpoint URL and API key as input. In response, it receives inventory data in JSON format (product name, category, quantity, price, etc.). It stores this data in an internal database and converts it into a format that can be used in the next step.

[0515] Step 2: Unsold items forecast

[0516] The server uses the collected inventory data to identify products that are predicted to remain unsold using an AI model (using TensorFlow). As input, the inventory data and past sales data are fed into the AI ​​model. The model performs feature engineering, extracts important features, and starts making predictions. As output, the server gets a list of products predicted to remain unsold, along with their probabilities.

[0517] Step 3: Generate discount information

[0518] The server sets discount prices and generates discount information based on the predicted unsold items list. As input, it uses the list of predicted unsold items and their regular prices. As output, it calculates the discount price (e.g., 20% off the regular price) and generates discount information. This information is stored in a database and updated in real time on the website and smartphone app.

[0519] Step 4: Collect food records and fridge information

[0520] Users use a smartphone app to upload their meal records and photos of their refrigerator. As input, they enter the details of their meals in text and take and upload photos of the inside of their refrigerator. This data is sent to a server and analyzed.

[0521] Step 5: Analyze your food log and refrigerator information

[0522] The server uses AI technology to analyze the received meal records and refrigerator photos. Text data and image data from the user are used as input. The text data is analyzed using natural language processing (NLP), and the image data is analyzed using image analysis technology (OpenCV and Google Cloud Vision API). The output is data that identifies current inventory status and consumption trends.

[0523] Step 6: Optimize individual consumption

[0524] The server makes personalized meal plans and product recommendations based on the user's preferences, nutritional balance, calorie information, and order history. It uses the user's profile information and analysis results as input. The recommendation engine calculates the optimal meal plans and products and generates personalized suggestions as output.

[0525] Step 7: Discount Notification

[0526] When the device (smartphone) receives information about a discounted product that the user wants, it immediately notifies the user via push notification. As input, it receives discount information from the server. As output, it sends a push notification to the user and displays the discount information.

[0527] The above are the specific processing steps and flow of the system program.

[0528] (Application example 1)

[0529] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0530] Food waste has become a serious problem in today's consumer society. Unsold food leads to increased waste, resulting in environmental impact and economic losses. Users also have difficulty keeping track of their food records and the state of their refrigerators, which can lead to buying excess food. Furthermore, the lack of recommendations for meals and products tailored to individual tastes makes it difficult to maintain a proper nutritional balance.

[0531] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0532] In this invention, the server includes means for analyzing inventory information to identify products that are expected to remain unsold, means for generating information for selling unsold products at discounted prices, means for sending notifications of discounted products based on the user's purchasing history and preferences, means for receiving discount information for products registered by the user and purchasing the applicable products, and means for managing the refrigerator status and providing advice on foods to purchase, thereby enabling the reduction of food waste and the optimization of the user's eating habits.

[0533] "Inventory information" is a collection of data about the quantity and condition of products in stores and warehouses.

[0534] "Unsold goods prediction" is the process of identifying products that are likely to remain unsold in the future based on past sales data and current inventory data.

[0535] A "discount price" is a special price that is discounted from the regular selling price.

[0536] "Discount Notifications" are messages or alerts that inform users of discount information based on specific times or events.

[0537] "User purchase history" refers to a record of products purchased by a user in the past.

[0538] "Individually suitable meals" and "individually suitable product recommendations" are suggestions for optimal meals and products selected based on the user's preferences, nutritional balance, and calorie information.

[0539] "Refrigerator status" refers to data about the types and quantities of food in the refrigerator, their expiration dates, and so on.

[0540] "Food waste" refers to the amount and value of food that is discarded without being consumed.

[0541] This invention is a system that identifies products that are predicted to remain unsold and offers them to users at discounted prices, thereby reducing food waste and improving the user's purchasing experience. Furthermore, the system analyzes the user's food records and refrigerator status to provide personalized purchasing advice and meal suggestions. A system that realizes this application example is described in detail below.

[0542] Hardware and Software

[0543] This system mainly uses the following hardware and software:

[0544] Hardware used: Smartphone, server

[0545] Software used: Python (API calls, data analysis, user notifications), Sklearn (linear regression model), Requests (API communication), image recognition library

[0546] Data collection and analysis

[0547] The server uses APIs to retrieve inventory data, including product names, categories, quantities, and prices, in order to collect real-time inventory information from stores and warehouses.

[0548] The server uses an AI model to predict leftover items, which uses Sklearn's linear regression to analyze past sales data and current inventory data to identify items that are likely to remain unsold in the future.

[0549] Discount information generation and notification

[0550] The server sets discount prices for products that are predicted to remain unsold and generates the discount information. The generated discount information is notified to users in a personalized format based on their purchasing history and preferences. The notification is sent in real time via a smartphone app.

[0551] Refrigerator management and meal suggestions

[0552] Users upload photos of their refrigerators using a smartphone app. These photos are analyzed using an image recognition library on the server. The analysis results are stored in a database, and the status of the user's refrigerator is managed.

[0553] The server analyzes the refrigerator's contents and the user's food records, provides advice on how to avoid forgetting to buy or overbuying, and generates optimal meal suggestions and recipes based on the user's preferences and nutritional balance.

[0554] Specific examples

[0555] For example, if a user wants to manage their shopping at a supermarket, they first use a smartphone app to check the supermarket's inventory information. At this time, the server predicts unsold items based on past sales data and generates discount price information. If there are any discounted items in the user's desired product list, a notification is sent to the smartphone.

[0556] Next, to manage their home refrigerator, users upload a photo of their refrigerator. The server analyzes the photo and determines the inventory status of the refrigerator. The system automatically advises users on what they should buy more of or what they have bought more than they needed.

[0557] Example prompt sentence:

[0558] "It collects inventory data in real time, predicts unsold items, and generates discount information. It sends discount notifications to users and analyzes photos of refrigerators to make meal suggestions."

[0559] This allows users to shop efficiently, reduce food waste and maintain a healthy diet.

[0560] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0561] Step 1:

[0562] The server collects inventory information from stores and warehouses via API. It uses the API endpoint as input and obtains inventory data (product name, category, quantity, price, etc.) as output. Specifically, it uses the Requests library to send a request to the API, parses the returned JSON data, and stores it in an internal database.

[0563] Step 2:

[0564] The server analyzes the acquired inventory data using an AI model (linear regression model). It uses past sales data and current inventory data as input and generates a list of products that are predicted to remain unsold as output. Specifically, it uses Sklearn's linear regression module to predict unsold items using this data.

[0565] Step 3:

[0566] The server sets discount prices for products predicted to remain unsold and generates the discount information. It uses a list of predicted unsold products as input and generates discount price information as output. Specifically, it calculates the price by discounting a certain percentage (for example, 20%) from the regular price and lists the discount information.

[0567] Step 4:

[0568] The server takes into account the user's purchasing history and preferences to send notifications of discounted products. It uses the user's purchasing history and preference data as input and sends discount notifications for the relevant products as output. Specifically, it extracts relevant discount information based on the user's profile information and sends notifications to the smartphone.

[0569] Step 5:

[0570] A user uploads a photo of the refrigerator using a smartphone app. The photo data of the refrigerator is used as input, and image data is sent to the server as output. Specifically, the user takes a photo using the app's camera function and sends the photo to the server.

[0571] Step 6:

[0572] The server analyzes the uploaded photo of the refrigerator. It uses the received image data as input and generates an inventory list of the refrigerator as output. Specifically, it uses an image recognition library to identify the food items in the photo and store it as structured data.

[0573] Step 7:

[0574] The server analyzes the refrigerator inventory list and the user's food record to generate advice to prevent forgetting to buy or overbuying. It uses the refrigerator inventory list and food record data as input and generates advice information as output. Specifically, it queries the database and provides advice based on the user's consumption habits.

[0575] Step 8:

[0576] The server generates personalized meal suggestions and recipes based on the user's preferences and nutritional balance. It uses the user's preference data, nutritional information, and calorie information as input, and generates meal suggestions and recipe information as output. Specifically, it comprehensively analyzes this data and proposes the optimal meal plan for the user.

[0577] Through these processing steps, the system can reduce food waste and optimize users' diets.

[0578] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0579] This invention relates to a food waste reduction and dietary lifestyle support system that combines a system that identifies products that are predicted to remain unsold and sells them at discounted prices with an emotion engine that recognizes user emotions. This system can adjust the content of product recommendations and notifications based on the user's emotions, providing a more personalized service.

[0580] 1. Reducing food waste

[0581] Inventory Data Collection

[0582] Server: Connects to the inventory systems of supermarkets and restaurants to collect inventory data in real time, obtaining data such as product name, category, quantity, and price through API requests.

[0583] Unsold items forecast

[0584] Server: Uses AI models to analyze collected inventory data and identify items that are predicted to remain unsold, taking into account historical sales data and seasonal trends.

[0585] Discount information generation

[0586] Server: Based on the predicted list of unsold items, set a discount price and generate discount information on the online platform, for example, set a price 20% off the regular price.

[0587] 2. Optimizing individual consumption

[0588] Collecting user's food records and refrigerator information

[0589] Users use a smartphone app to upload daily food records and photos of their refrigerators. Food records include food types, portions, and calorie information.

[0590] Analysis of food records and refrigerator information

[0591] Server: AI analyzes the food records and refrigerator photos provided by the user. Image analysis technology is used to recognize the food in the refrigerator, and food records are converted into data through text analysis.

[0592] 3. Personalized meal suggestions

[0593] Proposals that take into account individual preferences and nutritional balance

[0594] Server: Provides personalized meal suggestions based on user preferences, nutritional balance, calorie information, and order history, resulting in meal plans and recipes tailored to the user.

[0595] Emotion engine integration

[0596] Server: Integrates an emotion engine that recognizes the user's emotions and collects emotional data from the user's voice, facial expressions, behavior, etc. This allows the current emotional state to be understood.

[0597] 4. Real-time notifications

[0598] Discount information notification

[0599] Device: When a product desired by the user is discounted, the system sends a notification via a smartphone app. The timing and content of the notification are adjusted based on data from the emotion engine.

[0600] Tailoring suggestions based on emotions

[0601] Server: Analyzes the user's emotional data and recommends meals and products based on their emotional state. For example, if a user is feeling depressed, it will suggest meals and products that will lift their spirits.

[0602] Specific examples

[0603] For example, suppose Supermarket A has a large inventory of a certain product, but sales trends suggest that it will remain unsold. This system first collects inventory data, analyzes it with an AI model, and predicts that the product is likely to remain unsold. It then sets the price of the product at a 20% discount from the regular price and generates discount information.

[0604] If the product is included in User B's wish list that he or she registered in advance, a notification of the discount information will be sent to User B's device. When sending the notification, the emotion engine detects User B's emotional state, and if, for example, User B is feeling stressed, the notification will include a message to help them relax.

[0605] Furthermore, User B enters his / her daily food record into the app and uploads photos of his / her refrigerator. The system analyzes this and provides User B with advice that takes into account the foods he / she needs and nutritional balance. The emotion engine also suggests recipes and meal plans based on User B's emotional state. For example, if User B is tired, it recommends meals suitable for restoring energy. In this way, the system of the present invention reduces food waste and supports healthy eating habits that take into account the user's emotional state.

[0606] The processing flow will be explained below.

[0607] Overall process flow for recruitment and purchasing

[0608] Step 1. Collect and analyze store data

[0609] Step 1.1:

[0610] Server: Connects to the supermarket or restaurant inventory system and sends API requests to collect inventory data, including product name, category, quantity, and price.

[0611] Step 1.2:

[0612] Server: Collected inventory data is input into the AI ​​model, which then predicts unsold items based on past sales data and seasonal trends. The AI ​​model uses machine learning to identify the items most likely to remain unsold.

[0613] Step 1.3:

[0614] Server: Sets discount prices based on the list of products predicted to remain unsold. For example, generates discount information for 20% off the regular price and registers the information on the online platform.

[0615] User Behavior and Analytics

[0616] Step 2. Collecting and analyzing user data

[0617] Step 2.1:

[0618] User: Using a smartphone app, users upload daily food records and photos of their refrigerator, including the types and amounts of food consumed and images of the food stored in the refrigerator.

[0619] Step 2.2:

[0620] Server: Analyzes photos of refrigerators uploaded by users using image analysis technology to determine current inventory status. At the same time, analyzes text from food records to digitize users' eating habits.

[0621] Step 2.3:

[0622] Server: Based on the user's refrigerator inventory and food records, the server provides advice to prevent forgetting to buy or overbuying. This advice includes a list of necessary foods and ways to save money.

[0623] Personalized offers and notifications

[0624] Step 3. Optimize meal suggestions and notifications

[0625] Step 3.1:

[0626] Server: Analyzes user preferences, nutritional balance, calorie information, and order history to suggest personalized meal plans and recipes based on the user's health and individual nutritional needs.

[0627] Step 3.2:

[0628] Server: Uses the emotion engine to collect emotional data from the user's voice, facial expressions, and behavior, thereby understanding the user's current emotional state.

[0629] Step 3.3:

[0630] Server: Analyzes the user's emotional data and recommends meals and products based on their emotional state. For example, if a user is feeling depressed, it will suggest foods and recipes that will improve their mood.

[0631] Step 4. Real-time notification of discount information

[0632] Step 4.1:

[0633] Device: Real-time notifications are sent to users' devices when discounted items become available. The content and timing of notifications are also adjusted based on the emotion engine.

[0634] Running a concrete example

[0635] Example: Supermarket A's product inventory and user B's behavior

[0636] Step 5.1:

[0637] Server: Collects data from Supermarket A's inventory system and analyzes it with an AI model. Specific products are listed as items that are predicted to remain unsold.

[0638] Step 5.2:

[0639] Server: Apply a 20% discount to the product and generate the discount information.

[0640] Step 5.3:

[0641] User B: If the product is on their wish list, a notification about the discount will be sent to their device. If User B is feeling stressed, a notification will be sent with a message to help them relax.

[0642] Step 5.4:

[0643] User: Enters daily food records into the app and uploads photos of the refrigerator, allowing the system to understand the user's eating habits and refrigerator inventory.

[0644] Step 5.5:

[0645] Server: Based on the emotion engine, it proposes recipes and meal plans that take into account User B's emotional state. For example, if User B is tired, it recommends meals that will help restore energy.

[0646] Through the above steps, the system of the present invention reduces food waste and supports healthy eating habits that take into account the user's emotional state.

[0647] Example 2

[0648] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0649] Food waste has become a serious problem in modern society, resulting in many products remaining unsold and discarded. Furthermore, suggestions tailored to individual user dietary needs are not provided, making it difficult to provide healthy and balanced meals. Furthermore, there is a lack of personalized services that take into account the user's emotional state. These circumstances are contributing to increased food waste and a decline in user satisfaction.

[0650] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0651] In this invention, the server includes: means for collecting store inventory information; means for analyzing the collected inventory information and using an artificial intelligence model to identify products predicted to remain unsold; means for generating discount price information based on the list of unsold products; means for publishing the generated discount price information on an online platform; means for using a terminal to register information about products desired by the user and receive notifications when the products are discounted; means for the user to receive the notifications and purchase the target products; means for using image analysis technology to analyze the user's food log and images of the contents of the refrigerator; means for providing advice based on the analysis results to prevent forgetting to buy or overbuying; means for recommending meals and products that are individually suited to the user's preferences, nutritional balance, calorie information, and order history; means for collecting and analyzing emotional data from the user's voice, facial expressions, and behavior; and means for adjusting the recommendations based on the collected emotional data. This enables food waste reduction and personalized dietary support tailored to the user's emotional state.

[0652] "Inventory information" is data about products held by stores and restaurants, such as product names, categories, quantities, and prices.

[0653] An "artificial intelligence model" is an algorithm that learns from past data and trends and makes predictions and classifications based on new data.

[0654] "Discount price information" is price information set lower than the regular price for products that are expected to remain unsold.

[0655] An "online platform" is a digital space for providing product information and discount information via the Internet.

[0656] A "terminal" is an electronic device, such as a smartphone or tablet, that allows a user to receive and operate information.

[0657] "Food records" are data that include detailed information such as the types, amounts, and calories of the foods a user consumes.

[0658] "Image analysis technology" is a technology that processes image data and extracts meaningful information.

[0659] "Means for providing advice" refers to functions or methods that provide useful information or suggestions to users based on the analysis results.

[0660] "Preferences" is data that refers to a user's preferred foods and flavors.

[0661] "Nutritional balance" is data that indicates the proportions of necessary nutrients such as protein, lipids, carbohydrates, vitamins, and minerals.

[0662] "Calorie information" is data that indicates the amount of energy ingested from food or meals.

[0663] "Order History" is a record of products and services a User has previously purchased.

[0664] "Emotional data" is information that indicates the psychological state of a user, collected from their voice, facial expressions, behavior, etc.

[0665] The "emotion engine" is a system that analyzes collected emotional data and evaluates the user's state based on the results.

[0666] The present invention relates to a food waste reduction and dietary lifestyle support system that combines a system that identifies unsold products and sells them at discounted prices with an emotion engine that recognizes user emotions. This system is implemented using a specific combination of hardware and software.

[0667] Specifically, the server performs the following processes: First, it collects inventory information from stores and restaurants. To do this, it uses API requests to obtain data such as product name, category, quantity, and price. Next, it inputs the collected inventory information into an AI model to identify products that are predicted to remain unsold. This AI model uses machine learning libraries such as TensorFlow and PyTorch. It then generates discount price information based on the list of unsold products and publishes it on an online platform.

[0668] Users use a smartphone app to upload their daily food records and images of their refrigerator. The food records include information on the type, amount, and calories of food. The server analyzes the uploaded data and uses image analysis technology (such as OpenCV or TensorFlow) to recognize the foods in the refrigerator, and converts the food records into data using text analysis.

[0669] To provide personalized meal suggestions, the server considers the user's preferences, nutritional balance, calorie information, and order history. This allows it to propose personalized meal plans and recipes. It also integrates an emotion engine that collects and analyzes emotional data from the user's voice, facial expressions, and behavior. Based on the analysis results, it adjusts the content of suggestions and the timing of notifications.

[0670] When a discount is offered on a product the user wants, the system will send a notification via the smartphone app. The content and timing of the notification will be adjusted based on data from the emotion engine.

[0671] For example, if supermarket A has a large stock of a particular product and sales trends indicate that it will remain unsold, the server collects inventory data, analyzes it using an AI model, and predicts that the product is likely to remain unsold. The server then sets the price of the product at a 20% discount from the normal price and generates discount information. If the product is included in User B's desired product list that he or she previously registered, a notification of the discount information is sent to User B's device. When the notification is sent, the emotion engine detects User B's emotional state; for example, if User B is feeling stressed, the notification will include a message to help them relax.

[0672] Furthermore, User B enters their daily food records into the app and uploads photos of their refrigerator. The server analyzes this and provides advice on the foods User B needs and nutritional balance. The emotion engine also suggests recipes and meal plans based on User B's emotional state. For example, if User B is tired, it will recommend meals suitable for restoring energy.

[0673] Example prompt sentence:

[0674] "Please tell me how to specifically design a system that uses an emotion engine to recognize the emotional state of a particular user and then makes product or meal recommendations based on that emotion."

[0675] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0676] Step 1:

[0677] Inventory data collection

[0678] Server: Connects to the store or restaurant inventory system and collects inventory data such as product name, category, quantity, and price through API requests. Specifically, it accesses the API endpoint and obtains real-time inventory information.

[0679] Input: API response data from a store or restaurant inventory system.

[0680] Output: An inventory dataset containing product name, category, quantity, and price.

[0681] Step 2:

[0682] Unsold items forecast

[0683] Server: Collected inventory data is input into the AI ​​model to identify products that are predicted to remain unsold. Taking into account past sales data and seasonal trends, predictions are made using machine learning models using TensorFlow and PyTorch.

[0684] Input: Collected inventory dataset.

[0685] Output: A list of items that are predicted to remain unsold.

[0686] Step 3:

[0687] Generate discount information

[0688] Server: Based on the list of unsold items, the server sets a price 20% off the regular price and generates discount information. The generated discount information is published on the online platform.

[0689] Input: A list of unsold items.

[0690] Output: Discount information including discount price and product information.

[0691] Step 4:

[0692] Food records and refrigerator information collection

[0693] User: Using a smartphone app, users upload daily food records and photos of their refrigerator. Food records include food types, portions, and calorie information.

[0694] Input: User-uploaded food logs and photos of the refrigerator.

[0695] Output: Food records and photo data stored in cloud storage.

[0696] Step 5:

[0697] Analysis of food records and refrigerator information

[0698] Server: Analyzes the uploaded data, recognizes the food in the refrigerator using image analysis technology, and converts the food records into data using text analysis. Tools such as OpenCV and TensorFlow are used.

[0699] Input: Saved food records and photo data.

[0700] Output: Text data of the food record and a list of recognized foods in the refrigerator.

[0701] Step 6:

[0702] Personalized meal suggestions

[0703] Server: Providing personalized meal recommendations based on user preferences, nutritional balance, calorie information, and order history. Using user data to provide optimal meal plans and recipes.

[0704] Input: Text data of food records, list of recognized foods in the refrigerator, user preferences, nutritional information, and order history.

[0705] Output: A list of meal plans and recipe suggestions suitable for the user.

[0706] Step 7:

[0707] Emotion engine integration

[0708] Server: Collects and analyzes emotional data from the user's voice, facial expressions, and behavior. Tailors suggestions based on the user's emotional state. This is achieved using emotion analysis technologies such as DeepFace.

[0709] Input: User's voice, facial expression, and behavior data.

[0710] Output: User's emotional state data and suggestion information based on it.

[0711] Step 8:

[0712] Discount information notification

[0713] Device: A smartphone app sends notifications when a desired product becomes discounted. The timing and content of notifications are adjusted based on data from the emotion engine.

[0714] Input: Discount information and user emotional state data.

[0715] Output: A message notifying you of the discount.

[0716] Step 9:

[0717] Tailoring suggestions based on emotions

[0718] Server: Analyzes emotional data and recommends meals and products based on the user's emotional state. If the user is feeling down, it will make suggestions to lift their spirits.

[0719] Input: User emotional state data.

[0720] Output: A list of food and product suggestions corresponding to your emotional state.

[0721] (Application example 2)

[0722] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0723] In today's world, where food waste is a serious problem, there is a need to efficiently identify products that are predicted to remain unsold and sell them at appropriate discount prices. Furthermore, a system is needed to make personalized suggestions to users and send timely and appropriate product notifications to increase their purchasing motivation. Furthermore, it is also a challenge to provide passengers in autonomous vehicles with food and beverages that match their emotional state, thereby providing a comfortable travel experience.

[0724] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0725] In this invention, the server includes means for analyzing inventory information to identify products that are predicted to remain unsold, means for generating information for selling unsold products at discounted prices, means for registering information about products desired by users and sending notifications when the products become available at discounted prices, means for receiving discount information about products registered by users and purchasing the target products, and means for adjusting the content and timing of notifications using an emotion engine that analyzes user emotions. This enables efficient identification and sale of unsold products, personalized notifications to users, and emotional provision of food and beverages to passengers during travel.

[0726] "Inventory information" refers to data relating to the quantity, type, location, etc. of products in a commercial facility or storage facility.

[0727] "Discount pricing" means that a product is offered at a price lower than its normal selling price.

[0728] The "emotion engine" is a system that collects and analyzes emotional data from the user's voice, facial expressions, behavior, etc. to understand the user's emotional state.

[0729] A "notification" is a message or alarm sent to a communication device such as a smartphone or tablet to inform the user of specific information.

[0730] "Food records" are data recorded by users that includes daily meal contents, meal amounts, nutritional information, etc.

[0731] "Video inside storage facilities" refers to images or video data taken with a camera of the inside of storage facilities such as refrigerators and pantries.

[0732] "Preferences" refers to information about a user's likes, dislikes, and preferences.

[0733] "Nutritional balance" refers to a state in which the nutrients in the food consumed by the user are appropriately distributed.

[0734] "Calorie information" is data that indicates the energy content of foods and drinks, and is usually expressed in "kilocalories (kcal)."

[0735] "Order history" refers to recorded data of products that a user has purchased or ordered in the past.

[0736] This invention combines a system that identifies unsold products and sells them at discounted prices with an emotion engine that recognizes user emotions to reduce food waste and support dietary habits. The system operates in anticipation of personalized food and beverage delivery to passengers in autonomous vehicles.

[0737] The server includes the following means:

[0738] 1. Means for analyzing inventory information: This system works in conjunction with the inventory management system of the storage equipment installed in the autonomous vehicle to collect inventory data in real time. The server obtains information such as product name, category, quantity, and price through the implemented API. Data collection and management are performed using Python.

[0739] 2. Discount price generation method: Based on the collected inventory data, an AI model is used to predict unsold items. This model includes a function that uses TensorFlow to perform predictive analysis taking into account past sales data and seasonal trends. The server sets discount prices based on the predicted list of unsold items and generates discount information on the online platform.

[0740] 3. Means of integrating emotion engine: Using a camera and microphone, the user's facial expressions, voice, and behavior are analyzed in real time to grasp the user's emotional state. The emotion engine analyzes emotions using facial recognition and voice analysis technologies using TensorFlow and OpenCV. Emotion data is reflected in food and drink recommendations based on the user's emotional fluctuations.

[0741] The device (smartphone or tablet) has the following features:

[0742] 1. Notification method: Based on data from the emotion engine, food and drink recommendations and discount information tailored to the passenger's state are sent. These notifications are sent in real time, and the content and timing of the notifications are adjusted according to the passenger's emotional state.

[0743] The user (passenger) performs the following operations:

[0744] 1. Uploading food records and footage of the storage facility: Food records and footage of the storage facility are uploaded to the server via a smartphone app. The server analyzes the data and provides advice to prevent forgetting to buy things or overbuying. For example, if the user is tired, it will suggest a drink that will help restore energy.

[0745] To illustrate, consider the following scenario:

[0746] Scenario: Passenger A is traveling in an autonomous vehicle and is detected as tired by the emotion engine.

[0747] Example prompt: "I sense that Passenger A is tired. Would you like to offer him a refreshment drink?"

[0748] In this way, the system of the present invention enables efficient identification and sale of unsold merchandise, personalized notifications to users, and emotion-based food and beverage offerings to passengers during travel.

[0749] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0750] Step 1:

[0751] Inventory Data Collection

[0752] The server collects real-time inventory information from the storage facilities installed in the autonomous vehicles, obtaining data such as product name, category, quantity, and price through API requests. This data is collected using a Python script and stored in a database.

[0753] Input: Inventory information from storage facilities (product name, category, quantity, price)

[0754] Output: Stock information is saved in the database

[0755] Step 2:

[0756] Unsold items forecast

[0757] The server uses AI models based on collected inventory data to identify products that are likely to remain unsold, and TensorFlow is used to perform predictive analysis that takes into account past sales data and seasonal trends.

[0758] Input: Past sales data, current inventory data

[0759] Output: Unsold items prediction result (list of items predicted to be unsold)

[0760] Step 3:

[0761] Discount information generation

[0762] The server sets discount prices based on the predicted list of unsold items and generates discount information on the online platform. Specifically, it uses a Python script to calculate the discount price for each item and stores the information in a database.

[0763] Input: Unsold items prediction result (list of items predicted to be unsold)

[0764] Output: Discount information (list of products with discounted prices)

[0765] Step 4:

[0766] Emotion data collection and analysis

[0767] The device (smartphone or tablet) uses a camera and microphone to collect the user's facial expressions, voice, and behavior in real time. Using TensorFlow and OpenCV, this data is analyzed to understand the user's emotional state.

[0768] Input: User's facial expression data, voice data, behavior data

[0769] Output: User's emotional state (emotion type and intensity)

[0770] Step 5:

[0771] Tailoring and sending notifications

[0772] The server adjusts the content and timing of notifications based on the emotion engine data and discount information, then sends the notifications to the device. A Python script is used to generate an appropriate message tailored to the user's current emotional state.

[0773] Input: User's emotional state, discount information

[0774] Output: Tailored notification content (message based on emotional state)

[0775] Step 6:

[0776] Uploading food records and footage of storage facilities

[0777] Users upload their daily food records and footage of the storage facility to a server via a smartphone app, which then analyzes the data and provides advice on how to avoid forgetting to buy things or overbuying.

[0778] Input: Meal record data, video data inside storage facilities

[0779] Output: Consumption advice (advice to prevent forgetting to buy or overspending)

[0780] Step 7:

[0781] Personalized suggestions

[0782] The server integrates the user's emotional state, food log, and inventory data to suggest suitable foods and drinks to the user, and uses a Python script to generate an appropriate item list based on health status and preferences.

[0783] Input: User's emotional state, food log, inventory data

[0784] Output: Personalized food and drink suggestions (list of suggested foods and drinks)

[0785] In this way, the system of the present invention effectively provides discount sales of unsold items and personalized food and beverage offerings based on the user's emotional state through real-time data collection and analysis.

[0786] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0787] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0788] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0789] [Third embodiment]

[0790] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0791] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0792] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0793] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0794] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0795] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0796] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0797] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0798] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0799] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0800] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0801] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0802] This invention is a system that reduces food waste and supports users' eating habits. The main purpose of this system is to identify products that are predicted to remain unsold and sell them at a discount. Furthermore, the system analyzes the user's food records and the contents of the refrigerator, provides advice to prevent forgetting to buy or overbuying, and makes personalized meal and product recommendations to the user.

[0803] 1. Reducing food waste

[0804] Inventory Data Collection

[0805] Server: Connects to the inventory systems of supermarkets and restaurants to collect inventory data in real time. This includes obtaining inventory information for each store via API. Inventory data includes product name, category, quantity, price, etc.

[0806] Unsold items forecast

[0807] Server: Uses AI models to analyze collected inventory data and identify products that are predicted to remain unsold, based on historical sales data and seasonal trends.

[0808] Discount information generation

[0809] Server: Based on the list of predicted unsold items, the server sets discount prices and generates discount price information on the online platform. For example, a 20% discount off the regular price is applied to items predicted to be unsold.

[0810] 2. Optimizing individual consumption

[0811] Collecting user's food records and refrigerator information

[0812] Users use a smartphone app to upload food logs and photos of their refrigerators, including the types and amounts of food they eat and images of the food in their refrigerators.

[0813] Analysis of food records and refrigerator information

[0814] Server: AI analyzes the user's food records and refrigerator photos to understand current inventory status and consumption trends. Food records are broken down through text analysis, and refrigerator photos are digitized using image analysis technology.

[0815] 3. Personalized meal suggestions

[0816] Proposals that take into account individual preferences and nutritional balance

[0817] Server: Provides personalized meal suggestions based on user preferences, nutritional balance, calorie information, and order history. This provides meal plans and recipes tailored to the user's tastes and health status.

[0818] 4. Real-time notifications

[0819] Discount information notification

[0820] Device: When a product the user wants becomes discounted, the user is notified via a smartphone app. The user's desired product information is registered in advance, and an immediate notification is sent when the product becomes discounted.

[0821] Specific examples

[0822] For example, suppose Supermarket A has a large inventory of a certain product, but sales trends suggest that some items will remain unsold. The system first collects this inventory data, analyzes it using an AI model, and predicts that the product is likely to remain unsold. Next, it sets the price of the product at a 20% discount and generates discount information.

[0823] If the product is included in User B's desired product list that he or she has registered in advance, a notification of the discount information will be sent to User B's device. User B will receive the notification and can purchase the product at the discounted price through the smartphone app and pick it up at a nearby store.

[0824] Furthermore, User B enters his / her daily food records into the app and uploads photos of his / her refrigerator. The system analyzes these and makes suggestions to User B about the foods he / she needs and how to achieve an appropriate nutritional balance. It also provides personalized recipes and meal plans based on User B's preferences and nutritional needs. In this way, the system of the present invention helps reduce food waste and support users in leading healthy eating habits.

[0825] The processing flow will be explained below.

[0826] 1. Reducing food waste

[0827] Step 1.1: Collect inventory data

[0828] 1. Server: Connects to the inventory systems of supermarkets and restaurants and collects inventory data in real time.

[0829] Specific operation: Send an API request to obtain inventory information (product name, category, quantity, price, etc.) for each store.

[0830] Step 1.2: Unsold items forecast

[0831] 2. Server: Uses AI models to analyze collected inventory data and identify products that are predicted to remain unsold.

[0832] Specific operation: The acquired inventory data is input into an AI model, and unsold items are predicted based on past sales data and seasonal trends.

[0833] Step 1.3: Generate discount information

[0834] 3. Server: Based on the list of predicted unsold items, set discount prices and generate discount price information on the online platform.

[0835] Specific operation: Apply a 20% discount off the regular price to products predicted to remain unsold, and generate discount information.

[0836] 2. Optimizing individual consumption

[0837] Step 2.1: Collecting user's food log and refrigerator information

[0838] 1. User: Uses a smartphone app to upload food records and photos of the refrigerator.

[0839] Specific actions: Use the in-app form to enter your food record and take and upload a photo of your refrigerator using your smartphone camera.

[0840] Step 2.2: Analyze food logs and refrigerator information

[0841] 2. Server: AI analyzes the user's meal records and refrigerator photos to understand current inventory status and consumption trends.

[0842] Specific operation: Image analysis technology is used to recognize food in the refrigerator, and food records are broken down and digitized through text analysis.

[0843] 3. Personalized meal suggestions

[0844] Step 3.1: Recommendations based on individual preferences and nutritional balance

[0845] 1. Server: Provides personalized meal suggestions based on the user's preferences, nutritional balance, calorie information, and order history.

[0846] What it does: It uses a database of users and an algorithm to generate meal plans and recipes and display them to the user.

[0847] 4. Real-time notifications

[0848] Step 4.1: Discount Notification

[0849] 1. Device: When a product the user wants is discounted, the user is notified via a smartphone app.

[0850] Specific operation: Receive discount information from the server and notify the user of the information via push notification.

[0851] Specific examples

[0852] For example, suppose Supermarket A has a large inventory of a certain product, but sales trends suggest that some items will remain unsold. The system first collects this inventory data, analyzes it using an AI model, and predicts that the product is likely to remain unsold. Next, it sets the price of the product at a 20% discount and generates discount information.

[0853] If the product is included in User B's desired product list that he or she has registered in advance, a notification of the discount information will be sent to User B's device. User B will receive the notification and can purchase the product at the discounted price through the smartphone app and pick it up at a nearby store.

[0854] Furthermore, User B enters his / her daily food records into the app and uploads photos of his / her refrigerator. The system analyzes these and makes suggestions to User B about the foods he / she needs and how to achieve an appropriate nutritional balance. It also provides personalized recipes and meal plans based on User B's preferences and nutritional needs. In this way, the system of the present invention helps reduce food waste and support users in leading healthy eating habits.

[0855] Example 1

[0856] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0857] Food waste is a major problem in modern society, with unsold products commonly being discarded. This problem wastes resources, puts a strain on the environment, and results in economic losses. Furthermore, due to inadequate food management in refrigerators, users often forget to buy food or overbuy. Furthermore, it is difficult to provide meals and products that are suited to each individual user.

[0858] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0859] In this invention, the server includes a means for analyzing store inventory information and predicting unsold items, a means for generating discount prices for unsold items, and a means for registering product information desired by users and sending notifications when the relevant products become discounted. This allows for discount sales of unsold items and efficient user purchasing. Furthermore, the server analyzes food records and refrigerator information to provide advice to prevent forgetting to buy or overbuying, and recommends meals and products that are individually suited to the user based on the user's preferences, nutritional balance, calorie information, and order history, thereby supporting the user's healthy and efficient eating habits.

[0860] "Store inventory information" refers to data such as product type, quantity, price, and category in stores such as supermarkets and restaurants.

[0861] "Unsold product prediction" refers to identifying products that are likely to remain unsold within a certain period of time based on past sales data and seasonal trends.

[0862] "Generating discount prices" refers to applying a certain discount rate to products that are predicted to remain unsold and setting a new selling price.

[0863] "User's desired product information" refers to the data registered in advance by the user regarding the product they wish to purchase. This data includes the product name, category, etc.

[0864] "Means for sending notifications" refers to the ability to send notifications to users about specific events (e.g., when a discount price is applied) via a smartphone app, email, etc.

[0865] "Meal records" refers to data that records the type, amount, and time of meals consumed by a user.

[0866] "Refrigerator information" refers to data including the type, quantity, expiration date, etc. of food currently stored in the user's refrigerator.

[0867] "Advice to prevent forgetting to buy or overbuying" refers to suggestions and notifications to help users purchase the food they need at the right time and avoid overbuying.

[0868] "Preferences" refers to a user's personal tastes and eating habits, including preferences for certain ingredients and dishes.

[0869] "Nutritional balance" refers to the proper ratio of nutrients that a user needs to stay healthy and in optimal physical condition.

[0870] "Calorie information" refers to data indicating the energy content of a food or meal, usually expressed in kilocalories (kcal).

[0871] "Order History" refers to a record of the products a user has purchased in the past. This data is used to analyze user purchasing trends and preferences.

[0872] "Individually recommending meals and products" means individually suggesting optimal meal plans and products based on the user's preferences and health condition.

[0873] This invention is a system that reduces food waste and supports users' eating habits. The system aims to identify products that are predicted to remain unsold and sell them at discounted prices. Furthermore, the system analyzes the user's food records and refrigerator information to provide advice on preventing forgetting to buy or overbuying, and to recommend meals and products personalized to the user.

[0874] Inventory Data Collection

[0875] The server connects to the store's inventory system via API and collects inventory data in real time. This inventory data includes product name, category, quantity, price, etc. Specifically, it sends an HTTP request to the store's endpoint, parses the JSON response, and stores it in a database.

[0876] Unsold items forecast

[0877] The server uses the collected inventory data to identify products that are predicted to remain unsold using an AI model (for example, a machine learning model using TensorFlow). This prediction is based on inputs such as past sales data and seasonal trends. Feature engineering is performed to increase the likelihood of remaining unsold items, and the model is trained and evaluated accordingly.

[0878] Discount information generation

[0879] The server sets discount prices and generates discount information based on the list of predicted unsold items. This discount information is updated in real time on websites and smartphone apps. The set discount prices are linked to inventory information through a database update process.

[0880] Collecting user's food records and refrigerator information

[0881] Users upload food records and photos of their refrigerators through a smartphone app. Food records are entered as text and photos of the refrigerator are uploaded as images. This allows the user's consumption data to be collected.

[0882] Analysis of food records and refrigerator information

[0883] The server analyzes the food records using natural language processing (NLP) technology and the photos of the refrigerator using image analysis technology (such as OpenCV or Google Cloud Vision API). This analysis allows the server to understand the user's current inventory status and consumption trends.

[0884] Optimizing individual consumption

[0885] The server then recommends meal plans and products that are tailored to the user based on their preferences, nutritional balance, calorie information, and order history, resulting in personalized suggestions for the user.

[0886] Real-time notifications

[0887] When the device (smartphone) receives discount information for a desired product, it immediately notifies the user via push notification, making it easy for the user to purchase the desired product at the discounted price.

[0888] Specific examples

[0889] For example, if a store has a large stock of tomatoes and predicts that some will remain unsold, the server first collects inventory data. It then analyzes this data using an AI model and predicts that the tomatoes are likely to remain unsold. The server then sets the price of the tomatoes at a 20% discount from the regular price and generates discount information. This information is instantly reflected on the website and smartphone app.

[0890] If User B has registered tomatoes from this store as a purchase preference, they will receive a discount notification on their smartphone and be able to purchase tomatoes at a discounted price through the app. Additionally, User B can enter their daily food records in text and upload photos of their refrigerator. The server analyzes this information and provides personalized meal plans and recipes based on User B's preferences and nutritional balance.

[0891] Prompt Sentence Examples

[0892] "In order to reduce food waste, please design a system that analyzes data on products that are predicted to remain unsold in stores and generates discount information. Furthermore, please include a function that analyzes when users upload their food records and refrigerator information and makes suggestions based on necessary foods and nutritional balance."

[0893] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0894] Step 1: Collect inventory data

[0895] The server connects to the store's inventory system via API and collects inventory data in real time. It sends an HTTP request using the store's endpoint URL and API key as input. In response, it receives inventory data in JSON format (product name, category, quantity, price, etc.). It stores this data in an internal database and converts it into a format that can be used in the next step.

[0896] Step 2: Unsold items forecast

[0897] The server uses the collected inventory data to identify products that are predicted to remain unsold using an AI model (using TensorFlow). As input, the inventory data and past sales data are fed into the AI ​​model. The model performs feature engineering, extracts important features, and starts making predictions. As output, the server gets a list of products predicted to remain unsold, along with their probabilities.

[0898] Step 3: Generate discount information

[0899] The server sets discount prices and generates discount information based on the predicted unsold items list. As input, it uses the list of predicted unsold items and their regular prices. As output, it calculates the discount price (e.g., 20% off the regular price) and generates discount information. This information is stored in a database and updated in real time on the website and smartphone app.

[0900] Step 4: Collect food records and fridge information

[0901] Users use a smartphone app to upload their meal records and photos of their refrigerator. As input, they enter the details of their meals in text and take and upload photos of the inside of their refrigerator. This data is sent to a server and analyzed.

[0902] Step 5: Analyze your food log and refrigerator information

[0903] The server uses AI technology to analyze the received meal records and refrigerator photos. Text data and image data from the user are used as input. The text data is analyzed using natural language processing (NLP), and the image data is analyzed using image analysis technology (OpenCV and Google Cloud Vision API). The output is data that identifies current inventory status and consumption trends.

[0904] Step 6: Optimize individual consumption

[0905] The server makes personalized meal plans and product recommendations based on the user's preferences, nutritional balance, calorie information, and order history. It uses the user's profile information and analysis results as input. The recommendation engine calculates the optimal meal plans and products and generates personalized suggestions as output.

[0906] Step 7: Discount Notification

[0907] When the device (smartphone) receives information about a discounted product that the user wants, it immediately notifies the user via push notification. As input, it receives discount information from the server. As output, it sends a push notification to the user and displays the discount information.

[0908] The above are the specific processing steps and flow of the system program.

[0909] (Application example 1)

[0910] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0911] Food waste has become a serious problem in today's consumer society. Unsold food leads to increased waste, resulting in environmental impact and economic losses. Users also have difficulty keeping track of their food records and the state of their refrigerators, which can lead to buying excess food. Furthermore, the lack of recommendations for meals and products tailored to individual tastes makes it difficult to maintain a proper nutritional balance.

[0912] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0913] In this invention, the server includes means for analyzing inventory information to identify products that are expected to remain unsold, means for generating information for selling unsold products at discounted prices, means for sending notifications of discounted products based on the user's purchasing history and preferences, means for receiving discount information for products registered by the user and purchasing the applicable products, and means for managing the refrigerator status and providing advice on foods to purchase, thereby enabling the reduction of food waste and the optimization of the user's eating habits.

[0914] "Inventory information" is a collection of data about the quantity and condition of products in stores and warehouses.

[0915] "Unsold goods prediction" is the process of identifying products that are likely to remain unsold in the future based on past sales data and current inventory data.

[0916] A "discount price" is a special price that is discounted from the regular selling price.

[0917] "Discount Notifications" are messages or alerts that inform users of discount information based on specific times or events.

[0918] "User purchase history" refers to a record of products purchased by a user in the past.

[0919] "Individually suitable meals" and "individually suitable product recommendations" are suggestions for optimal meals and products selected based on the user's preferences, nutritional balance, and calorie information.

[0920] "Refrigerator status" refers to data about the types and quantities of food in the refrigerator, their expiration dates, and so on.

[0921] "Food waste" refers to the amount and value of food that is discarded without being consumed.

[0922] This invention is a system that identifies products that are predicted to remain unsold and offers them to users at discounted prices, thereby reducing food waste and improving the user's purchasing experience. Furthermore, the system analyzes the user's food records and refrigerator status to provide personalized purchasing advice and meal suggestions. A system that realizes this application example is described in detail below.

[0923] Hardware and Software

[0924] This system mainly uses the following hardware and software:

[0925] Hardware used: Smartphone, server

[0926] Software used: Python (API calls, data analysis, user notifications), Sklearn (linear regression model), Requests (API communication), image recognition library

[0927] Data collection and analysis

[0928] The server uses APIs to retrieve inventory data, including product names, categories, quantities, and prices, in order to collect real-time inventory information from stores and warehouses.

[0929] The server uses an AI model to predict leftover items, which uses Sklearn's linear regression to analyze past sales data and current inventory data to identify items that are likely to remain unsold in the future.

[0930] Discount information generation and notification

[0931] The server sets discount prices for products that are predicted to remain unsold and generates the discount information. The generated discount information is notified to users in a personalized format based on their purchasing history and preferences. The notification is sent in real time via a smartphone app.

[0932] Refrigerator management and meal suggestions

[0933] Users upload photos of their refrigerators using a smartphone app. These photos are analyzed using an image recognition library on the server. The analysis results are stored in a database, and the status of the user's refrigerator is managed.

[0934] The server analyzes the refrigerator's contents and the user's food records, provides advice on how to avoid forgetting to buy or overbuying, and generates optimal meal suggestions and recipes based on the user's preferences and nutritional balance.

[0935] Specific examples

[0936] For example, if a user wants to manage their shopping at a supermarket, they first use a smartphone app to check the supermarket's inventory information. At this time, the server predicts unsold items based on past sales data and generates discount price information. If there are any discounted items in the user's desired product list, a notification is sent to the smartphone.

[0937] Next, to manage their home refrigerator, users upload a photo of their refrigerator. The server analyzes the photo and determines the inventory status of the refrigerator. The system automatically advises users on what they should buy more of or what they have bought more than they needed.

[0938] Example prompt sentence:

[0939] "It collects inventory data in real time, predicts unsold items, and generates discount information. It sends discount notifications to users and analyzes photos of refrigerators to make meal suggestions."

[0940] This allows users to shop efficiently, reduce food waste and maintain a healthy diet.

[0941] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0942] Step 1:

[0943] The server collects inventory information from stores and warehouses via API. It uses the API endpoint as input and obtains inventory data (product name, category, quantity, price, etc.) as output. Specifically, it uses the Requests library to send a request to the API, parses the returned JSON data, and stores it in an internal database.

[0944] Step 2:

[0945] The server analyzes the acquired inventory data using an AI model (linear regression model). It uses past sales data and current inventory data as input and generates a list of products that are predicted to remain unsold as output. Specifically, it uses Sklearn's linear regression module to predict unsold items using this data.

[0946] Step 3:

[0947] The server sets discount prices for products predicted to remain unsold and generates the discount information. It uses a list of predicted unsold products as input and generates discount price information as output. Specifically, it calculates the price by discounting a certain percentage (for example, 20%) from the regular price and lists the discount information.

[0948] Step 4:

[0949] The server takes into account the user's purchasing history and preferences to send notifications of discounted products. It uses the user's purchasing history and preference data as input and sends discount notifications for the relevant products as output. Specifically, it extracts relevant discount information based on the user's profile information and sends notifications to the smartphone.

[0950] Step 5:

[0951] A user uploads a photo of the refrigerator using a smartphone app. The photo data of the refrigerator is used as input, and image data is sent to the server as output. Specifically, the user takes a photo using the app's camera function and sends the photo to the server.

[0952] Step 6:

[0953] The server analyzes the uploaded photo of the refrigerator. It uses the received image data as input and generates an inventory list of the refrigerator as output. Specifically, it uses an image recognition library to identify the food items in the photo and store it as structured data.

[0954] Step 7:

[0955] The server analyzes the refrigerator inventory list and the user's food record to generate advice to prevent forgetting to buy or overbuying. It uses the refrigerator inventory list and food record data as input and generates advice information as output. Specifically, it queries the database and provides advice based on the user's consumption habits.

[0956] Step 8:

[0957] The server generates personalized meal suggestions and recipes based on the user's preferences and nutritional balance. It uses the user's preference data, nutritional information, and calorie information as input, and generates meal suggestions and recipe information as output. Specifically, it comprehensively analyzes this data and proposes the optimal meal plan for the user.

[0958] Through these processing steps, the system can reduce food waste and optimize users' diets.

[0959] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0960] This invention relates to a food waste reduction and dietary lifestyle support system that combines a system that identifies products that are predicted to remain unsold and sells them at discounted prices with an emotion engine that recognizes user emotions. This system can adjust the content of product recommendations and notifications based on the user's emotions, providing a more personalized service.

[0961] 1. Reducing food waste

[0962] Inventory Data Collection

[0963] Server: Connects to the inventory systems of supermarkets and restaurants to collect inventory data in real time, obtaining data such as product name, category, quantity, and price through API requests.

[0964] Unsold items forecast

[0965] Server: Uses AI models to analyze collected inventory data and identify items that are predicted to remain unsold, taking into account historical sales data and seasonal trends.

[0966] Discount information generation

[0967] Server: Based on the predicted list of unsold items, set a discount price and generate discount information on the online platform, for example, set a price 20% off the regular price.

[0968] 2. Optimizing individual consumption

[0969] Collecting user's food records and refrigerator information

[0970] Users use a smartphone app to upload daily food records and photos of their refrigerators. Food records include food types, portions, and calorie information.

[0971] Analysis of food records and refrigerator information

[0972] Server: AI analyzes the food records and refrigerator photos provided by the user. Image analysis technology is used to recognize the food in the refrigerator, and food records are converted into data through text analysis.

[0973] 3. Personalized meal suggestions

[0974] Proposals that take into account individual preferences and nutritional balance

[0975] Server: Provides personalized meal suggestions based on user preferences, nutritional balance, calorie information, and order history, resulting in meal plans and recipes tailored to the user.

[0976] Emotion engine integration

[0977] Server: Integrates an emotion engine that recognizes the user's emotions and collects emotional data from the user's voice, facial expressions, behavior, etc. This allows the current emotional state to be understood.

[0978] 4. Real-time notifications

[0979] Discount information notification

[0980] Device: When a product desired by the user is discounted, the system sends a notification via a smartphone app. The timing and content of the notification are adjusted based on data from the emotion engine.

[0981] Tailoring suggestions based on emotions

[0982] Server: Analyzes the user's emotional data and recommends meals and products based on their emotional state. For example, if a user is feeling depressed, it will suggest meals and products that will lift their spirits.

[0983] Specific examples

[0984] For example, suppose Supermarket A has a large inventory of a certain product, but sales trends suggest that it will remain unsold. This system first collects inventory data, analyzes it with an AI model, and predicts that the product is likely to remain unsold. It then sets the price of the product at a 20% discount from the regular price and generates discount information.

[0985] If the product is included in User B's wish list that he or she registered in advance, a notification of the discount information will be sent to User B's device. When sending the notification, the emotion engine detects User B's emotional state, and if, for example, User B is feeling stressed, the notification will include a message to help them relax.

[0986] Furthermore, User B enters his / her daily food record into the app and uploads photos of his / her refrigerator. The system analyzes this and provides User B with advice that takes into account the foods he / she needs and nutritional balance. The emotion engine also suggests recipes and meal plans based on User B's emotional state. For example, if User B is tired, it recommends meals suitable for restoring energy. In this way, the system of the present invention reduces food waste and supports healthy eating habits that take into account the user's emotional state.

[0987] The processing flow will be explained below.

[0988] Overall process flow for recruitment and purchasing

[0989] Step 1. Collect and analyze store data

[0990] Step 1.1:

[0991] Server: Connects to the supermarket or restaurant inventory system and sends API requests to collect inventory data, including product name, category, quantity, and price.

[0992] Step 1.2:

[0993] Server: Collected inventory data is input into the AI ​​model, which then predicts unsold items based on past sales data and seasonal trends. The AI ​​model uses machine learning to identify the items most likely to remain unsold.

[0994] Step 1.3:

[0995] Server: Sets discount prices based on the list of products predicted to remain unsold. For example, generates discount information for 20% off the regular price and registers the information on the online platform.

[0996] User Behavior and Analytics

[0997] Step 2. Collecting and analyzing user data

[0998] Step 2.1:

[0999] User: Using a smartphone app, users upload daily food records and photos of their refrigerator, including the types and amounts of food consumed and images of the food stored in the refrigerator.

[1000] Step 2.2:

[1001] Server: Analyzes photos of refrigerators uploaded by users using image analysis technology to determine current inventory status. At the same time, analyzes text from food records to digitize users' eating habits.

[1002] Step 2.3:

[1003] Server: Based on the user's refrigerator inventory and food records, the server provides advice to prevent forgetting to buy or overbuying. This advice includes a list of necessary foods and ways to save money.

[1004] Personalized offers and notifications

[1005] Step 3. Optimize meal suggestions and notifications

[1006] Step 3.1:

[1007] Server: Analyzes user preferences, nutritional balance, calorie information, and order history to suggest personalized meal plans and recipes based on the user's health and individual nutritional needs.

[1008] Step 3.2:

[1009] Server: Uses the emotion engine to collect emotional data from the user's voice, facial expressions, and behavior, thereby understanding the user's current emotional state.

[1010] Step 3.3:

[1011] Server: Analyzes the user's emotional data and recommends meals and products based on their emotional state. For example, if a user is feeling depressed, it will suggest foods and recipes that will improve their mood.

[1012] Step 4. Real-time notification of discount information

[1013] Step 4.1:

[1014] Device: Real-time notifications are sent to users' devices when discounted items become available. The content and timing of notifications are also adjusted based on the emotion engine.

[1015] Running a concrete example

[1016] Example: Supermarket A's product inventory and user B's behavior

[1017] Step 5.1:

[1018] Server: Collects data from Supermarket A's inventory system and analyzes it with an AI model. Specific products are listed as items that are predicted to remain unsold.

[1019] Step 5.2:

[1020] Server: Apply a 20% discount to the product and generate the discount information.

[1021] Step 5.3:

[1022] User B: If the product is on their wish list, a notification about the discount will be sent to their device. If User B is feeling stressed, a notification will be sent with a message to help them relax.

[1023] Step 5.4:

[1024] User: Enters daily food records into the app and uploads photos of the refrigerator, allowing the system to understand the user's eating habits and refrigerator inventory.

[1025] Step 5.5:

[1026] Server: Based on the emotion engine, it proposes recipes and meal plans that take into account User B's emotional state. For example, if User B is tired, it recommends meals that will help restore energy.

[1027] Through the above steps, the system of the present invention reduces food waste and supports healthy eating habits that take into account the user's emotional state.

[1028] Example 2

[1029] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1030] Food waste has become a serious problem in modern society, resulting in many products remaining unsold and discarded. Furthermore, suggestions tailored to individual user dietary needs are not provided, making it difficult to provide healthy and balanced meals. Furthermore, there is a lack of personalized services that take into account the user's emotional state. These circumstances are contributing to increased food waste and a decline in user satisfaction.

[1031] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1032] In this invention, the server includes: means for collecting store inventory information; means for analyzing the collected inventory information and using an artificial intelligence model to identify products predicted to remain unsold; means for generating discount price information based on the list of unsold products; means for publishing the generated discount price information on an online platform; means for using a terminal to register information about products desired by the user and receive notifications when the products are discounted; means for the user to receive the notifications and purchase the target products; means for using image analysis technology to analyze the user's food log and images of the contents of the refrigerator; means for providing advice based on the analysis results to prevent forgetting to buy or overbuying; means for recommending meals and products that are individually suited to the user's preferences, nutritional balance, calorie information, and order history; means for collecting and analyzing emotional data from the user's voice, facial expressions, and behavior; and means for adjusting the recommendations based on the collected emotional data. This enables food waste reduction and personalized dietary support tailored to the user's emotional state.

[1033] "Inventory information" is data about products held by stores and restaurants, such as product names, categories, quantities, and prices.

[1034] An "artificial intelligence model" is an algorithm that learns from past data and trends and makes predictions and classifications based on new data.

[1035] "Discount price information" is price information set lower than the regular price for products that are expected to remain unsold.

[1036] An "online platform" is a digital space for providing product information and discount information via the Internet.

[1037] A "terminal" is an electronic device, such as a smartphone or tablet, that allows a user to receive and operate information.

[1038] "Food records" are data that include detailed information such as the types, amounts, and calories of the foods a user consumes.

[1039] "Image analysis technology" is a technology that processes image data and extracts meaningful information.

[1040] "Means for providing advice" refers to functions or methods that provide useful information or suggestions to users based on the analysis results.

[1041] "Preferences" is data that refers to a user's preferred foods and flavors.

[1042] "Nutritional balance" is data that indicates the proportions of necessary nutrients such as protein, lipids, carbohydrates, vitamins, and minerals.

[1043] "Calorie information" is data that indicates the amount of energy ingested from food or meals.

[1044] "Order History" is a record of products and services a User has previously purchased.

[1045] "Emotional data" is information that indicates the psychological state of a user, collected from their voice, facial expressions, behavior, etc.

[1046] The "emotion engine" is a system that analyzes collected emotional data and evaluates the user's state based on the results.

[1047] The present invention relates to a food waste reduction and dietary lifestyle support system that combines a system that identifies unsold products and sells them at discounted prices with an emotion engine that recognizes user emotions. This system is implemented using a specific combination of hardware and software.

[1048] Specifically, the server performs the following processes: First, it collects inventory information from stores and restaurants. To do this, it uses API requests to obtain data such as product name, category, quantity, and price. Next, it inputs the collected inventory information into an AI model to identify products that are predicted to remain unsold. This AI model uses machine learning libraries such as TensorFlow and PyTorch. It then generates discount price information based on the list of unsold products and publishes it on an online platform.

[1049] Users use a smartphone app to upload their daily food records and images of their refrigerator. The food records include information on the type, amount, and calories of food. The server analyzes the uploaded data and uses image analysis technology (such as OpenCV or TensorFlow) to recognize the foods in the refrigerator, and converts the food records into data using text analysis.

[1050] To provide personalized meal suggestions, the server considers the user's preferences, nutritional balance, calorie information, and order history. This allows it to propose personalized meal plans and recipes. It also integrates an emotion engine that collects and analyzes emotional data from the user's voice, facial expressions, and behavior. Based on the analysis results, it adjusts the content of suggestions and the timing of notifications.

[1051] When a discount is offered on a product the user wants, the system will send a notification via the smartphone app. The content and timing of the notification will be adjusted based on data from the emotion engine.

[1052] For example, if supermarket A has a large stock of a particular product and sales trends indicate that it will remain unsold, the server collects inventory data, analyzes it using an AI model, and predicts that the product is likely to remain unsold. The server then sets the price of the product at a 20% discount from the normal price and generates discount information. If the product is included in User B's desired product list that he or she previously registered, a notification of the discount information is sent to User B's device. When the notification is sent, the emotion engine detects User B's emotional state; for example, if User B is feeling stressed, the notification will include a message to help them relax.

[1053] Furthermore, User B enters their daily food records into the app and uploads photos of their refrigerator. The server analyzes this and provides advice on the foods User B needs and nutritional balance. The emotion engine also suggests recipes and meal plans based on User B's emotional state. For example, if User B is tired, it will recommend meals suitable for restoring energy.

[1054] Example prompt sentence:

[1055] "Please tell me how to specifically design a system that uses an emotion engine to recognize the emotional state of a particular user and then makes product or meal recommendations based on that emotion."

[1056] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1057] Step 1:

[1058] Inventory data collection

[1059] Server: Connects to the store or restaurant inventory system and collects inventory data such as product name, category, quantity, and price through API requests. Specifically, it accesses the API endpoint and obtains real-time inventory information.

[1060] Input: API response data from a store or restaurant inventory system.

[1061] Output: An inventory dataset containing product name, category, quantity, and price.

[1062] Step 2:

[1063] Unsold items forecast

[1064] Server: Collected inventory data is input into the AI ​​model to identify products that are predicted to remain unsold. Taking into account past sales data and seasonal trends, predictions are made using machine learning models using TensorFlow and PyTorch.

[1065] Input: Collected inventory dataset.

[1066] Output: A list of items that are predicted to remain unsold.

[1067] Step 3:

[1068] Generate discount information

[1069] Server: Based on the list of unsold items, the server sets a price 20% off the regular price and generates discount information. The generated discount information is published on the online platform.

[1070] Input: A list of unsold items.

[1071] Output: Discount information including discount price and product information.

[1072] Step 4:

[1073] Food records and refrigerator information collection

[1074] User: Using a smartphone app, users upload daily food records and photos of their refrigerator. Food records include food types, portions, and calorie information.

[1075] Input: User-uploaded food logs and photos of the refrigerator.

[1076] Output: Food records and photo data stored in cloud storage.

[1077] Step 5:

[1078] Analysis of food records and refrigerator information

[1079] Server: Analyzes the uploaded data, recognizes the food in the refrigerator using image analysis technology, and converts the food records into data using text analysis. Tools such as OpenCV and TensorFlow are used.

[1080] Input: Saved food records and photo data.

[1081] Output: Text data of the food record and a list of recognized foods in the refrigerator.

[1082] Step 6:

[1083] Personalized meal suggestions

[1084] Server: Providing personalized meal recommendations based on user preferences, nutritional balance, calorie information, and order history. Using user data to provide optimal meal plans and recipes.

[1085] Input: Text data of food records, list of recognized foods in the refrigerator, user preferences, nutritional information, and order history.

[1086] Output: A list of meal plans and recipe suggestions suitable for the user.

[1087] Step 7:

[1088] Emotion engine integration

[1089] Server: Collects and analyzes emotional data from the user's voice, facial expressions, and behavior. Tailors suggestions based on the user's emotional state. This is achieved using emotion analysis technologies such as DeepFace.

[1090] Input: User's voice, facial expression, and behavior data.

[1091] Output: User's emotional state data and suggestion information based on it.

[1092] Step 8:

[1093] Discount information notification

[1094] Device: A smartphone app sends notifications when a desired product becomes discounted. The timing and content of notifications are adjusted based on data from the emotion engine.

[1095] Input: Discount information and user emotional state data.

[1096] Output: A message notifying you of the discount.

[1097] Step 9:

[1098] Tailoring suggestions based on emotions

[1099] Server: Analyzes emotional data and recommends meals and products based on the user's emotional state. If the user is feeling down, it will make suggestions to lift their spirits.

[1100] Input: User emotional state data.

[1101] Output: A list of food and product suggestions corresponding to your emotional state.

[1102] (Application example 2)

[1103] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1104] In today's world, where food waste is a serious problem, there is a need to efficiently identify products that are predicted to remain unsold and sell them at appropriate discount prices. Furthermore, a system is needed to make personalized suggestions to users and send timely and appropriate product notifications to increase their purchasing motivation. Furthermore, it is also a challenge to provide passengers in autonomous vehicles with food and beverages that match their emotional state, thereby providing a comfortable travel experience.

[1105] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1106] In this invention, the server includes means for analyzing inventory information to identify products that are predicted to remain unsold, means for generating information for selling unsold products at discounted prices, means for registering information about products desired by users and sending notifications when the products become available at discounted prices, means for receiving discount information about products registered by users and purchasing the target products, and means for adjusting the content and timing of notifications using an emotion engine that analyzes user emotions. This enables efficient identification and sale of unsold products, personalized notifications to users, and emotional provision of food and beverages to passengers during travel.

[1107] "Inventory information" refers to data relating to the quantity, type, location, etc. of products in a commercial facility or storage facility.

[1108] "Discount pricing" means that a product is offered at a price lower than its normal selling price.

[1109] The "emotion engine" is a system that collects and analyzes emotional data from the user's voice, facial expressions, behavior, etc. to understand the user's emotional state.

[1110] A "notification" is a message or alarm sent to a communication device such as a smartphone or tablet to inform the user of specific information.

[1111] "Food records" are data recorded by users that includes daily meal contents, meal amounts, nutritional information, etc.

[1112] "Video inside storage facilities" refers to images or video data taken with a camera of the inside of storage facilities such as refrigerators and pantries.

[1113] "Preferences" refers to information about a user's likes, dislikes, and preferences.

[1114] "Nutritional balance" refers to a state in which the nutrients in the food consumed by the user are appropriately distributed.

[1115] "Calorie information" is data that indicates the energy content of foods and drinks, and is usually expressed in "kilocalories (kcal)."

[1116] "Order history" refers to recorded data of products that a user has purchased or ordered in the past.

[1117] This invention combines a system that identifies unsold products and sells them at discounted prices with an emotion engine that recognizes user emotions to reduce food waste and support dietary habits. The system operates in anticipation of personalized food and beverage delivery to passengers in autonomous vehicles.

[1118] The server includes the following means:

[1119] 1. Means for analyzing inventory information: This system works in conjunction with the inventory management system of the storage equipment installed in the autonomous vehicle to collect inventory data in real time. The server obtains information such as product name, category, quantity, and price through the implemented API. Data collection and management are performed using Python.

[1120] 2. Discount price generation method: Based on the collected inventory data, an AI model is used to predict unsold items. This model includes a function that uses TensorFlow to perform predictive analysis taking into account past sales data and seasonal trends. The server sets discount prices based on the predicted list of unsold items and generates discount information on the online platform.

[1121] 3. Means of integrating emotion engine: Using a camera and microphone, the user's facial expressions, voice, and behavior are analyzed in real time to grasp the user's emotional state. The emotion engine analyzes emotions using facial recognition and voice analysis technologies using TensorFlow and OpenCV. Emotion data is reflected in food and drink recommendations based on the user's emotional fluctuations.

[1122] The device (smartphone or tablet) has the following features:

[1123] 1. Notification method: Based on data from the emotion engine, food and drink recommendations and discount information tailored to the passenger's state are sent. These notifications are sent in real time, and the content and timing of the notifications are adjusted according to the passenger's emotional state.

[1124] The user (passenger) performs the following operations:

[1125] 1. Uploading food records and footage of the storage facility: Food records and footage of the storage facility are uploaded to the server via a smartphone app. The server analyzes the data and provides advice to prevent forgetting to buy things or overbuying. For example, if the user is tired, it will suggest a drink that will help restore energy.

[1126] To illustrate, consider the following scenario:

[1127] Scenario: Passenger A is traveling in an autonomous vehicle and is detected as tired by the emotion engine.

[1128] Example prompt: "I sense that Passenger A is tired. Would you like to offer him a refreshment drink?"

[1129] In this way, the system of the present invention enables efficient identification and sale of unsold merchandise, personalized notifications to users, and emotion-based food and beverage offerings to passengers during travel.

[1130] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1131] Step 1:

[1132] Inventory Data Collection

[1133] The server collects real-time inventory information from the storage facilities installed in the autonomous vehicles, obtaining data such as product name, category, quantity, and price through API requests. This data is collected using a Python script and stored in a database.

[1134] Input: Inventory information from storage facilities (product name, category, quantity, price)

[1135] Output: Stock information is saved in the database

[1136] Step 2:

[1137] Unsold items forecast

[1138] The server uses AI models based on collected inventory data to identify products that are likely to remain unsold, and TensorFlow is used to perform predictive analysis that takes into account past sales data and seasonal trends.

[1139] Input: Past sales data, current inventory data

[1140] Output: Unsold items prediction result (list of items predicted to be unsold)

[1141] Step 3:

[1142] Discount information generation

[1143] The server sets discount prices based on the predicted list of unsold items and generates discount information on the online platform. Specifically, it uses a Python script to calculate the discount price for each item and stores the information in a database.

[1144] Input: Unsold items prediction result (list of items predicted to be unsold)

[1145] Output: Discount information (list of products with discounted prices)

[1146] Step 4:

[1147] Emotion data collection and analysis

[1148] The device (smartphone or tablet) uses a camera and microphone to collect the user's facial expressions, voice, and behavior in real time. Using TensorFlow and OpenCV, this data is analyzed to understand the user's emotional state.

[1149] Input: User's facial expression data, voice data, behavior data

[1150] Output: User's emotional state (emotion type and intensity)

[1151] Step 5:

[1152] Tailoring and sending notifications

[1153] The server adjusts the content and timing of notifications based on the emotion engine data and discount information, then sends the notifications to the device. A Python script is used to generate an appropriate message tailored to the user's current emotional state.

[1154] Input: User's emotional state, discount information

[1155] Output: Tailored notification content (message based on emotional state)

[1156] Step 6:

[1157] Uploading food records and footage of storage facilities

[1158] Users upload their daily food records and footage of the storage facility to a server via a smartphone app, which then analyzes the data and provides advice on how to avoid forgetting to buy things or overbuying.

[1159] Input: Meal record data, video data inside storage facilities

[1160] Output: Consumption advice (advice to prevent forgetting to buy or overspending)

[1161] Step 7:

[1162] Personalized suggestions

[1163] The server integrates the user's emotional state, food log, and inventory data to suggest suitable foods and drinks to the user, and uses a Python script to generate an appropriate item list based on health status and preferences.

[1164] Input: User's emotional state, food log, inventory data

[1165] Output: Personalized food and drink suggestions (list of suggested foods and drinks)

[1166] In this way, the system of the present invention effectively provides discount sales of unsold items and personalized food and beverage offerings based on the user's emotional state through real-time data collection and analysis.

[1167] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1168] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1169] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1170] [Fourth embodiment]

[1171] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1172] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1173] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1174] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1175] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1176] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1177] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1178] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1179] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1180] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1181] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1182] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1183] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1184] This invention is a system that reduces food waste and supports users' eating habits. The main purpose of this system is to identify products that are predicted to remain unsold and sell them at a discount. Furthermore, the system analyzes the user's food records and the contents of the refrigerator, provides advice to prevent forgetting to buy or overbuying, and makes personalized meal and product recommendations to the user.

[1185] 1. Reducing food waste

[1186] Inventory Data Collection

[1187] Server: Connects to the inventory systems of supermarkets and restaurants to collect inventory data in real time. This includes obtaining inventory information for each store via API. Inventory data includes product name, category, quantity, price, etc.

[1188] Unsold items forecast

[1189] Server: Uses AI models to analyze collected inventory data and identify products that are predicted to remain unsold, based on historical sales data and seasonal trends.

[1190] Discount information generation

[1191] Server: Based on the list of predicted unsold items, the server sets discount prices and generates discount price information on the online platform. For example, a 20% discount off the regular price is applied to items predicted to be unsold.

[1192] 2. Optimizing individual consumption

[1193] Collecting user's food records and refrigerator information

[1194] Users use a smartphone app to upload food logs and photos of their refrigerators, including the types and amounts of food they eat and images of the food in their refrigerators.

[1195] Analysis of food records and refrigerator information

[1196] Server: AI analyzes the user's food records and refrigerator photos to understand current inventory status and consumption trends. Food records are broken down through text analysis, and refrigerator photos are digitized using image analysis technology.

[1197] 3. Personalized meal suggestions

[1198] Proposals that take into account individual preferences and nutritional balance

[1199] Server: Provides personalized meal suggestions based on user preferences, nutritional balance, calorie information, and order history. This provides meal plans and recipes tailored to the user's tastes and health status.

[1200] 4. Real-time notifications

[1201] Discount information notification

[1202] Device: When a product the user wants becomes discounted, the user is notified via a smartphone app. The user's desired product information is registered in advance, and an immediate notification is sent when the product becomes discounted.

[1203] Specific examples

[1204] For example, suppose Supermarket A has a large inventory of a certain product, but sales trends suggest that some items will remain unsold. The system first collects this inventory data, analyzes it using an AI model, and predicts that the product is likely to remain unsold. Next, it sets the price of the product at a 20% discount and generates discount information.

[1205] If the product is included in User B's desired product list that he or she has registered in advance, a notification of the discount information will be sent to User B's device. User B will receive the notification and can purchase the product at the discounted price through the smartphone app and pick it up at a nearby store.

[1206] Furthermore, User B enters his / her daily food records into the app and uploads photos of his / her refrigerator. The system analyzes these and makes suggestions to User B about the foods he / she needs and how to achieve an appropriate nutritional balance. It also provides personalized recipes and meal plans based on User B's preferences and nutritional needs. In this way, the system of the present invention helps reduce food waste and support users in leading healthy eating habits.

[1207] The processing flow will be explained below.

[1208] 1. Reducing food waste

[1209] Step 1.1: Collect inventory data

[1210] 1. Server: Connects to the inventory systems of supermarkets and restaurants and collects inventory data in real time.

[1211] Specific operation: Send an API request to obtain inventory information (product name, category, quantity, price, etc.) for each store.

[1212] Step 1.2: Unsold items forecast

[1213] 2. Server: Uses AI models to analyze collected inventory data and identify products that are predicted to remain unsold.

[1214] Specific operation: The acquired inventory data is input into an AI model, and unsold items are predicted based on past sales data and seasonal trends.

[1215] Step 1.3: Generate discount information

[1216] 3. Server: Based on the list of predicted unsold items, set discount prices and generate discount price information on the online platform.

[1217] Specific operation: Apply a 20% discount off the regular price to products predicted to remain unsold, and generate discount information.

[1218] 2. Optimizing individual consumption

[1219] Step 2.1: Collecting user's food log and refrigerator information

[1220] 1. User: Uses a smartphone app to upload food records and photos of the refrigerator.

[1221] Specific actions: Use the in-app form to enter your food record and take and upload a photo of your refrigerator using your smartphone camera.

[1222] Step 2.2: Analyze food logs and refrigerator information

[1223] 2. Server: AI analyzes the user's meal records and refrigerator photos to understand current inventory status and consumption trends.

[1224] Specific operation: Image analysis technology is used to recognize food in the refrigerator, and food records are broken down and digitized through text analysis.

[1225] 3. Personalized meal suggestions

[1226] Step 3.1: Recommendations based on individual preferences and nutritional balance

[1227] 1. Server: Provides personalized meal suggestions based on the user's preferences, nutritional balance, calorie information, and order history.

[1228] What it does: It uses a database of users and an algorithm to generate meal plans and recipes and display them to the user.

[1229] 4. Real-time notifications

[1230] Step 4.1: Discount Notification

[1231] 1. Device: When a product the user wants is discounted, the user is notified via a smartphone app.

[1232] Specific operation: Receive discount information from the server and notify the user of the information via push notification.

[1233] Specific examples

[1234] For example, suppose Supermarket A has a large inventory of a certain product, but sales trends suggest that some items will remain unsold. The system first collects this inventory data, analyzes it using an AI model, and predicts that the product is likely to remain unsold. Next, it sets the price of the product at a 20% discount and generates discount information.

[1235] If the product is included in User B's desired product list that he or she has registered in advance, a notification of the discount information will be sent to User B's device. User B will receive the notification and can purchase the product at the discounted price through the smartphone app and pick it up at a nearby store.

[1236] Furthermore, User B enters his / her daily food records into the app and uploads photos of his / her refrigerator. The system analyzes these and makes suggestions to User B about the foods he / she needs and how to achieve an appropriate nutritional balance. It also provides personalized recipes and meal plans based on User B's preferences and nutritional needs. In this way, the system of the present invention helps reduce food waste and support users in leading healthy eating habits.

[1237] Example 1

[1238] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1239] Food waste is a major problem in modern society, with unsold products commonly being discarded. This problem wastes resources, puts a strain on the environment, and results in economic losses. Furthermore, due to inadequate food management in refrigerators, users often forget to buy food or overbuy. Furthermore, it is difficult to provide meals and products that are suited to each individual user.

[1240] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1241] In this invention, the server includes a means for analyzing store inventory information and predicting unsold items, a means for generating discount prices for unsold items, and a means for registering product information desired by users and sending notifications when the relevant products become discounted. This allows for discount sales of unsold items and efficient user purchasing. Furthermore, the server analyzes food records and refrigerator information to provide advice to prevent forgetting to buy or overbuying, and recommends meals and products that are individually suited to the user based on the user's preferences, nutritional balance, calorie information, and order history, thereby supporting the user's healthy and efficient eating habits.

[1242] "Store inventory information" refers to data such as product type, quantity, price, and category in stores such as supermarkets and restaurants.

[1243] "Unsold product prediction" refers to identifying products that are likely to remain unsold within a certain period of time based on past sales data and seasonal trends.

[1244] "Generating discount prices" refers to applying a certain discount rate to products that are predicted to remain unsold and setting a new selling price.

[1245] "User's desired product information" refers to the data registered in advance by the user regarding the product they wish to purchase. This data includes the product name, category, etc.

[1246] "Means for sending notifications" refers to the ability to send notifications to users about specific events (e.g., when a discount price is applied) via a smartphone app, email, etc.

[1247] "Meal records" refers to data that records the type, amount, and time of meals consumed by a user.

[1248] "Refrigerator information" refers to data including the type, quantity, expiration date, etc. of food currently stored in the user's refrigerator.

[1249] "Advice to prevent forgetting to buy or overbuying" refers to suggestions and notifications to help users purchase the food they need at the right time and avoid overbuying.

[1250] "Preferences" refers to a user's personal tastes and eating habits, including preferences for certain ingredients and dishes.

[1251] "Nutritional balance" refers to the proper ratio of nutrients that a user needs to stay healthy and in optimal physical condition.

[1252] "Calorie information" refers to data indicating the energy content of a food or meal, usually expressed in kilocalories (kcal).

[1253] "Order History" refers to a record of the products a user has purchased in the past. This data is used to analyze user purchasing trends and preferences.

[1254] "Individually recommending meals and products" means individually suggesting optimal meal plans and products based on the user's preferences and health condition.

[1255] This invention is a system that reduces food waste and supports users' eating habits. The system aims to identify products that are predicted to remain unsold and sell them at discounted prices. Furthermore, the system analyzes the user's food records and refrigerator information to provide advice on preventing forgetting to buy or overbuying, and to recommend meals and products personalized to the user.

[1256] Inventory Data Collection

[1257] The server connects to the store's inventory system via API and collects inventory data in real time. This inventory data includes product name, category, quantity, price, etc. Specifically, it sends an HTTP request to the store's endpoint, parses the JSON response, and stores it in a database.

[1258] Unsold items forecast

[1259] The server uses the collected inventory data to identify products that are predicted to remain unsold using an AI model (for example, a machine learning model using TensorFlow). This prediction is based on inputs such as past sales data and seasonal trends. Feature engineering is performed to increase the likelihood of remaining unsold items, and the model is trained and evaluated accordingly.

[1260] Discount information generation

[1261] The server sets discount prices and generates discount information based on the list of predicted unsold items. This discount information is updated in real time on websites and smartphone apps. The set discount prices are linked to inventory information through a database update process.

[1262] Collecting user's food records and refrigerator information

[1263] Users upload food records and photos of their refrigerators through a smartphone app. Food records are entered as text and photos of the refrigerator are uploaded as images. This allows the user's consumption data to be collected.

[1264] Analysis of food records and refrigerator information

[1265] The server analyzes the food records using natural language processing (NLP) technology and the photos of the refrigerator using image analysis technology (such as OpenCV or Google Cloud Vision API). This analysis allows the server to understand the user's current inventory status and consumption trends.

[1266] Optimizing individual consumption

[1267] The server then recommends meal plans and products that are tailored to the user based on their preferences, nutritional balance, calorie information, and order history, resulting in personalized suggestions for the user.

[1268] Real-time notifications

[1269] When the device (smartphone) receives discount information for a desired product, it immediately notifies the user via push notification, making it easy for the user to purchase the desired product at the discounted price.

[1270] Specific examples

[1271] For example, if a store has a large stock of tomatoes and predicts that some will remain unsold, the server first collects inventory data. It then analyzes this data using an AI model and predicts that the tomatoes are likely to remain unsold. The server then sets the price of the tomatoes at a 20% discount from the regular price and generates discount information. This information is instantly reflected on the website and smartphone app.

[1272] If User B has registered tomatoes from this store as a purchase preference, they will receive a discount notification on their smartphone and be able to purchase tomatoes at a discounted price through the app. Additionally, User B can enter their daily food records in text and upload photos of their refrigerator. The server analyzes this information and provides personalized meal plans and recipes based on User B's preferences and nutritional balance.

[1273] Prompt Sentence Examples

[1274] "In order to reduce food waste, please design a system that analyzes data on products that are predicted to remain unsold in stores and generates discount information. Furthermore, please include a function that analyzes when users upload their food records and refrigerator information and makes suggestions based on necessary foods and nutritional balance."

[1275] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1276] Step 1: Collect inventory data

[1277] The server connects to the store's inventory system via API and collects inventory data in real time. It sends an HTTP request using the store's endpoint URL and API key as input. In response, it receives inventory data in JSON format (product name, category, quantity, price, etc.). It stores this data in an internal database and converts it into a format that can be used in the next step.

[1278] Step 2: Unsold items forecast

[1279] The server uses the collected inventory data to identify products that are predicted to remain unsold using an AI model (using TensorFlow). As input, the inventory data and past sales data are fed into the AI ​​model. The model performs feature engineering, extracts important features, and starts making predictions. As output, the server gets a list of products predicted to remain unsold, along with their probabilities.

[1280] Step 3: Generate discount information

[1281] The server sets discount prices and generates discount information based on the predicted unsold items list. As input, it uses the list of predicted unsold items and their regular prices. As output, it calculates the discount price (e.g., 20% off the regular price) and generates discount information. This information is stored in a database and updated in real time on the website and smartphone app.

[1282] Step 4: Collect food records and fridge information

[1283] Users use a smartphone app to upload their meal records and photos of their refrigerator. As input, they enter the details of their meals in text and take and upload photos of the inside of their refrigerator. This data is sent to a server and analyzed.

[1284] Step 5: Analyze your food log and refrigerator information

[1285] The server uses AI technology to analyze the received meal records and refrigerator photos. Text data and image data from the user are used as input. The text data is analyzed using natural language processing (NLP), and the image data is analyzed using image analysis technology (OpenCV and Google Cloud Vision API). The output is data that identifies current inventory status and consumption trends.

[1286] Step 6: Optimize individual consumption

[1287] The server makes personalized meal plans and product recommendations based on the user's preferences, nutritional balance, calorie information, and order history. It uses the user's profile information and analysis results as input. The recommendation engine calculates the optimal meal plans and products and generates personalized suggestions as output.

[1288] Step 7: Discount Notification

[1289] When the device (smartphone) receives information about a discounted product that the user wants, it immediately notifies the user via push notification. As input, it receives discount information from the server. As output, it sends a push notification to the user and displays the discount information.

[1290] The above are the specific processing steps and flow of the system program.

[1291] (Application example 1)

[1292] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1293] Food waste has become a serious problem in today's consumer society. Unsold food leads to increased waste, resulting in environmental impact and economic losses. Users also have difficulty keeping track of their food records and the state of their refrigerators, which can lead to buying excess food. Furthermore, the lack of recommendations for meals and products tailored to individual tastes makes it difficult to maintain a proper nutritional balance.

[1294] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1295] In this invention, the server includes means for analyzing inventory information to identify products that are expected to remain unsold, means for generating information for selling unsold products at discounted prices, means for sending notifications of discounted products based on the user's purchasing history and preferences, means for receiving discount information for products registered by the user and purchasing the applicable products, and means for managing the refrigerator status and providing advice on foods to purchase, thereby enabling the reduction of food waste and the optimization of the user's eating habits.

[1296] "Inventory information" is a collection of data about the quantity and condition of products in stores and warehouses.

[1297] "Unsold goods prediction" is the process of identifying products that are likely to remain unsold in the future based on past sales data and current inventory data.

[1298] A "discount price" is a special price that is discounted from the regular selling price.

[1299] "Discount Notifications" are messages or alerts that inform users of discount information based on specific times or events.

[1300] "User purchase history" refers to a record of products purchased by a user in the past.

[1301] "Individually suitable meals" and "individually suitable product recommendations" are suggestions for optimal meals and products selected based on the user's preferences, nutritional balance, and calorie information.

[1302] "Refrigerator status" refers to data about the types and quantities of food in the refrigerator, their expiration dates, and so on.

[1303] "Food waste" refers to the amount and value of food that is discarded without being consumed.

[1304] This invention is a system that identifies products that are predicted to remain unsold and offers them to users at discounted prices, thereby reducing food waste and improving the user's purchasing experience. Furthermore, the system analyzes the user's food records and refrigerator status to provide personalized purchasing advice and meal suggestions. A system that realizes this application example is described in detail below.

[1305] Hardware and Software

[1306] This system mainly uses the following hardware and software:

[1307] Hardware used: Smartphone, server

[1308] Software used: Python (API calls, data analysis, user notifications), Sklearn (linear regression model), Requests (API communication), image recognition library

[1309] Data collection and analysis

[1310] The server uses APIs to retrieve inventory data, including product names, categories, quantities, and prices, in order to collect real-time inventory information from stores and warehouses.

[1311] The server uses an AI model to predict leftover items, which uses Sklearn's linear regression to analyze past sales data and current inventory data to identify items that are likely to remain unsold in the future.

[1312] Discount information generation and notification

[1313] The server sets discount prices for products that are predicted to remain unsold and generates the discount information. The generated discount information is notified to users in a personalized format based on their purchasing history and preferences. The notification is sent in real time via a smartphone app.

[1314] Refrigerator management and meal suggestions

[1315] Users upload photos of their refrigerators using a smartphone app. These photos are analyzed using an image recognition library on the server. The analysis results are stored in a database, and the status of the user's refrigerator is managed.

[1316] The server analyzes the refrigerator's contents and the user's food records, provides advice on how to avoid forgetting to buy or overbuying, and generates optimal meal suggestions and recipes based on the user's preferences and nutritional balance.

[1317] Specific examples

[1318] For example, if a user wants to manage their shopping at a supermarket, they first use a smartphone app to check the supermarket's inventory information. At this time, the server predicts unsold items based on past sales data and generates discount price information. If there are any discounted items in the user's desired product list, a notification is sent to the smartphone.

[1319] Next, to manage their home refrigerator, users upload a photo of their refrigerator. The server analyzes the photo and determines the inventory status of the refrigerator. The system automatically advises users on what they should buy more of or what they have bought more than they needed.

[1320] Example prompt sentence:

[1321] "It collects inventory data in real time, predicts unsold items, and generates discount information. It sends discount notifications to users and analyzes photos of refrigerators to make meal suggestions."

[1322] This allows users to shop efficiently, reduce food waste and maintain a healthy diet.

[1323] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1324] Step 1:

[1325] The server collects inventory information from stores and warehouses via API. It uses the API endpoint as input and obtains inventory data (product name, category, quantity, price, etc.) as output. Specifically, it uses the Requests library to send a request to the API, parses the returned JSON data, and stores it in an internal database.

[1326] Step 2:

[1327] The server analyzes the acquired inventory data using an AI model (linear regression model). It uses past sales data and current inventory data as input and generates a list of products that are predicted to remain unsold as output. Specifically, it uses Sklearn's linear regression module to predict unsold items using this data.

[1328] Step 3:

[1329] The server sets discount prices for products predicted to remain unsold and generates the discount information. It uses a list of predicted unsold products as input and generates discount price information as output. Specifically, it calculates the price by discounting a certain percentage (for example, 20%) from the regular price and lists the discount information.

[1330] Step 4:

[1331] The server takes into account the user's purchasing history and preferences to send notifications of discounted products. It uses the user's purchasing history and preference data as input and sends discount notifications for the relevant products as output. Specifically, it extracts relevant discount information based on the user's profile information and sends notifications to the smartphone.

[1332] Step 5:

[1333] A user uploads a photo of the refrigerator using a smartphone app. The photo data of the refrigerator is used as input, and image data is sent to the server as output. Specifically, the user takes a photo using the app's camera function and sends the photo to the server.

[1334] Step 6:

[1335] The server analyzes the uploaded photo of the refrigerator. It uses the received image data as input and generates an inventory list of the refrigerator as output. Specifically, it uses an image recognition library to identify the food items in the photo and store it as structured data.

[1336] Step 7:

[1337] The server analyzes the refrigerator inventory list and the user's food record to generate advice to prevent forgetting to buy or overbuying. It uses the refrigerator inventory list and food record data as input and generates advice information as output. Specifically, it queries the database and provides advice based on the user's consumption habits.

[1338] Step 8:

[1339] The server generates personalized meal suggestions and recipes based on the user's preferences and nutritional balance. It uses the user's preference data, nutritional information, and calorie information as input, and generates meal suggestions and recipe information as output. Specifically, it comprehensively analyzes this data and proposes the optimal meal plan for the user.

[1340] Through these processing steps, the system can reduce food waste and optimize users' diets.

[1341] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1342] This invention relates to a food waste reduction and dietary lifestyle support system that combines a system that identifies products that are predicted to remain unsold and sells them at discounted prices with an emotion engine that recognizes user emotions. This system can adjust the content of product recommendations and notifications based on the user's emotions, providing a more personalized service.

[1343] 1. Reducing food waste

[1344] Inventory Data Collection

[1345] Server: Connects to the inventory systems of supermarkets and restaurants to collect inventory data in real time, obtaining data such as product name, category, quantity, and price through API requests.

[1346] Unsold items forecast

[1347] Server: Uses AI models to analyze collected inventory data and identify items that are predicted to remain unsold, taking into account historical sales data and seasonal trends.

[1348] Discount information generation

[1349] Server: Based on the predicted list of unsold items, set a discount price and generate discount information on the online platform, for example, set a price 20% off the regular price.

[1350] 2. Optimizing individual consumption

[1351] Collecting user's food records and refrigerator information

[1352] Users use a smartphone app to upload daily food records and photos of their refrigerators. Food records include food types, portions, and calorie information.

[1353] Analysis of food records and refrigerator information

[1354] Server: AI analyzes the food records and refrigerator photos provided by the user. Image analysis technology is used to recognize the food in the refrigerator, and food records are converted into data through text analysis.

[1355] 3. Personalized meal suggestions

[1356] Proposals that take into account individual preferences and nutritional balance

[1357] Server: Provides personalized meal suggestions based on user preferences, nutritional balance, calorie information, and order history, resulting in meal plans and recipes tailored to the user.

[1358] Emotion engine integration

[1359] Server: Integrates an emotion engine that recognizes the user's emotions and collects emotional data from the user's voice, facial expressions, behavior, etc. This allows the current emotional state to be understood.

[1360] 4. Real-time notifications

[1361] Discount information notification

[1362] Device: When a product desired by the user is discounted, the system sends a notification via a smartphone app. The timing and content of the notification are adjusted based on data from the emotion engine.

[1363] Tailoring suggestions based on emotions

[1364] Server: Analyzes the user's emotional data and recommends meals and products based on their emotional state. For example, if a user is feeling depressed, it will suggest meals and products that will lift their spirits.

[1365] Specific examples

[1366] For example, suppose Supermarket A has a large inventory of a certain product, but sales trends suggest that it will remain unsold. This system first collects inventory data, analyzes it with an AI model, and predicts that the product is likely to remain unsold. It then sets the price of the product at a 20% discount from the regular price and generates discount information.

[1367] If the product is included in User B's wish list that he or she registered in advance, a notification of the discount information will be sent to User B's device. When sending the notification, the emotion engine detects User B's emotional state, and if, for example, User B is feeling stressed, the notification will include a message to help them relax.

[1368] Furthermore, User B enters his / her daily food record into the app and uploads photos of his / her refrigerator. The system analyzes this and provides User B with advice that takes into account the foods he / she needs and nutritional balance. The emotion engine also suggests recipes and meal plans based on User B's emotional state. For example, if User B is tired, it recommends meals suitable for restoring energy. In this way, the system of the present invention reduces food waste and supports healthy eating habits that take into account the user's emotional state.

[1369] The processing flow will be explained below.

[1370] Overall process flow for recruitment and purchasing

[1371] Step 1. Collect and analyze store data

[1372] Step 1.1:

[1373] Server: Connects to the supermarket or restaurant inventory system and sends API requests to collect inventory data, including product name, category, quantity, and price.

[1374] Step 1.2:

[1375] Server: Collected inventory data is input into the AI ​​model, which then predicts unsold items based on past sales data and seasonal trends. The AI ​​model uses machine learning to identify the items most likely to remain unsold.

[1376] Step 1.3:

[1377] Server: Sets discount prices based on the list of products predicted to remain unsold. For example, generates discount information for 20% off the regular price and registers the information on the online platform.

[1378] User Behavior and Analytics

[1379] Step 2. Collecting and analyzing user data

[1380] Step 2.1:

[1381] User: Using a smartphone app, users upload daily food records and photos of their refrigerator, including the types and amounts of food consumed and images of the food stored in the refrigerator.

[1382] Step 2.2:

[1383] Server: Analyzes photos of refrigerators uploaded by users using image analysis technology to determine current inventory status. At the same time, analyzes text from food records to digitize users' eating habits.

[1384] Step 2.3:

[1385] Server: Based on the user's refrigerator inventory and food records, the server provides advice to prevent forgetting to buy or overbuying. This advice includes a list of necessary foods and ways to save money.

[1386] Personalized offers and notifications

[1387] Step 3. Optimize meal suggestions and notifications

[1388] Step 3.1:

[1389] Server: Analyzes user preferences, nutritional balance, calorie information, and order history to suggest personalized meal plans and recipes based on the user's health and individual nutritional needs.

[1390] Step 3.2:

[1391] Server: Uses the emotion engine to collect emotional data from the user's voice, facial expressions, and behavior, thereby understanding the user's current emotional state.

[1392] Step 3.3:

[1393] Server: Analyzes the user's emotional data and recommends meals and products based on their emotional state. For example, if a user is feeling depressed, it will suggest foods and recipes that will improve their mood.

[1394] Step 4. Real-time notification of discount information

[1395] Step 4.1:

[1396] Device: Real-time notifications are sent to users' devices when discounted items become available. The content and timing of notifications are also adjusted based on the emotion engine.

[1397] Running a concrete example

[1398] Example: Supermarket A's product inventory and user B's behavior

[1399] Step 5.1:

[1400] Server: Collects data from Supermarket A's inventory system and analyzes it with an AI model. Specific products are listed as items that are predicted to remain unsold.

[1401] Step 5.2:

[1402] Server: Apply a 20% discount to the product and generate the discount information.

[1403] Step 5.3:

[1404] User B: If the product is on their wish list, a notification about the discount will be sent to their device. If User B is feeling stressed, a notification will be sent with a message to help them relax.

[1405] Step 5.4:

[1406] User: Enters daily food records into the app and uploads photos of the refrigerator, allowing the system to understand the user's eating habits and refrigerator inventory.

[1407] Step 5.5:

[1408] Server: Based on the emotion engine, it proposes recipes and meal plans that take into account User B's emotional state. For example, if User B is tired, it recommends meals that will help restore energy.

[1409] Through the above steps, the system of the present invention reduces food waste and supports healthy eating habits that take into account the user's emotional state.

[1410] Example 2

[1411] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1412] Food waste has become a serious problem in modern society, resulting in many products remaining unsold and discarded. Furthermore, suggestions tailored to individual user dietary needs are not provided, making it difficult to provide healthy and balanced meals. Furthermore, there is a lack of personalized services that take into account the user's emotional state. These circumstances are contributing to increased food waste and a decline in user satisfaction.

[1413] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1414] In this invention, the server includes: means for collecting store inventory information; means for analyzing the collected inventory information and using an artificial intelligence model to identify products predicted to remain unsold; means for generating discount price information based on the list of unsold products; means for publishing the generated discount price information on an online platform; means for using a terminal to register information about products desired by the user and receive notifications when the products are discounted; means for the user to receive the notifications and purchase the target products; means for using image analysis technology to analyze the user's food log and images of the contents of the refrigerator; means for providing advice based on the analysis results to prevent forgetting to buy or overbuying; means for recommending meals and products that are individually suited to the user's preferences, nutritional balance, calorie information, and order history; means for collecting and analyzing emotional data from the user's voice, facial expressions, and behavior; and means for adjusting the recommendations based on the collected emotional data. This enables food waste reduction and personalized dietary support tailored to the user's emotional state.

[1415] "Inventory information" is data about products held by stores and restaurants, such as product names, categories, quantities, and prices.

[1416] An "artificial intelligence model" is an algorithm that learns from past data and trends and makes predictions and classifications based on new data.

[1417] "Discount price information" is price information set lower than the regular price for products that are expected to remain unsold.

[1418] An "online platform" is a digital space for providing product information and discount information via the Internet.

[1419] A "terminal" is an electronic device, such as a smartphone or tablet, that allows a user to receive and operate information.

[1420] "Food records" are data that include detailed information such as the types, amounts, and calories of the foods a user consumes.

[1421] "Image analysis technology" is a technology that processes image data and extracts meaningful information.

[1422] "Means for providing advice" refers to functions or methods that provide useful information or suggestions to users based on the analysis results.

[1423] "Preferences" is data that refers to a user's preferred foods and flavors.

[1424] "Nutritional balance" is data that indicates the proportions of necessary nutrients such as protein, lipids, carbohydrates, vitamins, and minerals.

[1425] "Calorie information" is data that indicates the amount of energy ingested from food or meals.

[1426] "Order History" is a record of products and services a User has previously purchased.

[1427] "Emotional data" is information that indicates the psychological state of a user, collected from their voice, facial expressions, behavior, etc.

[1428] The "emotion engine" is a system that analyzes collected emotional data and evaluates the user's state based on the results.

[1429] The present invention relates to a food waste reduction and dietary lifestyle support system that combines a system that identifies unsold products and sells them at discounted prices with an emotion engine that recognizes user emotions. This system is implemented using a specific combination of hardware and software.

[1430] Specifically, the server performs the following processes: First, it collects inventory information from stores and restaurants. To do this, it uses API requests to obtain data such as product name, category, quantity, and price. Next, it inputs the collected inventory information into an AI model to identify products that are predicted to remain unsold. This AI model uses machine learning libraries such as TensorFlow and PyTorch. It then generates discount price information based on the list of unsold products and publishes it on an online platform.

[1431] Users use a smartphone app to upload their daily food records and images of their refrigerator. The food records include information on the type, amount, and calories of food. The server analyzes the uploaded data and uses image analysis technology (such as OpenCV or TensorFlow) to recognize the foods in the refrigerator, and converts the food records into data using text analysis.

[1432] To provide personalized meal suggestions, the server considers the user's preferences, nutritional balance, calorie information, and order history. This allows it to propose personalized meal plans and recipes. It also integrates an emotion engine that collects and analyzes emotional data from the user's voice, facial expressions, and behavior. Based on the analysis results, it adjusts the content of suggestions and the timing of notifications.

[1433] When a discount is offered on a product the user wants, the system will send a notification via the smartphone app. The content and timing of the notification will be adjusted based on data from the emotion engine.

[1434] For example, if supermarket A has a large stock of a particular product and sales trends indicate that it will remain unsold, the server collects inventory data, analyzes it using an AI model, and predicts that the product is likely to remain unsold. The server then sets the price of the product at a 20% discount from the normal price and generates discount information. If the product is included in User B's desired product list that he or she previously registered, a notification of the discount information is sent to User B's device. When the notification is sent, the emotion engine detects User B's emotional state; for example, if User B is feeling stressed, the notification will include a message to help them relax.

[1435] Furthermore, User B enters their daily food records into the app and uploads photos of their refrigerator. The server analyzes this and provides advice on the foods User B needs and nutritional balance. The emotion engine also suggests recipes and meal plans based on User B's emotional state. For example, if User B is tired, it will recommend meals suitable for restoring energy.

[1436] Example prompt sentence:

[1437] "Please tell me how to specifically design a system that uses an emotion engine to recognize the emotional state of a particular user and then makes product or meal recommendations based on that emotion."

[1438] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1439] Step 1:

[1440] Inventory data collection

[1441] Server: Connects to the store or restaurant inventory system and collects inventory data such as product name, category, quantity, and price through API requests. Specifically, it accesses the API endpoint and obtains real-time inventory information.

[1442] Input: API response data from a store or restaurant inventory system.

[1443] Output: An inventory dataset containing product name, category, quantity, and price.

[1444] Step 2:

[1445] Unsold items forecast

[1446] Server: Collected inventory data is input into the AI ​​model to identify products that are predicted to remain unsold. Taking into account past sales data and seasonal trends, predictions are made using machine learning models using TensorFlow and PyTorch.

[1447] Input: Collected inventory dataset.

[1448] Output: A list of items that are predicted to remain unsold.

[1449] Step 3:

[1450] Generate discount information

[1451] Server: Based on the list of unsold items, the server sets a price 20% off the regular price and generates discount information. The generated discount information is published on the online platform.

[1452] Input: A list of unsold items.

[1453] Output: Discount information including discount price and product information.

[1454] Step 4:

[1455] Food records and refrigerator information collection

[1456] User: Using a smartphone app, users upload daily food records and photos of their refrigerator. Food records include food types, portions, and calorie information.

[1457] Input: User-uploaded food logs and photos of the refrigerator.

[1458] Output: Food records and photo data stored in cloud storage.

[1459] Step 5:

[1460] Analysis of food records and refrigerator information

[1461] Server: Analyzes the uploaded data, recognizes the food in the refrigerator using image analysis technology, and converts the food records into data using text analysis. Tools such as OpenCV and TensorFlow are used.

[1462] Input: Saved food records and photo data.

[1463] Output: Text data of the food record and a list of recognized foods in the refrigerator.

[1464] Step 6:

[1465] Personalized meal suggestions

[1466] Server: Providing personalized meal recommendations based on user preferences, nutritional balance, calorie information, and order history. Using user data to provide optimal meal plans and recipes.

[1467] Input: Text data of food records, list of recognized foods in the refrigerator, user preferences, nutritional information, and order history.

[1468] Output: A list of meal plans and recipe suggestions suitable for the user.

[1469] Step 7:

[1470] Emotion engine integration

[1471] Server: Collects and analyzes emotional data from the user's voice, facial expressions, and behavior. Tailors suggestions based on the user's emotional state. This is achieved using emotion analysis technologies such as DeepFace.

[1472] Input: User's voice, facial expression, and behavior data.

[1473] Output: User's emotional state data and suggestion information based on it.

[1474] Step 8:

[1475] Discount information notification

[1476] Device: A smartphone app sends notifications when a desired product becomes discounted. The timing and content of notifications are adjusted based on data from the emotion engine.

[1477] Input: Discount information and user emotional state data.

[1478] Output: A message notifying you of the discount.

[1479] Step 9:

[1480] Tailoring suggestions based on emotions

[1481] Server: Analyzes emotional data and recommends meals and products based on the user's emotional state. If the user is feeling down, it will make suggestions to lift their spirits.

[1482] Input: User emotional state data.

[1483] Output: A list of food and product suggestions corresponding to your emotional state.

[1484] (Application example 2)

[1485] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1486] In today's world, where food waste is a serious problem, there is a need to efficiently identify products that are predicted to remain unsold and sell them at appropriate discount prices. Furthermore, a system is needed to make personalized suggestions to users and send timely and appropriate product notifications to increase their purchasing motivation. Furthermore, it is also a challenge to provide passengers in autonomous vehicles with food and beverages that match their emotional state, thereby providing a comfortable travel experience.

[1487] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1488] In this invention, the server includes means for analyzing inventory information to identify products that are predicted to remain unsold, means for generating information for selling unsold products at discounted prices, means for registering information about products desired by users and sending notifications when the products become available at discounted prices, means for receiving discount information about products registered by users and purchasing the target products, and means for adjusting the content and timing of notifications using an emotion engine that analyzes user emotions. This enables efficient identification and sale of unsold products, personalized notifications to users, and emotional provision of food and beverages to passengers during travel.

[1489] "Inventory information" refers to data relating to the quantity, type, location, etc. of products in a commercial facility or storage facility.

[1490] "Discount pricing" means that a product is offered at a price lower than its normal selling price.

[1491] The "emotion engine" is a system that collects and analyzes emotional data from the user's voice, facial expressions, behavior, etc. to understand the user's emotional state.

[1492] A "notification" is a message or alarm sent to a communication device such as a smartphone or tablet to inform the user of specific information.

[1493] "Food records" are data recorded by users that includes daily meal contents, meal amounts, nutritional information, etc.

[1494] "Video inside storage facilities" refers to images or video data taken with a camera of the inside of storage facilities such as refrigerators and pantries.

[1495] "Preferences" refers to information about a user's likes, dislikes, and preferences.

[1496] "Nutritional balance" refers to a state in which the nutrients in the food consumed by the user are appropriately distributed.

[1497] "Calorie information" is data that indicates the energy content of foods and drinks, and is usually expressed in "kilocalories (kcal)."

[1498] "Order history" refers to recorded data of products that a user has purchased or ordered in the past.

[1499] This invention combines a system that identifies unsold products and sells them at discounted prices with an emotion engine that recognizes user emotions to reduce food waste and support dietary habits. The system operates in anticipation of personalized food and beverage delivery to passengers in autonomous vehicles.

[1500] The server includes the following means:

[1501] 1. Means for analyzing inventory information: This system works in conjunction with the inventory management system of the storage equipment installed in the autonomous vehicle to collect inventory data in real time. The server obtains information such as product name, category, quantity, and price through the implemented API. Data collection and management are performed using Python.

[1502] 2. Discount price generation method: Based on the collected inventory data, an AI model is used to predict unsold items. This model includes a function that uses TensorFlow to perform predictive analysis taking into account past sales data and seasonal trends. The server sets discount prices based on the predicted list of unsold items and generates discount information on the online platform.

[1503] 3. Means of integrating emotion engine: Using a camera and microphone, the user's facial expressions, voice, and behavior are analyzed in real time to grasp the user's emotional state. The emotion engine analyzes emotions using facial recognition and voice analysis technologies using TensorFlow and OpenCV. Emotion data is reflected in food and drink recommendations based on the user's emotional fluctuations.

[1504] The device (smartphone or tablet) has the following features:

[1505] 1. Notification method: Based on data from the emotion engine, food and drink recommendations and discount information tailored to the passenger's state are sent. These notifications are sent in real time, and the content and timing of the notifications are adjusted according to the passenger's emotional state.

[1506] The user (passenger) performs the following operations:

[1507] 1. Uploading food records and footage of the storage facility: Food records and footage of the storage facility are uploaded to the server via a smartphone app. The server analyzes the data and provides advice to prevent forgetting to buy things or overbuying. For example, if the user is tired, it will suggest a drink that will help restore energy.

[1508] To illustrate, consider the following scenario:

[1509] Scenario: Passenger A is traveling in an autonomous vehicle and is detected as tired by the emotion engine.

[1510] Example prompt: "I sense that Passenger A is tired. Would you like to offer him a refreshment drink?"

[1511] In this way, the system of the present invention enables efficient identification and sale of unsold merchandise, personalized notifications to users, and emotion-based food and beverage offerings to passengers during travel.

[1512] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1513] Step 1:

[1514] Inventory Data Collection

[1515] The server collects real-time inventory information from the storage facilities installed in the autonomous vehicles, obtaining data such as product name, category, quantity, and price through API requests. This data is collected using a Python script and stored in a database.

[1516] Input: Inventory information from storage facilities (product name, category, quantity, price)

[1517] Output: Stock information is saved in the database

[1518] Step 2:

[1519] Unsold items forecast

[1520] The server uses AI models based on collected inventory data to identify products that are likely to remain unsold, and TensorFlow is used to perform predictive analysis that takes into account past sales data and seasonal trends.

[1521] Input: Past sales data, current inventory data

[1522] Output: Unsold items prediction result (list of items predicted to be unsold)

[1523] Step 3:

[1524] Discount information generation

[1525] The server sets discount prices based on the predicted list of unsold items and generates discount information on the online platform. Specifically, it uses a Python script to calculate the discount price for each item and stores the information in a database.

[1526] Input: Unsold items prediction result (list of items predicted to be unsold)

[1527] Output: Discount information (list of products with discounted prices)

[1528] Step 4:

[1529] Emotion data collection and analysis

[1530] The device (smartphone or tablet) uses a camera and microphone to collect the user's facial expressions, voice, and behavior in real time. Using TensorFlow and OpenCV, this data is analyzed to understand the user's emotional state.

[1531] Input: User's facial expression data, voice data, behavior data

[1532] Output: User's emotional state (emotion type and intensity)

[1533] Step 5:

[1534] Tailoring and sending notifications

[1535] The server adjusts the content and timing of notifications based on the emotion engine data and discount information, then sends the notifications to the device. A Python script is used to generate an appropriate message tailored to the user's current emotional state.

[1536] Input: User's emotional state, discount information

[1537] Output: Tailored notification content (message based on emotional state)

[1538] Step 6:

[1539] Uploading food records and footage of storage facilities

[1540] Users upload their daily food records and footage of the storage facility to a server via a smartphone app, which then analyzes the data and provides advice on how to avoid forgetting to buy things or overbuying.

[1541] Input: Meal record data, video data inside storage facilities

[1542] Output: Consumption advice (advice to prevent forgetting to buy or overspending)

[1543] Step 7:

[1544] Personalized suggestions

[1545] The server integrates the user's emotional state, food log, and inventory data to suggest suitable foods and drinks to the user, and uses a Python script to generate an appropriate item list based on health status and preferences.

[1546] Input: User's emotional state, food log, inventory data

[1547] Output: Personalized food and drink suggestions (list of suggested foods and drinks)

[1548] In this way, the system of the present invention effectively provides discount sales of unsold items and personalized food and beverage offerings based on the user's emotional state through real-time data collection and analysis.

[1549] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1550] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1551] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1552] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1553] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1554] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1555] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1556] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1557] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1558] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1559] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1560] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1561] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1562] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1563] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1564] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1565] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1566] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1567] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1568] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1569] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1570] The following is further disclosed regarding the above embodiment.

[1571] (Claim 1)

[1572] a means for analyzing store inventory information to identify items predicted to be unsold;

[1573] a means for generating information for selling unsold merchandise at a discount;

[1574] A means for users to register information about products they want and receive notifications when those products become available at discounted prices;

[1575] A means for a user to receive discount information for registered products and purchase the applicable products;

[1576] A system including:

[1577] (Claim 2)

[1578] 2. The system according to claim 1, further comprising means for analyzing the user's food record and photographs of the contents of the refrigerator and providing advice to prevent forgetting to buy or overbuying.

[1579] (Claim 3)

[1580] 10. The system of claim 1, further comprising means for individually recommending suitable meals and products based on the user's preferences, nutritional balance, calorie information and order history.

[1581] "Example 1"

[1582] (Claim 1)

[1583] A means for analyzing store inventory information and predicting unsold items;

[1584] a means for generating discount prices for unsold merchandise;

[1585] A way to register product information desired by users and receive notifications when the relevant product becomes available at a discounted price,

[1586] A means for receiving discount information and purchasing eligible products;

[1587] A system including:

[1588] (Claim 2)

[1589] The system of claim 1 further includes a means for analyzing the user's food records and information in the refrigerator to provide advice to prevent forgetting to buy or overbuying, and a means for recommending meals and products that are individually suited to the user based on the user's preferences, nutritional balance, calorie information, and order history.

[1590] "Application Example 1"

[1591] (Claim 1)

[1592] a means for analyzing inventory information to identify items predicted to be unsold;

[1593] a means for generating information for selling unsold merchandise at a discount;

[1594] means for sending notifications of discounted items based on the user's purchasing history and preferences;

[1595] A means for a user to receive discount information for registered products and purchase the applicable products;

[1596] A way to manage your refrigerator and advise you on what foods to buy.

[1597] A system including:

[1598] (Claim 2)

[1599] 2. The system according to claim 1, further comprising means for analyzing the user's food record and photographs of the contents of the refrigerator and providing advice to prevent forgetting to buy or overbuying.

[1600] (Claim 3)

[1601] 10. The system of claim 1, further comprising means for individually recommending suitable meals and products based on the user's preferences, nutritional balance, calorie information and order history.

[1602] "Example 2: Combining Emotion Engines"

[1603] (Claim 1)

[1604] A means of collecting store inventory information;

[1605] a means for using an artificial intelligence model to analyze the collected inventory information to identify items that are predicted to remain unsold;

[1606] a means for generating discount price information based on the list of unsold items;

[1607] a means for publishing the generated discount price information on an online platform;

[1608] A means using a terminal that allows a user to register information about a product they want and sends a notification when that product becomes available at a discounted price;

[1609] A means for users to receive notifications and purchase eligible products;

[1610] A system including:

[1611] (Claim 2)

[1612] means for using image analysis technology to analyze images of the user's food log and the contents of the refrigerator;

[1613] A means to provide advice based on the analysis results to prevent forgetting to buy or overbuying,

[1614] The system of claim 1 further comprising:

[1615] (Claim 3)

[1616] A means for individually recommending suitable meals and products taking into account the user's preferences, nutritional balance, calorie information, and order history;

[1617] A means of collecting and analyzing emotional data from users' voices, facial expressions, and behaviors;

[1618] a means for adjusting the recommendations based on the collected emotional data; and

[1619] The system of claim 1 further comprising:

[1620] "Application example 2 when combining emotion engines"

[1621] Rewritten claims

[1622] (Claim 1)

[1623] a means for analyzing inventory information to identify items predicted to be unsold;

[1624] a means for generating information for selling unsold merchandise at a discount;

[1625] A means for users to register information about products they want and receive notifications when those products become available at discounted prices;

[1626] A means for a user to receive discount information for registered products and purchase the applicable products;

[1627] A means to adjust the content and timing of notifications using an emotion engine that analyzes user emotions,

[1628] A system including:

[1629] (Claim 2)

[1630] 2. The system according to claim 1, further comprising means for analyzing the user's meal record and the video of the storage facility and providing advice to prevent forgetting to buy or overbuying.

[1631] (Claim 3)

[1632] 10. The system of claim 1, further comprising means for individually recommending suitable meals and products based on the user's preferences, nutritional balance, calorie information, and order history. [Explanation of symbols]

[1633] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for analyzing store inventory information to identify items predicted to be unsold; a means for generating information for selling unsold merchandise at a discount; A means for users to register information about products they want and receive notifications when those products become available at discounted prices; A means for a user to receive discount information for registered products and purchase the applicable products; A system including:

2. The system according to claim 1, further comprising means for analyzing the user's food record and photographs of the contents of the refrigerator and providing advice to prevent forgetting to buy or overbuying.

3. 10. The system of claim 1, further comprising means for individually recommending suitable meals and products based on the user's preferences, nutritional balance, calorie information and order history.

Images