system

Abstract

Provide a system. A means for acquiring a purchase history from a user's purchase history database; means for acquiring sale item information from a store's sale item database; A means for analyzing a user's purchase history and estimating which items are likely to remain in the refrigerator; a means for generating a list of recommended products for a user based on the acquired sale product information and estimated refrigerator inventory information; means for transmitting the generated recommended product list to a user's mobile terminal or a display device in the store; a means of collecting user-provided feedback data to fine-tune the recommendation algorithm; and A system including:

Description

[Technical Field]

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

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

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

[0004] Today's consumers have a growing need to complete their shopping as efficiently as possible in their busy daily lives. However, traditional stores lack systems that utilize data such as purchase history and store visit times to provide appropriate product recommendations, which often results in customers overlooking what they need or making unnecessary purchases. For this reason, there is a need for a system that effectively utilizes purchase history and sale information to provide appropriate product suggestions tailored to each individual user. [Means for solving the problem]

[0005] The present invention solves the above problems by the following means.

[0006] First, we provide a means to retrieve purchase history from a user's purchase history database. This allows you to accurately track past purchases and the dates and times they were made. Second, we provide a means to retrieve sale information from a store's sale item database. This allows you to accurately find out what items are on sale that day.

[0007] Furthermore, we provide a method for analyzing a user's purchase history and estimating which items are likely to remain in the refrigerator. This method allows us to estimate refrigerator inventory based on recent purchases and prioritize recommended items that are actually needed.

[0008] Then, a means is provided to generate a list of recommended products for the user based on the acquired sale product information and estimated refrigerator inventory information, which allows the system to pick out products that best suit the user's preferences and past purchase history.

[0009] Finally, we provide a means for transmitting the generated recommended product list to the user's mobile device or an in-store display device. This provides the user with the information they need to efficiently shop in a physical store in real time. Furthermore, by collecting feedback data provided by the user and providing a means for fine-tuning the recommendation algorithm, we can further improve the accuracy of recommendations in future.

[0010] The "user purchase history database" is a database that records and stores information about products that users have purchased in the past.

[0011] A "sales product database" is a database that records and stores information about products that a store sells at special prices during a specific period.

[0012] The "means for acquiring purchase history" is a mechanism for extracting past purchases and their purchase dates and times from a user's purchase history database.

[0013] The "means for acquiring sale item information" is a mechanism for retrieving information on items currently on sale from the sale item database.

[0014] A "means for analyzing purchase history" is a system for analyzing a user's past purchasing behavior data and understanding their trends and patterns.

[0015] The "means for estimating items that are likely to still be in the refrigerator" is a mechanism for identifying items that are likely to still be in the user's refrigerator based on purchase history.

[0016] The "means for generating a recommended product list" is a mechanism for creating a list of products appropriate for the user based on the acquired sale product information and estimated refrigerator inventory information.

[0017] "Mobile device" refers to an electronic device that a user can carry with them, such as a smartphone or tablet.

[0018] "Display devices within a store" refers to devices for displaying information, such as displays and monitors installed within a store.

[0019] "Feedback Data" refers to data provided by users regarding their purchasing behavior and usage of recommended products.

[0020] A "recommendation algorithm" is a calculation method for making optimal product recommendations to users based on collected data. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] The present invention relates to a system that combines a user's purchase history and sale item information to individually recommend optimal products. This system includes a purchase history database, a sale item database, data analysis means, a recommended product generation means, an information provision means, and a feedback collection means.

[0043] Data Acquisition

[0044] Obtaining a user's purchase history

[0045] The server accesses the purchase history database linked to the user ID and retrieves past purchase history data. This data includes the names and quantities of products purchased in the past, as well as the purchase dates and times. For example, the information might be "User ID: 12345, Purchased items: Tomato, lettuce, chicken, Purchase date and time: 2023-09-15 18:30."

[0046] Obtaining special sale information

[0047] The server retrieves information about products currently on sale from the store's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[0048] Analyzing the data

[0049] Analysis of purchase history and estimation of refrigerator inventory

[0050] The server estimates which items are likely to remain in the user's refrigerator based on the acquired purchase history. For example, if a user has purchased tomatoes, lettuce, and chicken three times in the last two weeks, the server estimates that these items are likely to remain in the refrigerator.

[0051] Generate recommended products

[0052] Generate recommended product lists based on sale items and refrigerator inventory

[0053] The server generates a list of recommended products that are optimal for the user based on the acquired sale item information and estimated refrigerator inventory information. Among the sale items, it prioritizes and recommends items that match the user's past purchase history and preferences. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, it determines that these items are suitable.

[0054] Providing information

[0055] Submit a recommended product list

[0056] The server sends the generated recommended product list to the user's mobile device or a display device in the store. The device (mobile device) receives this information and visually presents it to the user. Specifically, a "Today's Recommended Product List" is displayed on the smartphone app via push notification. For example, "Recommended Product List: 1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Croutons, etc."

[0057] Collecting feedback

[0058] Purchase History Updates and Feedback

[0059] When a user actually purchases a product, that information is automatically added to their purchase history. The server collects the feedback data provided by the user and fine-tunes the recommendation algorithm, which can then provide even better recommendations to the user in the future.

[0060] The above is an embodiment of the present invention. This system allows users to shop efficiently, avoid missing out on needed products, and make the most of sales information.

[0061] The processing flow will be explained below.

[0062] Step 1: Get the data

[0063] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. This data includes the date and time of each purchase, the purchased item, and the purchased quantity. For example, the user ID is "12345," the purchased items are "tomato, lettuce, chicken," and the purchase date and time is "2023-09-15 18:30."

[0064] Step 2: Get sale information

[0065] The server retrieves information about products currently on sale from the store's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, the information might be "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[0066] Step 3: Analyze your purchase history

[0067] The server analyzes the acquired purchase history data and estimates which items may remain in the refrigerator based on the user's recent purchase frequency. For example, if an item has been purchased three or more times in the past two weeks, it is assumed that the item is likely to remain in the refrigerator. If the user has recently purchased tomatoes, lettuce, and chicken multiple times, it is assumed that these items remain in the refrigerator.

[0068] Step 4: Generate a list of recommended products

[0069] The server generates a list of recommended products for the user based on the sale product information and the estimated refrigerator inventory. From the sale products, it selects products to recommend preferentially based on the user's preferences and past purchase history. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, these will be included in the recommended product list.

[0070] Step 5: Submit your recommended products list

[0071] The server sends the generated recommended product list to the user's mobile device or a display device in the store. The device (mobile device) receives this information and visually presents it to the user. For example, a smartphone app might display "Today's Recommended Product List" as "1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Croutons, etc."

[0072] Step 6: Gather feedback

[0073] When a user actually purchases a product, that information is automatically added to their purchase history. The server collects feedback data provided by the user (e.g., purchase history) and fine-tunes the recommendation algorithm, thereby improving the accuracy of future recommendations.

[0074] These are the specific processing steps that allow users to shop efficiently and take full advantage of sales information.

[0075] Example 1

[0076] 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."

[0077] Conventional recommendation systems recommend products based solely on a user's purchasing history, which makes it difficult to fully consider the user's recent purchasing behavior or sales information, making it difficult to recommend appropriate products in a timely manner. Furthermore, they have low accuracy in identifying products that are likely to interest users, which prevents them from fully motivating users to purchase. Furthermore, the mechanisms for efficiently collecting user feedback and incorporating it into the recommendation algorithm are insufficient, leaving a need for an improved user experience. Therefore, there is a need for a system that can combine a user's purchasing history, sales information, and feedback to make more accurate product recommendations.

[0078] 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.

[0079] In this invention, the server includes means for acquiring a purchase history from a purchase history data storage acquired based on a user identifier, means for acquiring sale item information from a retailer's sale item data storage, means for analyzing the purchase history and estimating items that are likely to still be stored in the refrigerator, means for generating an optimal recommended product list for the user based on the acquired sale item information and the estimated refrigerator inventory information, means for transmitting the generated recommended product list to the user's mobile communication terminal or an in-store display device, and means for collecting evaluation data provided by the user and adjusting the recommendation algorithm. This makes it possible to integrate the user's purchase history, sale information, and feedback to make more accurate and timely product recommendations.

[0080] A "user identifier" is unique information used to identify a specific user, such as an ID or account number.

[0081] "Purchase history data storage" is data storage that stores information about products purchased by users in the past, including product names, quantities, purchase dates, and so on.

[0082] "Sale product data storage" is a data storage that stores information about products on sale at a retail store, including the name, price, and sale period of the sale product.

[0083] "Refrigeration equipment" refers to equipment used to store food and other items at low temperatures. Generally, this includes refrigerators and freezers.

[0084] A "recommended product list" is a list of products recommended to a user. It is generated based on the user's purchase history and special sale information.

[0085] A "mobile communication terminal" is a communication device that can be carried and used by a user. This includes smartphones and tablet terminals.

[0086] "In-store display devices" are devices installed in stores to display information. These include digital signage and information display screens.

[0087] "Evaluation data" refers to data related to evaluations of products provided by users, including product ratings and feedback.

[0088] A "recommendation algorithm" is a set of calculation procedures and rules for recommending optimal products to users. The algorithm operates based on purchase history and sale information.

[0089] The present invention is a system for recommending optimal products to individual users by utilizing their purchasing history and sale product information. This system is implemented mainly by a server, a terminal, and a user.

[0090] The server accesses multiple databases to retrieve the user's purchase history data and sale item data. Based on the user identifier, the server issues a query to the purchase history data storage to retrieve information such as the name, quantity, and purchase date and time of items previously purchased by the user. The server then accesses the retailer's sale item data storage to retrieve information such as the name, sale price, and sale period of the sale item.

[0091] The server analyzes the acquired purchase history data and estimates which items are likely to still be stored in the refrigerator. This analysis takes into account factors such as the user's recent purchase frequency. For example, if a user has purchased tomatoes, lettuce, and chicken three times in the last two weeks, it estimates that these items are likely to remain in the refrigerator.

[0092] Next, the server generates a list of recommended products that are optimal for the user based on the acquired sale product information and estimated cooling equipment inventory information. This list prioritizes and recommends products that match the user's past purchase history and preferences from among the sale products. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, these products will be included in the recommended product list.

[0093] The generated recommended product list is sent from the server to the user's mobile communication device or to a display device in the store. The device receives this information and visually presents it to the user. Specifically, the "Today's Recommended Product List" is displayed via push notification on the user's smartphone app. For example, the recommended product list might be: 1. Tomato sauce (on sale) 2. Cheese (on sale) 3. Croutons.

[0094] When a user actually purchases a product, that information is automatically added to the purchase history. The server collects the user's rating data and adjusts the recommendation algorithm, thereby further improving the accuracy of the product recommendations provided to the user in the future.

[0095] Examples and prompts

[0096] Examples:

[0097] If a user has purchased tomatoes three times and lettuce twice in the last two weeks, the server will infer that these items are likely to remain in the refrigerator.

[0098] The server generates a list of recommended products because "tomato sauce" and "cheese" are on sale and these products match the user's purchase history.

[0099] Display the following recommended product list on your device: 1. Tomato sauce (on sale) 2. Cheese (on sale) 3. Croutons.

[0100] Example prompt:

[0101] 1. "How can I estimate the inventory in a cooling device based on a user's purchasing history?"

[0102] 2. "Explain how to generate a list of recommended products by combining special offers and user preferences."

[0103] 3. "Please give me a concrete example of how a list of recommended products can be displayed on a user's mobile device."

[0104] The above is an embodiment of the present invention. This system allows users to shop efficiently, avoid missing out on needed products, and make the most of sales information.

[0105] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0106] Step 1:

[0107] Obtaining a user's purchase history

[0108] The server accesses the purchase history data storage based on the user identifier. The server retrieves the user's past purchase history using a database query. For example, it executes the SQL query "SELECT product name, quantity, purchase date and time FROM purchase history WHERE user ID = '12345'".

[0109] Input: User Identifier

[0110] Output: Purchase history data (e.g., "User ID: 12345, Purchased items: Tomato, lettuce, chicken, Purchase date and time: 2023-09-15 18:30")

[0111] Step 2:

[0112] Obtaining special sale information

[0113] The server accesses the retailer's sales data storage and retrieves information about products currently on sale. The server retrieves the sales information using a database query. For example, the server executes the SQL query "SELECT product name, sale price, sale period FROM sale product WHERE current_date BETWEEN (registered trademark) start date AND end date."

[0114] Input: Current date

[0115] Output: Special sale item data (e.g. "Special sale items: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12")

[0116] Step 3:

[0117] Analysis of purchase history and estimation of cooling equipment inventory

[0118] The server uses the acquired purchase history data to estimate which items are likely to still be stored in the refrigerator. This analysis takes into account the user's recent purchase frequency and purchase date and time. For example, if a user has purchased tomatoes, lettuce, and chicken three times in the last two weeks, it estimates that these items are likely to remain in the refrigerator.

[0119] Input: Purchase history data (output from Step 1)

[0120] Output: Estimated cooling equipment inventory (e.g., "Tomatoes, Lettuce, Chicken")

[0121] Step 4:

[0122] Generate recommended products

[0123] The server generates a list of recommended products for the user based on the sale product information and estimated cooling equipment inventory. This list prioritizes products that match the user's past purchase history and preferences.

[0124] Input: Sale item data (output of Step 2) and estimated cooling equipment inventory (output of Step 3)

[0125] Output: Recommended product list (e.g. "Recommended product list: 1. Tomato sauce (on sale) 2. Cheese (on sale) 3. Croutons")

[0126] Step 5:

[0127] Submit a recommended product list

[0128] The server then sends the generated recommended product list to the user's mobile communication device or to a display device in the store. The server then formats the data in JSON format and sends it as a POST request to the API endpoint.

[0129] Input: Recommended product list (output of step 4)

[0130] Output: A recommendation notification delivered to the user's device (e.g., "Recommended product list: 1. Tomato sauce (on sale) 2. Cheese (on sale) 3. Croutons")

[0131] Step 6:

[0132] Gathering feedback and adjusting recommendation algorithms

[0133] When a user actually purchases a product, that information is automatically added to the purchase history. The server collects user evaluation data and adjusts the recommendation algorithm, thereby improving the accuracy of the recommended products provided next time.

[0134] Input: User rating data and new purchase history (user purchase information)

[0135] Output: A fine-tuned recommendation algorithm

[0136] The above is the specific processing flow of the system.

[0137] (Application example 1)

[0138] 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."

[0139] Conventional purchasing support systems are limited to recommending products based on a user's purchase history, and are unable to optimally utilize sale items. Furthermore, they lack a means for users to efficiently search for sale items within a store, reducing the convenience of shopping. Furthermore, there are limited ways to improve the accuracy of recommendations using feedback, making it difficult to improve user satisfaction. A comprehensive solution to these issues was needed.

[0140] 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.

[0141] In this invention, the server includes means for acquiring a purchase history from a user's purchase history database, means for acquiring sale item information from a store's sale item database, means for analyzing the user's purchase history and estimating items that are likely to still be in the refrigerator, means for generating a list of recommended items for the user based on the acquired sale item information and the estimated refrigerator inventory information, means for transmitting the generated recommended item list to the user's mobile device or an in-store display device, means for collecting feedback data provided by the user and fine-tuning the recommendation algorithm, and means for guiding the user to navigate within the store to the sale items. This enables efficient shopping by making the most of sale information and can improve the user's overall purchasing experience.

[0142] The "user purchase history database" is an information management system for storing information on products purchased by a user in the past.

[0143] The "sale item database" is an information management system for storing information about items currently on sale at a store.

[0144] The "means for acquiring purchase history" refers to a method or system for accessing a user's purchase history database and acquiring past purchase information.

[0145] The "means for acquiring sale item information" refers to a method or system for accessing a sale item database and acquiring information on items currently on sale.

[0146] A "means for analyzing purchase history" is a method or system for analyzing a user's purchase history data and identifying specific purchasing trends or patterns.

[0147] The "means for estimating items that are likely to still be in the refrigerator" refers to a method or system for estimating products that are likely to currently be in stock in the user's refrigerator based on the user's purchase history.

[0148] The "means for generating a recommended product list" is a method or system for creating a list that recommends the most suitable products to the user based on the acquired sale product information and estimated refrigerator inventory information.

[0149] A "mobile device" is a device that a user can carry and use, such as a smartphone or tablet.

[0150] An "in-store display device" is a device that is installed in a store and displays information to users.

[0151] A "means for collecting feedback data" is a method or system for collecting user-provided ratings and opinions to improve the performance of the system.

[0152] A "means for fine-tuning recommendation algorithms" is a method or system for improving the performance of recommendation algorithms based on collected feedback data.

[0153] A "navigation guidance means" is a method or system that provides location information and route guidance to help users find special sale items within a store.

[0154] This invention relates to a system that combines a user's purchase history with sale item information to individually recommend optimal products. The system includes a purchase history database, a sale item database, data analysis means, a recommended product generation means, an information provision means, and a feedback collection means.

[0155] The server first accesses the user's purchase history database and retrieves past purchase history data linked to the user ID. This data includes the names and quantities of products the user has previously purchased, as well as the purchase dates and times. Next, the server retrieves information about products currently on sale from the store's sales product database. This information includes the names of the products on sale, the sale prices, and the sale periods.

[0156] The server estimates which items are likely to remain in the user's refrigerator based on the acquired purchase history data. For example, if a specific item has been purchased several times in the past two weeks, it can estimate that the item is likely to remain in the refrigerator. The estimated refrigerator inventory information is combined with the acquired sale item information to generate a list of recommended products that are optimal for the user.

[0157] The generated recommended product list is sent from the server to the user's mobile device (smartphone or tablet) or to a display device in the store. This information is displayed on the mobile device via push notification, providing a visual presentation to the user. For example, a "Today's Recommended Products List" may be displayed on a smartphone app. Furthermore, the system also has a function to navigate the user to specific sale items within the store, allowing users to efficiently find sale items.

[0158] Additionally, when a user actually purchases a product, that information is automatically added to the purchase history. The server collects feedback data provided by the user and fine-tunes the recommendation algorithm to improve the accuracy of product recommendations for future users.

[0159] For example, when a user opens an application, they receive a push notification that reads: "Today's featured items: 1. Tomato Sauce (On Sale) 2. Cheese (On Sale). Please use the in-app navigation feature to find special offers on the store map."

[0160] For example, you can use the following prompts for your generative AI model:

[0161] "Generate the best recommended product list based on the user's purchase history and special sale information. As an example, consider the following purchase history and special sale information: User ID: 12345, Purchased items: Tomato, lettuce, chicken, Purchase date and time: 2023-09-15 18:30, Special sale items: Tomato sauce, cheese, Sale period: 2023-10-10 to 2023-10-12."

[0162] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0163] Step 1:

[0164] The server accesses the user's purchase history database and retrieves past purchase history data linked to the user ID. The input is the user ID, and the output is purchase history data (e.g., product name, quantity, purchase date and time). Specifically, it uses the Python requests library to retrieve the purchase history from the database and parses it in JSON format.

[0165] Step 2:

[0166] The server accesses the store's sales database and retrieves information about products currently on sale. The input is a database access request, and the output is sales information (e.g., product name, sale price, sale period). Specifically, the server uses the same Python requests library to retrieve data from the sales database and parse it in JSON format.

[0167] Step 3:

[0168] The server analyzes the purchase history data and estimates the items that are likely to still be in the user's refrigerator. The input is the acquired purchase history data, and the output is the estimated refrigerator inventory data. Specifically, it aggregates the data using the Pandas library and calculates the items still remaining in the refrigerator based on past purchase frequency.

[0169] Step 4:

[0170] The server generates a list of recommended products based on the acquired sale item information and estimated refrigerator inventory information. The input is sale item information and refrigerator inventory data, and the output is a list of recommended products. Specifically, it uses a generative AI model (e.g., TENSORFLOW (registered trademark) or PyTorch) to learn the user's purchasing trends and generate a list of recommended products.

[0171] Step 5:

[0172] The server sends the generated recommended product list to the user's mobile device or an in-store display device. The input is the recommended product list, and the output is a specific message to be sent to the mobile device or display device. Specifically, the server uses Firebase Cloud Messaging (FCM) to send the notification.

[0173] Step 6:

[0174] The device receives the recommended product list and visually presents it to the user. The input is the recommended product list sent from the server, and the output is the list displayed to the user. Specifically, a push notification is displayed on the smartphone app, and the list is presented as "Today's Recommended Product List."

[0175] Step 7:

[0176] The server collects user-provided feedback data and fine-tunes the recommendation algorithm. The input is the user feedback data, and the output is the adjusted model of the algorithm. Specifically, it analyzes the feedback data and adjusts the learning parameters of the generative AI model.

[0177] Step 8:

[0178] The terminal provides guidance so that the user can navigate within the store to the sale items. The input is the user's location information and sale item information, and the output is navigation information to the sale items. Specifically, it uses the Google (registered trademark) Maps API to display a map of the store and provides guidance on the shortest route.

[0179] 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.

[0180] The present invention relates to a system that recommends optimal products to individuals by combining a user's purchase history, sale item information, and an emotion engine that recognizes the user's emotions. This system includes a purchase history database, a sale item database, data analysis means, a recommended product generation means, information provision means, feedback collection means, and emotion recognition means.

[0181] Data Acquisition

[0182] Obtaining a user's purchase history

[0183] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. This data includes the date and time of each purchase, the purchased item, and the purchased quantity. For example, the user ID is "12345," the purchased items are "tomato, lettuce, chicken," and the purchase date and time is "2023-09-15 18:30."

[0184] Obtaining special sale information

[0185] The server retrieves information about products currently on sale from the store's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, the information might be "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[0186] Analyzing the data

[0187] Analysis of purchase history and estimation of refrigerator inventory

[0188] The server analyzes the acquired purchase history data and estimates which items may remain in the refrigerator based on the user's recent purchase frequency. For example, if an item has been purchased three or more times in the past two weeks, it is assumed that the item is likely to remain in the refrigerator. If the user has recently purchased tomatoes, lettuce, and chicken multiple times, it is assumed that these items remain in the refrigerator.

[0189] Generate recommended products

[0190] Generate recommended product lists based on sale items and refrigerator inventory

[0191] The server generates a list of recommended products for the user based on the sale product information and the estimated refrigerator inventory. From the sale products, it selects products to recommend preferentially based on the user's preferences and past purchase history. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, these will be included in the recommended product list.

[0192] emotion recognition

[0193] User Emotion Recognition

[0194] The device (mobile device) uses a camera and microphone to recognize the user's emotions. This information is sent to the server in real time. For example, if the user is tired or stressed, the device can sense their emotional state.

[0195] Adjusting product listings based on sentiment data

[0196] The server adjusts the recommended product list based on the user's emotional data. For example, if the user is feeling stressed, the server can prioritize products with a relaxing effect (such as herbal tea) in the list.

[0197] Providing information

[0198] Submit a recommended product list

[0199] The server sends the generated recommended product list to the user's mobile device or a display device in the store. The device (mobile device) receives this information and visually presents it to the user. For example, a smartphone app might display "Today's Recommended Product List" as "1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Croutons, etc."

[0200] Collecting feedback

[0201] Purchase History Updates and Feedback

[0202] When a user actually purchases a product, that information is automatically added to their purchase history. The server collects feedback data provided by the user (e.g., purchase history) and fine-tunes the recommendation algorithm, thereby improving the accuracy of future recommendations.

[0203] The above is an embodiment of the present invention. This system allows users to shop efficiently, maximize sales information, and receive optimal product recommendations based on their current emotional state.

[0204] The processing flow will be explained below.

[0205] Step 1: Get your purchase history

[0206] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. This data includes the date and time of each purchase, the purchased items, and the purchased quantities. Specifically, the information might be something like "User ID: 12345, Purchased items: Tomato, lettuce, chicken, Purchase date and time: 2023-09-15 18:30."

[0207] Step 2: Get sale information

[0208] The server retrieves information about products currently on sale from the store's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[0209] Step 3: Analyze your purchase history

[0210] The server analyzes the acquired purchase history data and estimates which items may remain in the refrigerator based on the user's recent purchase frequency. Specifically, it estimates that items that have been purchased three or more times in the last two weeks remain in the refrigerator. For example, if the user has recently purchased tomatoes, lettuce, and chicken multiple times, it estimates that these items remain in the refrigerator.

[0211] Step 4: Obtaining emotion data

[0212] The device (mobile device) uses a camera and microphone to recognize the user's emotions and transmits the data to a server. For example, if the user is tired or stressed, the device can detect that emotional state.

[0213] Step 5: Generate a list of recommended products

[0214] The server generates a list of recommended products based on the sale product information, estimated refrigerator inventory, and emotional data. From the sale products, it selects products to recommend based on the user's preferences and current emotional state. For example, if the user is tired, it prioritizes products with a relaxing effect (such as herbal tea) in the list.

[0215] Step 6: Submit your recommended products list

[0216] The server sends the generated recommended product list to the user's mobile device or to a display device in the store. The device (mobile device) receives this information and visually presents it to the user. Specifically, the smartphone app displays "Today's Recommended Product List" as follows: 1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Herbal Tea (Based on User Emotion Data)."

[0217] Step 7: Gather feedback

[0218] When a user actually purchases a product, that information is automatically added to their purchase history. The server collects feedback data provided by the user (e.g., purchase history) and fine-tunes the recommendation algorithm, thereby improving the accuracy of future product recommendations.

[0219] The above is the specific processing flow of the product recommendation system for users that combines an emotion engine. This enables users to receive optimal product recommendations based on their current emotional state, enabling them to shop efficiently.

[0220] Example 2

[0221] 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."

[0222] The present invention aims to provide an optimal product recommendation system that takes into account not only a user's purchase history and sale product information, but also the user's emotional state. Conventional recommendation systems generally rely on a user's preferences and purchase history, but there is a demand for more accurate product recommendations that meet the user's needs by taking the user's emotional state into account. Therefore, it is necessary to recognize the user's emotional state and adjust the product list based on that.

[0223] 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.

[0224] In this invention, the server includes means for acquiring a purchase history from a user's purchase history database, means for acquiring sale item information from a store's sale item database, means for analyzing the user's purchase history and estimating items that are likely to still be in the refrigerator, means for generating a list of recommended items for the user based on the acquired sale item information and the estimated refrigerator inventory information, means for transmitting the generated recommended item list to the user's mobile device or an in-store display device, means for recognizing the user's emotions and acquiring the data, means for adjusting the recommended item list based on the recognized emotion data, and means for collecting feedback data provided by the user and fine-tuning the recommendation algorithm, thereby enabling more accurate product recommendations that take the user's emotional state into consideration.

[0225] "Purchase history" is data containing information about products purchased by a user in the past, specifically including the purchase date and time, product name, and purchase quantity.

[0226] "Special sale product information" is data containing information about products that a store is offering at special prices, and specifically includes the names of the products on sale, the sale prices, the sale periods, and so on.

[0227] The "purchase history database" is a database for storing data on a user's past purchase history.

[0228] The "sales product database" is a database for storing information about sales products at a store.

[0229] "Refrigerator inventory" is a concept for estimating products that are likely to still be in a user's refrigerator, and is estimated based on the user's purchase history data.

[0230] The "recommended product list" is a list of products recommended to the user, and is generated based on sale product information, refrigerator inventory, and the user's emotional state.

[0231] A "user's mobile terminal" is an electronic device that a user carries and uses, such as a smartphone or tablet.

[0232] The "display device in the store" refers to a display device such as a display or monitor installed in the store.

[0233] "Emotion recognition" is a technology that uses devices such as cameras and microphones to detect a user's emotional state.

[0234] "Feedback data" is data provided by a user after purchasing a product, and includes purchase history, impressions, and the like.

[0235] A "recommendation algorithm" is an algorithm that recommends products based on a user's purchase history, sale information, emotional data, etc.

[0236] "Emotional state" indicates the type and intensity of the emotion the user is feeling, and includes fatigue, stress, happiness, and the like.

[0237] The present invention is a system that recommends optimal products to individuals by combining a user's purchase history, sale product information, and an engine that recognizes the user's emotions. This system includes a user purchase history database, a sale product database, data analysis means, a recommended product generation means, information provision means, feedback collection means, and emotion recognition means.

[0238] Data Acquisition

[0239] Obtaining a user's purchase history

[0240] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. This data includes the date and time of each purchase, the purchased item, and the purchased quantity. For example, the user ID is "12345," the purchased items are "tomato, lettuce, chicken," and the purchase date and time is "2023-09-15 18:30."

[0241] Obtaining special sale information

[0242] The server retrieves information about the products currently on sale from the store's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, the information might be "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[0243] Analyzing the data

[0244] Analysis of purchase history and estimation of refrigerator inventory

[0245] The server analyzes the acquired purchase history data and estimates which items may remain in the refrigerator based on the user's recent purchase frequency. For example, if a product has been purchased three or more times in the past two weeks, it is estimated that the item is likely to remain in the refrigerator. If the user has recently purchased tomatoes, lettuce, and chicken multiple times, it is estimated that these items remain in the refrigerator.

[0246] Generate recommended products

[0247] Generate recommended product lists based on sale items and refrigerator inventory

[0248] The server generates a list of recommended products for the user based on the sale product information and the estimated refrigerator inventory. From the sale products, it selects products to recommend preferentially based on the user's preferences and past purchase history. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, these will be included in the recommended product list.

[0249] emotion recognition

[0250] User Emotion Recognition

[0251] The device (mobile device) uses a camera and microphone to recognize the user's emotions. This information is sent to the server in real time. For example, if the user is tired or stressed, the device can sense their emotional state.

[0252] Adjusting product listings based on sentiment data

[0253] The server adjusts the recommended product list based on the user's emotional data. For example, if the user is feeling stressed, the server can prioritize products with a relaxing effect (such as herbal tea) in the list.

[0254] Providing information

[0255] Submit a recommended product list

[0256] The server sends the generated recommended product list to the user's mobile device or a display device in the store. The device (mobile device) receives this information and visually presents it to the user. For example, a smartphone app might display "Today's Recommended Product List" as "1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Croutons, etc."

[0257] Collecting feedback

[0258] Purchase History Updates and Feedback

[0259] When a user actually purchases a product, that information is automatically added to their purchase history. The server collects feedback data provided by the user (e.g., purchase history) and fine-tunes the recommendation algorithm, thereby improving the accuracy of future recommendations.

[0260] Examples of prompt statements

[0261] Below is an example of a prompt sentence for a generative AI model to recommend products based on a user's purchase history, sale information, and emotional data:

[0262] User ID: 12345

[0263] Recent purchase history: Tomato, lettuce, chicken (2023-09-15 18:30)

[0264] Special Offer:

[0265] 1. Tomato Sauce (Special Sale Period: 2023-10-10 to 2023-10-12)

[0266] 2. Cheese (Special Sale Period: 2023-10-10 to 2023-10-12)

[0267] User emotion data: Stress state (via emotion engine)

[0268] This enables more accurate product recommendations that take into account the user's emotional state.

[0269] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0270] Step 1:

[0271] The server receives the user ID as input and retrieves the user's purchase history data from the purchase history database. This data includes the date and time of each purchase, the purchased items, and the purchase quantity. Specifically, using the user ID "12345," it retrieves "Purchase date and time: 2023-09-15 18:30, purchased items: tomato, lettuce, chicken, purchase quantity: 1 each." The retrieved data is sent to the next analysis step.

[0272] Step 2:

[0273] The server uses the acquired purchase history data as input and applies an analysis algorithm to calculate the frequency of items recently purchased by the user. For example, items purchased three or more times in the past two weeks are estimated as refrigerator inventory. The output is estimated refrigerator inventory information; if "tomatoes, lettuce, and chicken" are included, they are estimated to be left in the refrigerator.

[0274] Step 3:

[0275] The server sends a query to the store's special sale database to retrieve information about the current sale items. The input is a query statement to the database, and the output is "Special sale item name: Tomato sauce, Special sale price: 200 yen, Special sale period: 2023-10-10 to 2023-10-12."

[0276] Step 4:

[0277] The server combines the sale product information and estimated refrigerator inventory information as input, and generates a list of recommended products based on the user's preferences and purchase history. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, the server prioritizes tomato sauce and cheese. The output is the generated list of recommended products.

[0278] Step 5:

[0279] The device (mobile device) captures the user's facial expressions and voice data using a camera and microphone, and inputs this data into an emotion recognition engine. The engine analyzes this data and recognizes the user's emotional state (e.g., stress level). The output is real-time emotion data, which is sent to a server.

[0280] Step 6:

[0281] The server adjusts the recommended product list based on the emotional data sent by the user. For example, if the user is under stress, it adds relaxing herbal tea to the list. This adjustment generates a final recommended product list that reflects the emotional data.

[0282] Step 7:

[0283] The server sends the generated recommended product list to the user's mobile device or a display device in the store. The device (mobile device) receives this information and visually presents it to the user. For example, a smartphone app might display "Today's Recommended Product List" as "1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Herbal Tea (Reflecting Emotional Data)."

[0284] Step 8:

[0285] When a user makes a purchase, that information is automatically added to the purchase history database, and the server collects this new purchase history data. The server also uses the feedback data provided by the user to fine-tune the recommendation algorithm, which improves the accuracy of future recommendations.

[0286] (Application example 2)

[0287] 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."

[0288] Today's consumers are extremely busy and need assistance in efficiently purchasing daily necessities and food. Furthermore, a system that allows users to purchase items without missing out on special offers would respond to consumers' desire to save money. However, conventional recommendation systems have difficulty recommending optimal products because they do not fully consider users' emotions or individual purchasing habits. Furthermore, providing information in real time is crucial to effectively take advantage of special offers in the market.

[0289] 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.

[0290] In this invention, the server includes means for acquiring a purchase history from a purchase history database of the user, means for acquiring sale item information from a sale item database of the commercial facility, means for analyzing the user's purchase history and estimating items that are likely to still be in the refrigerator, means for generating a list of recommended items for the user based on the acquired sale item information and the estimated refrigerator inventory information, means for transmitting the generated recommended item list to the user's mobile terminal or a display device in the commercial facility, means for collecting feedback data provided by the user and fine-tuning a recommendation algorithm, emotion recognition means for collecting user emotion data, and means for adjusting the recommended item list based on the emotion data. This makes it possible to quickly and accurately recommend optimal products based on the user's emotional state and individual purchasing characteristics while effectively utilizing sale information.

[0291] The "user purchase history database" is an accessible database that records the history of products that a user has purchased in the past.

[0292] A "sales product database" is a database that records and provides access to information about products on sale at commercial facilities.

[0293] The "emotion recognition means" is a means for recognizing the user's emotions using sensors such as a camera or microphone, and acquiring that information.

[0294] The "means for acquiring purchase history" is a means for accessing a purchase history database of a user and acquiring information on products that the user has purchased in the past.

[0295] The "means for acquiring sale item information" refers to a means for accessing a sale item database and acquiring information about items on sale at commercial facilities.

[0296] The "means for analyzing purchase history" is a means for analyzing the user's purchasing patterns based on the acquired purchase history and estimating items that are likely to remain in the refrigerator.

[0297] The "means for generating a recommended product list" is a means for creating an optimal product list for a user based on sale product information and estimated refrigerator inventory information.

[0298] The "means for transmitting a recommended product list" is a means for transmitting the generated recommended product list to a user's mobile terminal or a display device in a commercial facility.

[0299] "Means for collecting feedback data" refers to means for collecting post-purchase opinions and purchase information provided by users and using them to improve recommendation algorithms.

[0300] The "means for adjusting the recommended product list based on emotion data" refers to a means for adjusting the contents of the recommended product list based on the user's emotion data acquired by the emotion recognition means, and recommending optimal products to the user.

[0301] This invention relates to a system that recommends optimal products to individuals by combining a user's purchase history, sale item information, and an emotion engine that recognizes the user's emotions. The main elements are a purchase history database, a sale item database, data analysis means, a recommended product generation means, information provision means, feedback collection means, and emotion recognition means.

[0302] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. This data includes the date and time of each purchase, the purchased item, and the purchased quantity. For example, the user ID is "12345," the purchased items are "tomato, lettuce, chicken," and the purchase date and time is "2023-09-15 18:30."

[0303] Next, the server retrieves information about products currently on sale from the commercial facility's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[0304] Based on this, the server analyzes the purchase history data and estimates which items may remain in the refrigerator based on the user's recent purchase frequency. For example, if an item has been purchased three or more times in the past two weeks, it is assumed that the item is likely to remain in the refrigerator. If the user has recently purchased tomatoes, lettuce, and chicken multiple times, it is assumed that these items remain in the refrigerator.

[0305] Based on the estimated refrigerator inventory, the server compares it with sale item information to generate a list of recommended items. From the sale items, it selects items to recommend preferentially based on the user's preferences and past purchase history. For example, tomato sauce and cheese are on sale, and the user frequently purchases tomatoes, so these are included in the recommended items list.

[0306] Furthermore, the mobile device uses a camera and microphone to recognize the user's emotions in real time, and this information is sent to a server to measure the user's emotional state, for example, if they are tired or stressed.

[0307] The server adjusts the recommended product list based on the user's emotional data. For example, if the user is feeling stressed, the server can prioritize products with a relaxing effect (such as herbal tea) in the list.

[0308] The generated recommended product list is sent from the server to the user's mobile device or to a display device within the commercial facility. The mobile device receives this information and visually presents it to the user. For example, a smartphone app might display "Today's Recommended Product List" as "1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Croutons, etc."

[0309] Finally, when a user actually purchases a product, that information is automatically added to their purchase history. The server collects the feedback data provided by the user (e.g., purchase history) and fine-tunes the recommendation algorithm, thereby improving the accuracy of future recommendations.

[0310] For example and prompt purposes, we will use the following information as input:

[0311] Specific prompt examples:

[0312] User ID: 12345

[0313] Purchase History API URL: http: / / example.com / api / purchase_history

[0314] Special Offers API URL: http: / / example.com / api / special_offers

[0315] Recommendation API URL: http: / / example.com / api / recommendation

[0316] Emotion: stressed

[0317] Generate a list of recommended products

[0318] As a result, users can shop efficiently, make the most of sale information, and receive optimal product recommendations based on their emotions. This system simultaneously satisfies consumers' desire for savings and convenience, and is expected to improve customer satisfaction in commercial facilities.

[0319] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0320] Step 1:

[0321] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. The input is the user ID and the output is the purchase history data. This data includes the date and time of each purchase, the purchased item, and the purchased quantity. Specifically, it sends a request to the API endpoint and retrieves the purchase history data as a response.

[0322] Step 2:

[0323] The server retrieves information about products currently on sale from the commercial facility's sale product database. The input is the API URL of the sale product database, and the output is the sale product information. This information includes the name of the sale product, the sale price, and the sale period. Specifically, it sends a request to the API endpoint and retrieves the sale product data as a response.

[0324] Step 3:

[0325] The server analyzes the acquired purchase history data and estimates which items may remain in the refrigerator based on the user's most recent purchase frequency. The input is the purchase history data, and the output is a list of items estimated to remain in the refrigerator. Specifically, it calculates the purchase frequency of each product and lists items that have been frequently purchased within a certain period of time.

[0326] Step 4:

[0327] The server collects the user's emotional data through an emotion recognition means. The input is the user's real-time video and audio data, and the output is the judged emotional data. Specifically, it analyzes the data input from the camera and microphone and identifies the emotion using a generative AI model.

[0328] Step 5:

[0329] The server generates a recommended product list based on the acquired sale product information, estimated refrigerator inventory information, and emotional data. The inputs are sale product information, refrigerator inventory information, and emotional data, and the output is a recommended product list. Specifically, the server selects products from the sale products that match the user's preferences and emotional state, and generates the list.

[0330] Step 6:

[0331] The server then sends the generated recommended product list to the user's mobile device or a display device within the commercial facility. The input is the recommended product list, and the output is the information displayed on the user's device or display device. Specifically, the list is sent to the device so that the user can visually confirm it.

[0332] Step 7:

[0333] When a user actually purchases a product, the purchase information is added to the purchase history. The input is the information about the purchased product, and the output is an updated purchase history database. Specifically, the purchase information is added to the database, and the server keeps the data as up-to-date.

[0334] Step 8:

[0335] The server collects post-purchase feedback data and fine-tunes the recommendation algorithm. The input is the feedback data provided by the user, and the output is an improved recommendation algorithm. Specifically, the server analyzes the collected feedback and adjusts the algorithm parameters.

[0336] 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.

[0337] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0338] 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.

[0339] [Second embodiment]

[0340] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0341] 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.

[0342] 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).

[0343] 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.

[0344] 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.

[0345] 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).

[0346] 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.

[0347] 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.

[0348] 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.

[0349] 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.

[0350] 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.

[0351] 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."

[0352] The present invention relates to a system that combines a user's purchase history and sale item information to individually recommend optimal products. This system includes a purchase history database, a sale item database, data analysis means, a recommended product generation means, an information provision means, and a feedback collection means.

[0353] Data Acquisition

[0354] Obtaining a user's purchase history

[0355] The server accesses the purchase history database linked to the user ID and retrieves past purchase history data. This data includes the names and quantities of products purchased in the past, as well as the purchase dates and times. For example, the information might be "User ID: 12345, Purchased items: Tomato, lettuce, chicken, Purchase date and time: 2023-09-15 18:30."

[0356] Obtaining special sale information

[0357] The server retrieves information about products currently on sale from the store's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[0358] Analyzing the data

[0359] Analysis of purchase history and estimation of refrigerator inventory

[0360] The server estimates which items are likely to remain in the user's refrigerator based on the acquired purchase history. For example, if a user has purchased tomatoes, lettuce, and chicken three times in the last two weeks, the server estimates that these items are likely to remain in the refrigerator.

[0361] Generate recommended products

[0362] Generate recommended product lists based on sale items and refrigerator inventory

[0363] The server generates a list of recommended products that are optimal for the user based on the acquired sale item information and estimated refrigerator inventory information. Among the sale items, it prioritizes and recommends items that match the user's past purchase history and preferences. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, it determines that these items are suitable.

[0364] Providing information

[0365] Submit a recommended product list

[0366] The server sends the generated recommended product list to the user's mobile device or a display device in the store. The device (mobile device) receives this information and visually presents it to the user. Specifically, a "Today's Recommended Product List" is displayed on the smartphone app via push notification. For example, "Recommended Product List: 1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Croutons, etc."

[0367] Collecting feedback

[0368] Purchase History Updates and Feedback

[0369] When a user actually purchases a product, that information is automatically added to their purchase history. The server collects the feedback data provided by the user and fine-tunes the recommendation algorithm, which can then provide even better recommendations to the user in the future.

[0370] The above is an embodiment of the present invention. This system allows users to shop efficiently, avoid missing out on needed products, and make the most of sales information.

[0371] The processing flow will be explained below.

[0372] Step 1: Get the data

[0373] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. This data includes the date and time of each purchase, the purchased item, and the purchased quantity. For example, the user ID is "12345," the purchased items are "tomato, lettuce, chicken," and the purchase date and time is "2023-09-15 18:30."

[0374] Step 2: Get sale information

[0375] The server retrieves information about products currently on sale from the store's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, the information might be "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[0376] Step 3: Analyze your purchase history

[0377] The server analyzes the acquired purchase history data and estimates which items may remain in the refrigerator based on the user's recent purchase frequency. For example, if an item has been purchased three or more times in the past two weeks, it is assumed that the item is likely to remain in the refrigerator. If the user has recently purchased tomatoes, lettuce, and chicken multiple times, it is assumed that these items remain in the refrigerator.

[0378] Step 4: Generate a list of recommended products

[0379] The server generates a list of recommended products for the user based on the sale product information and the estimated refrigerator inventory. From the sale products, it selects products to recommend preferentially based on the user's preferences and past purchase history. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, these will be included in the recommended product list.

[0380] Step 5: Submit your recommended products list

[0381] The server sends the generated recommended product list to the user's mobile device or a display device in the store. The device (mobile device) receives this information and visually presents it to the user. For example, a smartphone app might display "Today's Recommended Product List" as "1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Croutons, etc."

[0382] Step 6: Gather feedback

[0383] When a user actually purchases a product, that information is automatically added to their purchase history. The server collects feedback data provided by the user (e.g., purchase history) and fine-tunes the recommendation algorithm, thereby improving the accuracy of future recommendations.

[0384] These are the specific processing steps that allow users to shop efficiently and take full advantage of sales information.

[0385] Example 1

[0386] 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."

[0387] Conventional recommendation systems recommend products based solely on a user's purchasing history, which makes it difficult to fully consider the user's recent purchasing behavior or sales information, making it difficult to recommend appropriate products in a timely manner. Furthermore, they have low accuracy in identifying products that are likely to interest users, which prevents them from fully motivating users to purchase. Furthermore, the mechanisms for efficiently collecting user feedback and incorporating it into the recommendation algorithm are insufficient, leaving a need for an improved user experience. Therefore, there is a need for a system that can combine a user's purchasing history, sales information, and feedback to make more accurate product recommendations.

[0388] 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.

[0389] In this invention, the server includes means for acquiring a purchase history from a purchase history data storage acquired based on a user identifier, means for acquiring sale item information from a retailer's sale item data storage, means for analyzing the purchase history and estimating items that are likely to still be stored in the refrigerator, means for generating an optimal recommended product list for the user based on the acquired sale item information and the estimated refrigerator inventory information, means for transmitting the generated recommended product list to the user's mobile communication terminal or an in-store display device, and means for collecting evaluation data provided by the user and adjusting the recommendation algorithm. This makes it possible to integrate the user's purchase history, sale information, and feedback to make more accurate and timely product recommendations.

[0390] A "user identifier" is unique information used to identify a specific user, such as an ID or account number.

[0391] "Purchase history data storage" is data storage that stores information about products purchased by users in the past, including product names, quantities, purchase dates, and so on.

[0392] "Sale product data storage" is a data storage that stores information about products on sale at a retail store, including the name, price, and sale period of the sale product.

[0393] "Refrigeration equipment" refers to equipment used to store food and other items at low temperatures. Generally, this includes refrigerators and freezers.

[0394] A "recommended product list" is a list of products recommended to a user. It is generated based on the user's purchase history and special sale information.

[0395] A "mobile communication terminal" is a communication device that can be carried and used by a user. This includes smartphones and tablet terminals.

[0396] "In-store display devices" are devices installed in stores to display information. These include digital signage and information display screens.

[0397] "Evaluation data" refers to data related to evaluations of products provided by users, including product ratings and feedback.

[0398] A "recommendation algorithm" is a set of calculation procedures and rules for recommending optimal products to users. The algorithm operates based on purchase history and sale information.

[0399] The present invention is a system for recommending optimal products to individual users by utilizing their purchasing history and sale product information. This system is implemented mainly by a server, a terminal, and a user.

[0400] The server accesses multiple databases to retrieve the user's purchase history data and sale item data. Based on the user identifier, the server issues a query to the purchase history data storage to retrieve information such as the name, quantity, and purchase date and time of items previously purchased by the user. The server then accesses the retailer's sale item data storage to retrieve information such as the name, sale price, and sale period of the sale item.

[0401] The server analyzes the acquired purchase history data and estimates which items are likely to still be stored in the refrigerator. This analysis takes into account factors such as the user's recent purchase frequency. For example, if a user has purchased tomatoes, lettuce, and chicken three times in the last two weeks, it estimates that these items are likely to remain in the refrigerator.

[0402] Next, the server generates a list of recommended products that are optimal for the user based on the acquired sale product information and estimated cooling equipment inventory information. This list prioritizes and recommends products that match the user's past purchase history and preferences from among the sale products. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, these products will be included in the recommended product list.

[0403] The generated recommended product list is sent from the server to the user's mobile communication device or to a display device in the store. The device receives this information and visually presents it to the user. Specifically, the "Today's Recommended Product List" is displayed via push notification on the user's smartphone app. For example, the recommended product list might be: 1. Tomato sauce (on sale) 2. Cheese (on sale) 3. Croutons.

[0404] When a user actually purchases a product, that information is automatically added to the purchase history. The server collects the user's rating data and adjusts the recommendation algorithm, thereby further improving the accuracy of the product recommendations provided to the user in the future.

[0405] Examples and prompts

[0406] Examples:

[0407] If a user has purchased tomatoes three times and lettuce twice in the last two weeks, the server will infer that these items are likely to remain in the refrigerator.

[0408] The server generates a list of recommended products because "tomato sauce" and "cheese" are on sale and these products match the user's purchase history.

[0409] Display the following recommended product list on your device: 1. Tomato sauce (on sale) 2. Cheese (on sale) 3. Croutons.

[0410] Example prompt:

[0411] 1. "How can I estimate the inventory in a cooling device based on a user's purchasing history?"

[0412] 2. "Explain how to generate a list of recommended products by combining special offers and user preferences."

[0413] 3. "Please give me a concrete example of how a list of recommended products can be displayed on a user's mobile device."

[0414] The above is an embodiment of the present invention. This system allows users to shop efficiently, avoid missing out on needed products, and make the most of sales information.

[0415] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0416] Step 1:

[0417] Obtaining a user's purchase history

[0418] The server accesses the purchase history data storage based on the user identifier. The server retrieves the user's past purchase history using a database query. For example, it executes the SQL query "SELECT product name, quantity, purchase date and time FROM purchase history WHERE user ID = '12345'".

[0419] Input: User Identifier

[0420] Output: Purchase history data (e.g., "User ID: 12345, Purchased items: Tomato, lettuce, chicken, Purchase date and time: 2023-09-15 18:30")

[0421] Step 2:

[0422] Obtaining special sale information

[0423] The server accesses the retailer's sales data storage and retrieves information about products currently on sale. The server retrieves the sales information using a database query. For example, it executes the SQL query "SELECT product name, sale price, sale period FROM sale product WHERE current_date BETWEEN start_date AND end_date."

[0424] Input: Current date

[0425] Output: Special sale item data (e.g. "Special sale items: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12")

[0426] Step 3:

[0427] Analysis of purchase history and estimation of cooling equipment inventory

[0428] The server uses the acquired purchase history data to estimate which items are likely to still be stored in the refrigerator. This analysis takes into account the user's recent purchase frequency and purchase date and time. For example, if a user has purchased tomatoes, lettuce, and chicken three times in the last two weeks, it estimates that these items are likely to remain in the refrigerator.

[0429] Input: Purchase history data (output from Step 1)

[0430] Output: Estimated cooling equipment inventory (e.g., "Tomatoes, Lettuce, Chicken")

[0431] Step 4:

[0432] Generate recommended products

[0433] The server generates a list of recommended products for the user based on the sale product information and estimated cooling equipment inventory. This list prioritizes products that match the user's past purchase history and preferences.

[0434] Input: Sale item data (output of Step 2) and estimated cooling equipment inventory (output of Step 3)

[0435] Output: Recommended product list (e.g. "Recommended product list: 1. Tomato sauce (on sale) 2. Cheese (on sale) 3. Croutons")

[0436] Step 5:

[0437] Submit a recommended product list

[0438] The server then sends the generated recommended product list to the user's mobile communication device or to a display device in the store. The server then formats the data in JSON format and sends it as a POST request to the API endpoint.

[0439] Input: Recommended product list (output of step 4)

[0440] Output: A recommendation notification delivered to the user's device (e.g., "Recommended product list: 1. Tomato sauce (on sale) 2. Cheese (on sale) 3. Croutons")

[0441] Step 6:

[0442] Gathering feedback and adjusting recommendation algorithms

[0443] When a user actually purchases a product, that information is automatically added to the purchase history. The server collects user evaluation data and adjusts the recommendation algorithm, thereby improving the accuracy of the recommended products provided next time.

[0444] Input: User rating data and new purchase history (user purchase information)

[0445] Output: A fine-tuned recommendation algorithm

[0446] The above is the specific processing flow of the system.

[0447] (Application example 1)

[0448] 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."

[0449] Conventional purchasing support systems are limited to recommending products based on a user's purchase history, and are unable to optimally utilize sale items. Furthermore, they lack a means for users to efficiently search for sale items within a store, reducing the convenience of shopping. Furthermore, there are limited ways to improve the accuracy of recommendations using feedback, making it difficult to improve user satisfaction. A comprehensive solution to these issues was needed.

[0450] 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.

[0451] In this invention, the server includes means for acquiring a purchase history from a user's purchase history database, means for acquiring sale item information from a store's sale item database, means for analyzing the user's purchase history and estimating items that are likely to still be in the refrigerator, means for generating a list of recommended items for the user based on the acquired sale item information and the estimated refrigerator inventory information, means for transmitting the generated recommended item list to the user's mobile device or an in-store display device, means for collecting feedback data provided by the user and fine-tuning the recommendation algorithm, and means for guiding the user to navigate within the store to the sale items. This enables efficient shopping by making the most of sale information and can improve the user's overall purchasing experience.

[0452] The "user purchase history database" is an information management system for storing information on products purchased by a user in the past.

[0453] The "sale item database" is an information management system for storing information about items currently on sale at a store.

[0454] The "means for acquiring purchase history" refers to a method or system for accessing a user's purchase history database and acquiring past purchase information.

[0455] The "means for acquiring sale item information" refers to a method or system for accessing a sale item database and acquiring information on items currently on sale.

[0456] A "means for analyzing purchase history" is a method or system for analyzing a user's purchase history data and identifying specific purchasing trends or patterns.

[0457] The "means for estimating items that are likely to still be in the refrigerator" refers to a method or system for estimating products that are likely to currently be in stock in the user's refrigerator based on the user's purchase history.

[0458] The "means for generating a recommended product list" is a method or system for creating a list that recommends the most suitable products to the user based on the acquired sale product information and estimated refrigerator inventory information.

[0459] A "mobile device" is a device that a user can carry and use, such as a smartphone or tablet.

[0460] An "in-store display device" is a device that is installed in a store and displays information to users.

[0461] A "means for collecting feedback data" is a method or system for collecting user-provided ratings and opinions to improve the performance of the system.

[0462] A "means for fine-tuning recommendation algorithms" is a method or system for improving the performance of recommendation algorithms based on collected feedback data.

[0463] A "navigation guidance means" is a method or system that provides location information and route guidance to help users find special sale items within a store.

[0464] This invention relates to a system that combines a user's purchase history with sale item information to individually recommend optimal products. The system includes a purchase history database, a sale item database, data analysis means, a recommended product generation means, an information provision means, and a feedback collection means.

[0465] The server first accesses the user's purchase history database and retrieves past purchase history data linked to the user ID. This data includes the names and quantities of products the user has previously purchased, as well as the purchase dates and times. Next, the server retrieves information about products currently on sale from the store's sales product database. This information includes the names of the products on sale, the sale prices, and the sale periods.

[0466] The server estimates which items are likely to remain in the user's refrigerator based on the acquired purchase history data. For example, if a specific item has been purchased several times in the past two weeks, it can estimate that the item is likely to remain in the refrigerator. The estimated refrigerator inventory information is combined with the acquired sale item information to generate a list of recommended products that are optimal for the user.

[0467] The generated recommended product list is sent from the server to the user's mobile device (smartphone or tablet) or to a display device in the store. This information is displayed on the mobile device via push notification, providing a visual presentation to the user. For example, a "Today's Recommended Products List" may be displayed on a smartphone app. Furthermore, the system also has a function to navigate the user to specific sale items within the store, allowing users to efficiently find sale items.

[0468] Additionally, when a user actually purchases a product, that information is automatically added to the purchase history. The server collects feedback data provided by the user and fine-tunes the recommendation algorithm to improve the accuracy of product recommendations for future users.

[0469] For example, when a user opens an application, they receive a push notification that reads: "Today's featured items: 1. Tomato Sauce (On Sale) 2. Cheese (On Sale). Please use the in-app navigation feature to find special offers on the store map."

[0470] For example, you can use the following prompts for your generative AI model:

[0471] "Generate the best recommended product list based on the user's purchase history and special sale information. As an example, consider the following purchase history and special sale information: User ID: 12345, Purchased items: Tomato, lettuce, chicken, Purchase date and time: 2023-09-15 18:30, Special sale items: Tomato sauce, cheese, Sale period: 2023-10-10 to 2023-10-12."

[0472] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0473] Step 1:

[0474] The server accesses the user's purchase history database and retrieves past purchase history data linked to the user ID. The input is the user ID, and the output is purchase history data (e.g., product name, quantity, purchase date and time). Specifically, it uses the Python requests library to retrieve the purchase history from the database and parses it in JSON format.

[0475] Step 2:

[0476] The server accesses the store's sales database and retrieves information about products currently on sale. The input is a database access request, and the output is sales information (e.g., product name, sale price, sale period). Specifically, the server uses the same Python requests library to retrieve data from the sales database and parse it in JSON format.

[0477] Step 3:

[0478] The server analyzes the purchase history data and estimates the items that are likely to still be in the user's refrigerator. The input is the acquired purchase history data, and the output is the estimated refrigerator inventory data. Specifically, it aggregates the data using the Pandas library and calculates the items still remaining in the refrigerator based on past purchase frequency.

[0479] Step 4:

[0480] The server generates a list of recommended products based on the acquired sale item information and estimated refrigerator inventory information. The input is sale item information and refrigerator inventory data, and the output is a list of recommended products. Specifically, it uses a generative AI model (e.g., TensorFlow or PyTorch) to learn the user's purchasing trends and generate a list of recommended products.

[0481] Step 5:

[0482] The server sends the generated recommended product list to the user's mobile device or an in-store display device. The input is the recommended product list, and the output is a specific message to be sent to the mobile device or display device. Specifically, the server uses Firebase Cloud Messaging (FCM) to send the notification.

[0483] Step 6:

[0484] The device receives the recommended product list and visually presents it to the user. The input is the recommended product list sent from the server, and the output is the list displayed to the user. Specifically, a push notification is displayed on the smartphone app, and the list is presented as "Today's Recommended Product List."

[0485] Step 7:

[0486] The server collects user-provided feedback data and fine-tunes the recommendation algorithm. The input is the user feedback data, and the output is the adjusted model of the algorithm. Specifically, it analyzes the feedback data and adjusts the learning parameters of the generative AI model.

[0487] Step 8:

[0488] The device provides guidance so that the user can navigate within the store to the sale items. The input is the user's location information and sale item information, and the output is navigation information to the sale items. Specifically, it uses the Google Maps API to display a map of the store and provides guidance on the shortest route.

[0489] 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.

[0490] The present invention relates to a system that recommends optimal products to individuals by combining a user's purchase history, sale item information, and an emotion engine that recognizes the user's emotions. This system includes a purchase history database, a sale item database, data analysis means, a recommended product generation means, information provision means, feedback collection means, and emotion recognition means.

[0491] Data Acquisition

[0492] Obtaining a user's purchase history

[0493] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. This data includes the date and time of each purchase, the purchased item, and the purchased quantity. For example, the user ID is "12345," the purchased items are "tomato, lettuce, chicken," and the purchase date and time is "2023-09-15 18:30."

[0494] Obtaining special sale information

[0495] The server retrieves information about products currently on sale from the store's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, the information might be "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[0496] Analyzing the data

[0497] Analysis of purchase history and estimation of refrigerator inventory

[0498] The server analyzes the acquired purchase history data and estimates which items may remain in the refrigerator based on the user's recent purchase frequency. For example, if an item has been purchased three or more times in the past two weeks, it is assumed that the item is likely to remain in the refrigerator. If the user has recently purchased tomatoes, lettuce, and chicken multiple times, it is assumed that these items remain in the refrigerator.

[0499] Generate recommended products

[0500] Generate recommended product lists based on sale items and refrigerator inventory

[0501] The server generates a list of recommended products for the user based on the sale product information and the estimated refrigerator inventory. From the sale products, it selects products to recommend preferentially based on the user's preferences and past purchase history. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, these will be included in the recommended product list.

[0502] emotion recognition

[0503] User Emotion Recognition

[0504] The device (mobile device) uses a camera and microphone to recognize the user's emotions. This information is sent to the server in real time. For example, if the user is tired or stressed, the device can sense their emotional state.

[0505] Adjusting product listings based on sentiment data

[0506] The server adjusts the recommended product list based on the user's emotional data. For example, if the user is feeling stressed, the server can prioritize products with a relaxing effect (such as herbal tea) in the list.

[0507] Providing information

[0508] Submit a recommended product list

[0509] The server sends the generated recommended product list to the user's mobile device or a display device in the store. The device (mobile device) receives this information and visually presents it to the user. For example, a smartphone app might display "Today's Recommended Product List" as "1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Croutons, etc."

[0510] Collecting feedback

[0511] Purchase History Updates and Feedback

[0512] When a user actually purchases a product, that information is automatically added to their purchase history. The server collects feedback data provided by the user (e.g., purchase history) and fine-tunes the recommendation algorithm, thereby improving the accuracy of future recommendations.

[0513] The above is an embodiment of the present invention. This system allows users to shop efficiently, maximize sales information, and receive optimal product recommendations based on their current emotional state.

[0514] The processing flow will be explained below.

[0515] Step 1: Get your purchase history

[0516] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. This data includes the date and time of each purchase, the purchased items, and the purchased quantities. Specifically, the information might be something like "User ID: 12345, Purchased items: Tomato, lettuce, chicken, Purchase date and time: 2023-09-15 18:30."

[0517] Step 2: Get sale information

[0518] The server retrieves information about products currently on sale from the store's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[0519] Step 3: Analyze your purchase history

[0520] The server analyzes the acquired purchase history data and estimates which items may remain in the refrigerator based on the user's recent purchase frequency. Specifically, it estimates that items that have been purchased three or more times in the last two weeks remain in the refrigerator. For example, if the user has recently purchased tomatoes, lettuce, and chicken multiple times, it estimates that these items remain in the refrigerator.

[0521] Step 4: Obtaining emotion data

[0522] The device (mobile device) uses a camera and microphone to recognize the user's emotions and transmits the data to a server. For example, if the user is tired or stressed, the device can detect that emotional state.

[0523] Step 5: Generate a list of recommended products

[0524] The server generates a list of recommended products based on the sale product information, estimated refrigerator inventory, and emotional data. From the sale products, it selects products to recommend based on the user's preferences and current emotional state. For example, if the user is tired, it prioritizes products with a relaxing effect (such as herbal tea) in the list.

[0525] Step 6: Submit your recommended products list

[0526] The server sends the generated recommended product list to the user's mobile device or to a display device in the store. The device (mobile device) receives this information and visually presents it to the user. Specifically, the smartphone app displays "Today's Recommended Product List" as follows: 1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Herbal Tea (Based on User Emotion Data)."

[0527] Step 7: Gather feedback

[0528] When a user actually purchases a product, that information is automatically added to their purchase history. The server collects feedback data provided by the user (e.g., purchase history) and fine-tunes the recommendation algorithm, thereby improving the accuracy of future product recommendations.

[0529] The above is the specific processing flow of the product recommendation system for users that combines an emotion engine. This enables users to receive optimal product recommendations based on their current emotional state, enabling them to shop efficiently.

[0530] Example 2

[0531] 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."

[0532] The present invention aims to provide an optimal product recommendation system that takes into account not only a user's purchase history and sale product information, but also the user's emotional state. Conventional recommendation systems generally rely on a user's preferences and purchase history, but there is a demand for more accurate product recommendations that meet the user's needs by taking the user's emotional state into account. Therefore, it is necessary to recognize the user's emotional state and adjust the product list based on that.

[0533] 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.

[0534] In this invention, the server includes means for acquiring a purchase history from a user's purchase history database, means for acquiring sale item information from a store's sale item database, means for analyzing the user's purchase history and estimating items that are likely to still be in the refrigerator, means for generating a list of recommended items for the user based on the acquired sale item information and the estimated refrigerator inventory information, means for transmitting the generated recommended item list to the user's mobile device or an in-store display device, means for recognizing the user's emotions and acquiring the data, means for adjusting the recommended item list based on the recognized emotion data, and means for collecting feedback data provided by the user and fine-tuning the recommendation algorithm, thereby enabling more accurate product recommendations that take the user's emotional state into consideration.

[0535] "Purchase history" is data containing information about products purchased by a user in the past, specifically including the purchase date and time, product name, and purchase quantity.

[0536] "Special sale product information" is data containing information about products that a store is offering at special prices, and specifically includes the names of the products on sale, the sale prices, the sale periods, and so on.

[0537] The "purchase history database" is a database for storing data on a user's past purchase history.

[0538] The "sales product database" is a database for storing information about sales products at a store.

[0539] "Refrigerator inventory" is a concept for estimating products that are likely to still be in a user's refrigerator, and is estimated based on the user's purchase history data.

[0540] The "recommended product list" is a list of products recommended to the user, and is generated based on sale product information, refrigerator inventory, and the user's emotional state.

[0541] A "user's mobile terminal" is an electronic device that a user carries and uses, such as a smartphone or tablet.

[0542] The "display device in the store" refers to a display device such as a display or monitor installed in the store.

[0543] "Emotion recognition" is a technology that uses devices such as cameras and microphones to detect a user's emotional state.

[0544] "Feedback data" is data provided by a user after purchasing a product, and includes purchase history, impressions, and the like.

[0545] A "recommendation algorithm" is an algorithm that recommends products based on a user's purchase history, sale information, emotional data, etc.

[0546] "Emotional state" indicates the type and intensity of the emotion the user is feeling, and includes fatigue, stress, happiness, and the like.

[0547] The present invention is a system that recommends optimal products to individuals by combining a user's purchase history, sale product information, and an engine that recognizes the user's emotions. This system includes a user purchase history database, a sale product database, data analysis means, a recommended product generation means, information provision means, feedback collection means, and emotion recognition means.

[0548] Data Acquisition

[0549] Obtaining a user's purchase history

[0550] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. This data includes the date and time of each purchase, the purchased item, and the purchased quantity. For example, the user ID is "12345," the purchased items are "tomato, lettuce, chicken," and the purchase date and time is "2023-09-15 18:30."

[0551] Obtaining special sale information

[0552] The server retrieves information about the products currently on sale from the store's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, the information might be "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[0553] Analyzing the data

[0554] Analysis of purchase history and estimation of refrigerator inventory

[0555] The server analyzes the acquired purchase history data and estimates which items may remain in the refrigerator based on the user's recent purchase frequency. For example, if a product has been purchased three or more times in the past two weeks, it is estimated that the item is likely to remain in the refrigerator. If the user has recently purchased tomatoes, lettuce, and chicken multiple times, it is estimated that these items remain in the refrigerator.

[0556] Generate recommended products

[0557] Generate recommended product lists based on sale items and refrigerator inventory

[0558] The server generates a list of recommended products for the user based on the sale product information and the estimated refrigerator inventory. From the sale products, it selects products to recommend preferentially based on the user's preferences and past purchase history. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, these will be included in the recommended product list.

[0559] emotion recognition

[0560] User Emotion Recognition

[0561] The device (mobile device) uses a camera and microphone to recognize the user's emotions. This information is sent to the server in real time. For example, if the user is tired or stressed, the device can sense their emotional state.

[0562] Adjusting product listings based on sentiment data

[0563] The server adjusts the recommended product list based on the user's emotional data. For example, if the user is feeling stressed, the server can prioritize products with a relaxing effect (such as herbal tea) in the list.

[0564] Providing information

[0565] Submit a recommended product list

[0566] The server sends the generated recommended product list to the user's mobile device or a display device in the store. The device (mobile device) receives this information and visually presents it to the user. For example, a smartphone app might display "Today's Recommended Product List" as "1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Croutons, etc."

[0567] Collecting feedback

[0568] Purchase History Updates and Feedback

[0569] When a user actually purchases a product, that information is automatically added to their purchase history. The server collects feedback data provided by the user (e.g., purchase history) and fine-tunes the recommendation algorithm, thereby improving the accuracy of future recommendations.

[0570] Examples of prompt statements

[0571] Below is an example of a prompt sentence for a generative AI model to recommend products based on a user's purchase history, sale information, and emotional data:

[0572] User ID: 12345

[0573] Recent purchase history: Tomato, lettuce, chicken (2023-09-15 18:30)

[0574] Special Offer:

[0575] 1. Tomato Sauce (Special Sale Period: 2023-10-10 to 2023-10-12)

[0576] 2. Cheese (Special Sale Period: 2023-10-10 to 2023-10-12)

[0577] User emotion data: Stress state (via emotion engine)

[0578] This enables more accurate product recommendations that take into account the user's emotional state.

[0579] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0580] Step 1:

[0581] The server receives the user ID as input and retrieves the user's purchase history data from the purchase history database. This data includes the date and time of each purchase, the purchased items, and the purchase quantity. Specifically, using the user ID "12345," it retrieves "Purchase date and time: 2023-09-15 18:30, purchased items: tomato, lettuce, chicken, purchase quantity: 1 each." The retrieved data is sent to the next analysis step.

[0582] Step 2:

[0583] The server uses the acquired purchase history data as input and applies an analysis algorithm to calculate the frequency of items recently purchased by the user. For example, items purchased three or more times in the past two weeks are estimated as refrigerator inventory. The output is estimated refrigerator inventory information; if "tomatoes, lettuce, and chicken" are included, they are estimated to be left in the refrigerator.

[0584] Step 3:

[0585] The server sends a query to the store's special sale database to retrieve information about the current sale items. The input is a query statement to the database, and the output is "Special sale item name: Tomato sauce, Special sale price: 200 yen, Special sale period: 2023-10-10 to 2023-10-12."

[0586] Step 4:

[0587] The server combines the sale product information and estimated refrigerator inventory information as input, and generates a list of recommended products based on the user's preferences and purchase history. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, the server prioritizes tomato sauce and cheese. The output is the generated list of recommended products.

[0588] Step 5:

[0589] The device (mobile device) captures the user's facial expressions and voice data using a camera and microphone, and inputs this data into an emotion recognition engine. The engine analyzes this data and recognizes the user's emotional state (e.g., stress level). The output is real-time emotion data, which is sent to a server.

[0590] Step 6:

[0591] The server adjusts the recommended product list based on the emotional data sent by the user. For example, if the user is under stress, it adds relaxing herbal tea to the list. This adjustment generates a final recommended product list that reflects the emotional data.

[0592] Step 7:

[0593] The server sends the generated recommended product list to the user's mobile device or a display device in the store. The device (mobile device) receives this information and visually presents it to the user. For example, a smartphone app might display "Today's Recommended Product List" as "1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Herbal Tea (Reflecting Emotional Data)."

[0594] Step 8:

[0595] When a user makes a purchase, that information is automatically added to the purchase history database, and the server collects this new purchase history data. The server also uses the feedback data provided by the user to fine-tune the recommendation algorithm, which improves the accuracy of future recommendations.

[0596] (Application example 2)

[0597] 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."

[0598] Today's consumers are extremely busy and need assistance in efficiently purchasing daily necessities and food. Furthermore, a system that allows users to purchase items without missing out on special offers would respond to consumers' desire to save money. However, conventional recommendation systems have difficulty recommending optimal products because they do not fully consider users' emotions or individual purchasing habits. Furthermore, providing information in real time is crucial to effectively take advantage of special offers in the market.

[0599] 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.

[0600] In this invention, the server includes means for acquiring a purchase history from a purchase history database of the user, means for acquiring sale item information from a sale item database of the commercial facility, means for analyzing the user's purchase history and estimating items that are likely to still be in the refrigerator, means for generating a list of recommended items for the user based on the acquired sale item information and the estimated refrigerator inventory information, means for transmitting the generated recommended item list to the user's mobile terminal or a display device in the commercial facility, means for collecting feedback data provided by the user and fine-tuning a recommendation algorithm, emotion recognition means for collecting user emotion data, and means for adjusting the recommended item list based on the emotion data. This makes it possible to quickly and accurately recommend optimal products based on the user's emotional state and individual purchasing characteristics while effectively utilizing sale information.

[0601] The "user purchase history database" is an accessible database that records the history of products that a user has purchased in the past.

[0602] A "sales product database" is a database that records and provides access to information about products on sale at commercial facilities.

[0603] The "emotion recognition means" is a means for recognizing the user's emotions using sensors such as a camera or microphone, and acquiring that information.

[0604] The "means for acquiring purchase history" is a means for accessing a purchase history database of a user and acquiring information on products that the user has purchased in the past.

[0605] The "means for acquiring sale item information" refers to a means for accessing a sale item database and acquiring information about items on sale at commercial facilities.

[0606] The "means for analyzing purchase history" is a means for analyzing the user's purchasing patterns based on the acquired purchase history and estimating items that are likely to remain in the refrigerator.

[0607] The "means for generating a recommended product list" is a means for creating an optimal product list for a user based on sale product information and estimated refrigerator inventory information.

[0608] The "means for transmitting a recommended product list" is a means for transmitting the generated recommended product list to a user's mobile terminal or a display device in a commercial facility.

[0609] "Means for collecting feedback data" refers to means for collecting post-purchase opinions and purchase information provided by users and using them to improve recommendation algorithms.

[0610] The "means for adjusting the recommended product list based on emotion data" refers to a means for adjusting the contents of the recommended product list based on the user's emotion data acquired by the emotion recognition means, and recommending optimal products to the user.

[0611] This invention relates to a system that recommends optimal products to individuals by combining a user's purchase history, sale item information, and an emotion engine that recognizes the user's emotions. The main elements are a purchase history database, a sale item database, data analysis means, a recommended product generation means, information provision means, feedback collection means, and emotion recognition means.

[0612] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. This data includes the date and time of each purchase, the purchased item, and the purchased quantity. For example, the user ID is "12345," the purchased items are "tomato, lettuce, chicken," and the purchase date and time is "2023-09-15 18:30."

[0613] Next, the server retrieves information about products currently on sale from the commercial facility's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[0614] Based on this, the server analyzes the purchase history data and estimates which items may remain in the refrigerator based on the user's recent purchase frequency. For example, if an item has been purchased three or more times in the past two weeks, it is assumed that the item is likely to remain in the refrigerator. If the user has recently purchased tomatoes, lettuce, and chicken multiple times, it is assumed that these items remain in the refrigerator.

[0615] Based on the estimated refrigerator inventory, the server compares it with sale item information to generate a list of recommended items. From the sale items, it selects items to recommend preferentially based on the user's preferences and past purchase history. For example, tomato sauce and cheese are on sale, and the user frequently purchases tomatoes, so these are included in the recommended items list.

[0616] Furthermore, the mobile device uses a camera and microphone to recognize the user's emotions in real time, and this information is sent to a server to measure the user's emotional state, for example, if they are tired or stressed.

[0617] The server adjusts the recommended product list based on the user's emotional data. For example, if the user is feeling stressed, the server can prioritize products with a relaxing effect (such as herbal tea) in the list.

[0618] The generated recommended product list is sent from the server to the user's mobile device or to a display device within the commercial facility. The mobile device receives this information and visually presents it to the user. For example, a smartphone app might display "Today's Recommended Product List" as "1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Croutons, etc."

[0619] Finally, when a user actually purchases a product, that information is automatically added to their purchase history. The server collects the feedback data provided by the user (e.g., purchase history) and fine-tunes the recommendation algorithm, thereby improving the accuracy of future recommendations.

[0620] For example and prompt purposes, we will use the following information as input:

[0621] Specific prompt examples:

[0622] User ID: 12345

[0623] Purchase History API URL: http: / / example.com / api / purchase_history

[0624] Special Offers API URL: http: / / example.com / api / special_offers

[0625] Recommendation API URL: http: / / example.com / api / recommendation

[0626] Emotion: stressed

[0627] Generate a list of recommended products

[0628] As a result, users can shop efficiently, make the most of sale information, and receive optimal product recommendations based on their emotions. This system simultaneously satisfies consumers' desire for savings and convenience, and is expected to improve customer satisfaction in commercial facilities.

[0629] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0630] Step 1:

[0631] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. The input is the user ID and the output is the purchase history data. This data includes the date and time of each purchase, the purchased item, and the purchased quantity. Specifically, it sends a request to the API endpoint and retrieves the purchase history data as a response.

[0632] Step 2:

[0633] The server retrieves information about products currently on sale from the commercial facility's sale product database. The input is the API URL of the sale product database, and the output is the sale product information. This information includes the name of the sale product, the sale price, and the sale period. Specifically, it sends a request to the API endpoint and retrieves the sale product data as a response.

[0634] Step 3:

[0635] The server analyzes the acquired purchase history data and estimates which items may remain in the refrigerator based on the user's most recent purchase frequency. The input is the purchase history data, and the output is a list of items estimated to remain in the refrigerator. Specifically, it calculates the purchase frequency of each product and lists items that have been frequently purchased within a certain period of time.

[0636] Step 4:

[0637] The server collects the user's emotional data through an emotion recognition means. The input is the user's real-time video and audio data, and the output is the judged emotional data. Specifically, it analyzes the data input from the camera and microphone and identifies the emotion using a generative AI model.

[0638] Step 5:

[0639] The server generates a recommended product list based on the acquired sale product information, estimated refrigerator inventory information, and emotional data. The inputs are sale product information, refrigerator inventory information, and emotional data, and the output is a recommended product list. Specifically, the server selects products from the sale products that match the user's preferences and emotional state, and generates the list.

[0640] Step 6:

[0641] The server then sends the generated recommended product list to the user's mobile device or a display device within the commercial facility. The input is the recommended product list, and the output is the information displayed on the user's device or display device. Specifically, the list is sent to the device so that the user can visually confirm it.

[0642] Step 7:

[0643] When a user actually purchases a product, the purchase information is added to the purchase history. The input is the information about the purchased product, and the output is an updated purchase history database. Specifically, the purchase information is added to the database, and the server keeps the data as up-to-date.

[0644] Step 8:

[0645] The server collects post-purchase feedback data and fine-tunes the recommendation algorithm. The input is the feedback data provided by the user, and the output is an improved recommendation algorithm. Specifically, the server analyzes the collected feedback and adjusts the algorithm parameters.

[0646] 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.

[0647] 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.

[0648] 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.

[0649] [Third embodiment]

[0650] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0651] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0652] 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).

[0653] 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.

[0654] 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.

[0655] 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).

[0656] 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.

[0657] 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.

[0658] 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.

[0659] 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.

[0660] 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.

[0661] 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."

[0662] The present invention relates to a system that combines a user's purchase history and sale item information to individually recommend optimal products. This system includes a purchase history database, a sale item database, data analysis means, a recommended product generation means, an information provision means, and a feedback collection means.

[0663] Data Acquisition

[0664] Obtaining a user's purchase history

[0665] The server accesses the purchase history database linked to the user ID and retrieves past purchase history data. This data includes the names and quantities of products purchased in the past, as well as the purchase dates and times. For example, the information might be "User ID: 12345, Purchased items: Tomato, lettuce, chicken, Purchase date and time: 2023-09-15 18:30."

[0666] Obtaining special sale information

[0667] The server retrieves information about products currently on sale from the store's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[0668] Analyzing the data

[0669] Analysis of purchase history and estimation of refrigerator inventory

[0670] The server estimates which items are likely to remain in the user's refrigerator based on the acquired purchase history. For example, if a user has purchased tomatoes, lettuce, and chicken three times in the last two weeks, the server estimates that these items are likely to remain in the refrigerator.

[0671] Generate recommended products

[0672] Generate recommended product lists based on sale items and refrigerator inventory

[0673] The server generates a list of recommended products that are optimal for the user based on the acquired sale item information and estimated refrigerator inventory information. Among the sale items, it prioritizes and recommends items that match the user's past purchase history and preferences. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, it determines that these items are suitable.

[0674] Providing information

[0675] Submit a recommended product list

[0676] The server sends the generated recommended product list to the user's mobile device or a display device in the store. The device (mobile device) receives this information and visually presents it to the user. Specifically, a "Today's Recommended Product List" is displayed on the smartphone app via push notification. For example, "Recommended Product List: 1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Croutons, etc."

[0677] Collecting feedback

[0678] Purchase History Updates and Feedback

[0679] When a user actually purchases a product, that information is automatically added to their purchase history. The server collects the feedback data provided by the user and fine-tunes the recommendation algorithm, which can then provide even better recommendations to the user in the future.

[0680] The above is an embodiment of the present invention. This system allows users to shop efficiently, avoid missing out on needed products, and make the most of sales information.

[0681] The processing flow will be explained below.

[0682] Step 1: Get the data

[0683] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. This data includes the date and time of each purchase, the purchased item, and the purchased quantity. For example, the user ID is "12345," the purchased items are "tomato, lettuce, chicken," and the purchase date and time is "2023-09-15 18:30."

[0684] Step 2: Get sale information

[0685] The server retrieves information about products currently on sale from the store's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, the information might be "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[0686] Step 3: Analyze your purchase history

[0687] The server analyzes the acquired purchase history data and estimates which items may remain in the refrigerator based on the user's recent purchase frequency. For example, if an item has been purchased three or more times in the past two weeks, it is assumed that the item is likely to remain in the refrigerator. If the user has recently purchased tomatoes, lettuce, and chicken multiple times, it is assumed that these items remain in the refrigerator.

[0688] Step 4: Generate a list of recommended products

[0689] The server generates a list of recommended products for the user based on the sale product information and the estimated refrigerator inventory. From the sale products, it selects products to recommend preferentially based on the user's preferences and past purchase history. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, these will be included in the recommended product list.

[0690] Step 5: Submit your recommended products list

[0691] The server sends the generated recommended product list to the user's mobile device or a display device in the store. The device (mobile device) receives this information and visually presents it to the user. For example, a smartphone app might display "Today's Recommended Product List" as "1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Croutons, etc."

[0692] Step 6: Gather feedback

[0693] When a user actually purchases a product, that information is automatically added to their purchase history. The server collects feedback data provided by the user (e.g., purchase history) and fine-tunes the recommendation algorithm, thereby improving the accuracy of future recommendations.

[0694] These are the specific processing steps that allow users to shop efficiently and take full advantage of sales information.

[0695] Example 1

[0696] 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."

[0697] Conventional recommendation systems recommend products based solely on a user's purchasing history, which makes it difficult to fully consider the user's recent purchasing behavior or sales information, making it difficult to recommend appropriate products in a timely manner. Furthermore, they have low accuracy in identifying products that are likely to interest users, which prevents them from fully motivating users to purchase. Furthermore, the mechanisms for efficiently collecting user feedback and incorporating it into the recommendation algorithm are insufficient, leaving a need for an improved user experience. Therefore, there is a need for a system that can combine a user's purchasing history, sales information, and feedback to make more accurate product recommendations.

[0698] 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.

[0699] In this invention, the server includes means for acquiring a purchase history from a purchase history data storage acquired based on a user identifier, means for acquiring sale item information from a retailer's sale item data storage, means for analyzing the purchase history and estimating items that are likely to still be stored in the refrigerator, means for generating an optimal recommended product list for the user based on the acquired sale item information and the estimated refrigerator inventory information, means for transmitting the generated recommended product list to the user's mobile communication terminal or an in-store display device, and means for collecting evaluation data provided by the user and adjusting the recommendation algorithm. This makes it possible to integrate the user's purchase history, sale information, and feedback to make more accurate and timely product recommendations.

[0700] A "user identifier" is unique information used to identify a specific user, such as an ID or account number.

[0701] "Purchase history data storage" is data storage that stores information about products purchased by users in the past, including product names, quantities, purchase dates, and so on.

[0702] "Sale product data storage" is a data storage that stores information about products on sale at a retail store, including the name, price, and sale period of the sale product.

[0703] "Refrigeration equipment" refers to equipment used to store food and other items at low temperatures. Generally, this includes refrigerators and freezers.

[0704] A "recommended product list" is a list of products recommended to a user. It is generated based on the user's purchase history and special sale information.

[0705] A "mobile communication terminal" is a communication device that can be carried and used by a user. This includes smartphones and tablet terminals.

[0706] "In-store display devices" are devices installed in stores to display information. These include digital signage and information display screens.

[0707] "Evaluation data" refers to data related to evaluations of products provided by users, including product ratings and feedback.

[0708] A "recommendation algorithm" is a set of calculation procedures and rules for recommending optimal products to users. The algorithm operates based on purchase history and sale information.

[0709] The present invention is a system for recommending optimal products to individual users by utilizing their purchasing history and sale product information. This system is implemented mainly by a server, a terminal, and a user.

[0710] The server accesses multiple databases to retrieve the user's purchase history data and sale item data. Based on the user identifier, the server issues a query to the purchase history data storage to retrieve information such as the name, quantity, and purchase date and time of items previously purchased by the user. The server then accesses the retailer's sale item data storage to retrieve information such as the name, sale price, and sale period of the sale item.

[0711] The server analyzes the acquired purchase history data and estimates which items are likely to still be stored in the refrigerator. This analysis takes into account factors such as the user's recent purchase frequency. For example, if a user has purchased tomatoes, lettuce, and chicken three times in the last two weeks, it estimates that these items are likely to remain in the refrigerator.

[0712] Next, the server generates a list of recommended products that are optimal for the user based on the acquired sale product information and estimated cooling equipment inventory information. This list prioritizes and recommends products that match the user's past purchase history and preferences from among the sale products. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, these products will be included in the recommended product list.

[0713] The generated recommended product list is sent from the server to the user's mobile communication device or to a display device in the store. The device receives this information and visually presents it to the user. Specifically, the "Today's Recommended Product List" is displayed via push notification on the user's smartphone app. For example, the recommended product list might be: 1. Tomato sauce (on sale) 2. Cheese (on sale) 3. Croutons.

[0714] When a user actually purchases a product, that information is automatically added to the purchase history. The server collects the user's rating data and adjusts the recommendation algorithm, thereby further improving the accuracy of the product recommendations provided to the user in the future.

[0715] Examples and prompts

[0716] Examples:

[0717] If a user has purchased tomatoes three times and lettuce twice in the last two weeks, the server will infer that these items are likely to remain in the refrigerator.

[0718] The server generates a list of recommended products because "tomato sauce" and "cheese" are on sale and these products match the user's purchase history.

[0719] Display the following recommended product list on your device: 1. Tomato sauce (on sale) 2. Cheese (on sale) 3. Croutons.

[0720] Example prompt:

[0721] 1. "How can I estimate the inventory in a cooling device based on a user's purchasing history?"

[0722] 2. "Explain how to generate a list of recommended products by combining special offers and user preferences."

[0723] 3. "Please give me a concrete example of how a list of recommended products can be displayed on a user's mobile device."

[0724] The above is an embodiment of the present invention. This system allows users to shop efficiently, avoid missing out on needed products, and make the most of sales information.

[0725] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0726] Step 1:

[0727] Obtaining a user's purchase history

[0728] The server accesses the purchase history data storage based on the user identifier. The server retrieves the user's past purchase history using a database query. For example, it executes the SQL query "SELECT product name, quantity, purchase date and time FROM purchase history WHERE user ID = '12345'".

[0729] Input: User Identifier

[0730] Output: Purchase history data (e.g., "User ID: 12345, Purchased items: Tomato, lettuce, chicken, Purchase date and time: 2023-09-15 18:30")

[0731] Step 2:

[0732] Obtaining special sale information

[0733] The server accesses the retailer's sales data storage and retrieves information about products currently on sale. The server retrieves the sales information using a database query. For example, it executes the SQL query "SELECT product name, sale price, sale period FROM sale product WHERE current_date BETWEEN start_date AND end_date."

[0734] Input: Current date

[0735] Output: Special sale item data (e.g. "Special sale items: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12")

[0736] Step 3:

[0737] Analysis of purchase history and estimation of cooling equipment inventory

[0738] The server uses the acquired purchase history data to estimate which items are likely to still be stored in the refrigerator. This analysis takes into account the user's recent purchase frequency and purchase date and time. For example, if a user has purchased tomatoes, lettuce, and chicken three times in the last two weeks, it estimates that these items are likely to remain in the refrigerator.

[0739] Input: Purchase history data (output from Step 1)

[0740] Output: Estimated cooling equipment inventory (e.g., "Tomatoes, Lettuce, Chicken")

[0741] Step 4:

[0742] Generate recommended products

[0743] The server generates a list of recommended products for the user based on the sale product information and estimated cooling equipment inventory. This list prioritizes products that match the user's past purchase history and preferences.

[0744] Input: Sale item data (output of Step 2) and estimated cooling equipment inventory (output of Step 3)

[0745] Output: Recommended product list (e.g. "Recommended product list: 1. Tomato sauce (on sale) 2. Cheese (on sale) 3. Croutons")

[0746] Step 5:

[0747] Submit a recommended product list

[0748] The server then sends the generated recommended product list to the user's mobile communication device or to a display device in the store. The server then formats the data in JSON format and sends it as a POST request to the API endpoint.

[0749] Input: Recommended product list (output of step 4)

[0750] Output: A recommendation notification delivered to the user's device (e.g., "Recommended product list: 1. Tomato sauce (on sale) 2. Cheese (on sale) 3. Croutons")

[0751] Step 6:

[0752] Gathering feedback and adjusting recommendation algorithms

[0753] When a user actually purchases a product, that information is automatically added to the purchase history. The server collects user evaluation data and adjusts the recommendation algorithm, thereby improving the accuracy of the recommended products provided next time.

[0754] Input: User rating data and new purchase history (user purchase information)

[0755] Output: A fine-tuned recommendation algorithm

[0756] The above is the specific processing flow of the system.

[0757] (Application example 1)

[0758] 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."

[0759] Conventional purchasing support systems are limited to recommending products based on a user's purchase history, and are unable to optimally utilize sale items. Furthermore, they lack a means for users to efficiently search for sale items within a store, reducing the convenience of shopping. Furthermore, there are limited ways to improve the accuracy of recommendations using feedback, making it difficult to improve user satisfaction. A comprehensive solution to these issues was needed.

[0760] 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.

[0761] In this invention, the server includes means for acquiring a purchase history from a user's purchase history database, means for acquiring sale item information from a store's sale item database, means for analyzing the user's purchase history and estimating items that are likely to still be in the refrigerator, means for generating a list of recommended items for the user based on the acquired sale item information and the estimated refrigerator inventory information, means for transmitting the generated recommended item list to the user's mobile device or an in-store display device, means for collecting feedback data provided by the user and fine-tuning the recommendation algorithm, and means for guiding the user to navigate within the store to the sale items. This enables efficient shopping by making the most of sale information and can improve the user's overall purchasing experience.

[0762] The "user purchase history database" is an information management system for storing information on products purchased by a user in the past.

[0763] The "sale item database" is an information management system for storing information about items currently on sale at a store.

[0764] The "means for acquiring purchase history" refers to a method or system for accessing a user's purchase history database and acquiring past purchase information.

[0765] The "means for acquiring sale item information" refers to a method or system for accessing a sale item database and acquiring information on items currently on sale.

[0766] A "means for analyzing purchase history" is a method or system for analyzing a user's purchase history data and identifying specific purchasing trends or patterns.

[0767] The "means for estimating items that are likely to still be in the refrigerator" refers to a method or system for estimating products that are likely to currently be in stock in the user's refrigerator based on the user's purchase history.

[0768] The "means for generating a recommended product list" is a method or system for creating a list that recommends the most suitable products to the user based on the acquired sale product information and estimated refrigerator inventory information.

[0769] A "mobile device" is a device that a user can carry and use, such as a smartphone or tablet.

[0770] An "in-store display device" is a device that is installed in a store and displays information to users.

[0771] A "means for collecting feedback data" is a method or system for collecting user-provided ratings and opinions to improve the performance of the system.

[0772] A "means for fine-tuning recommendation algorithms" is a method or system for improving the performance of recommendation algorithms based on collected feedback data.

[0773] A "navigation guidance means" is a method or system that provides location information and route guidance to help users find special sale items within a store.

[0774] This invention relates to a system that combines a user's purchase history with sale item information to individually recommend optimal products. The system includes a purchase history database, a sale item database, data analysis means, a recommended product generation means, an information provision means, and a feedback collection means.

[0775] The server first accesses the user's purchase history database and retrieves past purchase history data linked to the user ID. This data includes the names and quantities of products the user has previously purchased, as well as the purchase dates and times. Next, the server retrieves information about products currently on sale from the store's sales product database. This information includes the names of the products on sale, the sale prices, and the sale periods.

[0776] The server estimates which items are likely to remain in the user's refrigerator based on the acquired purchase history data. For example, if a specific item has been purchased several times in the past two weeks, it can estimate that the item is likely to remain in the refrigerator. The estimated refrigerator inventory information is combined with the acquired sale item information to generate a list of recommended products that are optimal for the user.

[0777] The generated recommended product list is sent from the server to the user's mobile device (smartphone or tablet) or to a display device in the store. This information is displayed on the mobile device via push notification, providing a visual presentation to the user. For example, a "Today's Recommended Products List" may be displayed on a smartphone app. Furthermore, the system also has a function to navigate the user to specific sale items within the store, allowing users to efficiently find sale items.

[0778] Additionally, when a user actually purchases a product, that information is automatically added to the purchase history. The server collects feedback data provided by the user and fine-tunes the recommendation algorithm to improve the accuracy of product recommendations for future users.

[0779] For example, when a user opens an application, they receive a push notification that reads: "Today's featured items: 1. Tomato Sauce (On Sale) 2. Cheese (On Sale). Please use the in-app navigation feature to find special offers on the store map."

[0780] For example, you can use the following prompts for your generative AI model:

[0781] "Generate the best recommended product list based on the user's purchase history and special sale information. As an example, consider the following purchase history and special sale information: User ID: 12345, Purchased items: Tomato, lettuce, chicken, Purchase date and time: 2023-09-15 18:30, Special sale items: Tomato sauce, cheese, Sale period: 2023-10-10 to 2023-10-12."

[0782] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0783] Step 1:

[0784] The server accesses the user's purchase history database and retrieves past purchase history data linked to the user ID. The input is the user ID, and the output is purchase history data (e.g., product name, quantity, purchase date and time). Specifically, it uses the Python requests library to retrieve the purchase history from the database and parses it in JSON format.

[0785] Step 2:

[0786] The server accesses the store's sales database and retrieves information about products currently on sale. The input is a database access request, and the output is sales information (e.g., product name, sale price, sale period). Specifically, the server uses the same Python requests library to retrieve data from the sales database and parse it in JSON format.

[0787] Step 3:

[0788] The server analyzes the purchase history data and estimates the items that are likely to still be in the user's refrigerator. The input is the acquired purchase history data, and the output is the estimated refrigerator inventory data. Specifically, it aggregates the data using the Pandas library and calculates the items still remaining in the refrigerator based on past purchase frequency.

[0789] Step 4:

[0790] The server generates a list of recommended products based on the acquired sale item information and estimated refrigerator inventory information. The input is sale item information and refrigerator inventory data, and the output is a list of recommended products. Specifically, it uses a generative AI model (e.g., TensorFlow or PyTorch) to learn the user's purchasing trends and generate a list of recommended products.

[0791] Step 5:

[0792] The server sends the generated recommended product list to the user's mobile device or an in-store display device. The input is the recommended product list, and the output is a specific message to be sent to the mobile device or display device. Specifically, the server uses Firebase Cloud Messaging (FCM) to send the notification.

[0793] Step 6:

[0794] The device receives the recommended product list and visually presents it to the user. The input is the recommended product list sent from the server, and the output is the list displayed to the user. Specifically, a push notification is displayed on the smartphone app, and the list is presented as "Today's Recommended Product List."

[0795] Step 7:

[0796] The server collects user-provided feedback data and fine-tunes the recommendation algorithm. The input is the user feedback data, and the output is the adjusted model of the algorithm. Specifically, it analyzes the feedback data and adjusts the learning parameters of the generative AI model.

[0797] Step 8:

[0798] The device provides guidance so that the user can navigate within the store to the sale items. The input is the user's location information and sale item information, and the output is navigation information to the sale items. Specifically, it uses the Google Maps API to display a map of the store and provides guidance on the shortest route.

[0799] 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.

[0800] The present invention relates to a system that recommends optimal products to individuals by combining a user's purchase history, sale item information, and an emotion engine that recognizes the user's emotions. This system includes a purchase history database, a sale item database, data analysis means, a recommended product generation means, information provision means, feedback collection means, and emotion recognition means.

[0801] Data Acquisition

[0802] Obtaining a user's purchase history

[0803] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. This data includes the date and time of each purchase, the purchased item, and the purchased quantity. For example, the user ID is "12345," the purchased items are "tomato, lettuce, chicken," and the purchase date and time is "2023-09-15 18:30."

[0804] Obtaining special sale information

[0805] The server retrieves information about products currently on sale from the store's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, the information might be "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[0806] Analyzing the data

[0807] Analysis of purchase history and estimation of refrigerator inventory

[0808] The server analyzes the acquired purchase history data and estimates which items may remain in the refrigerator based on the user's recent purchase frequency. For example, if an item has been purchased three or more times in the past two weeks, it is assumed that the item is likely to remain in the refrigerator. If the user has recently purchased tomatoes, lettuce, and chicken multiple times, it is assumed that these items remain in the refrigerator.

[0809] Generate recommended products

[0810] Generate recommended product lists based on sale items and refrigerator inventory

[0811] The server generates a list of recommended products for the user based on the sale product information and the estimated refrigerator inventory. From the sale products, it selects products to recommend preferentially based on the user's preferences and past purchase history. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, these will be included in the recommended product list.

[0812] emotion recognition

[0813] User Emotion Recognition

[0814] The device (mobile device) uses a camera and microphone to recognize the user's emotions. This information is sent to the server in real time. For example, if the user is tired or stressed, the device can sense their emotional state.

[0815] Adjusting product listings based on sentiment data

[0816] The server adjusts the recommended product list based on the user's emotional data. For example, if the user is feeling stressed, the server can prioritize products with a relaxing effect (such as herbal tea) in the list.

[0817] Providing information

[0818] Submit a recommended product list

[0819] The server sends the generated recommended product list to the user's mobile device or a display device in the store. The device (mobile device) receives this information and visually presents it to the user. For example, a smartphone app might display "Today's Recommended Product List" as "1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Croutons, etc."

[0820] Collecting feedback

[0821] Purchase History Updates and Feedback

[0822] When a user actually purchases a product, that information is automatically added to their purchase history. The server collects feedback data provided by the user (e.g., purchase history) and fine-tunes the recommendation algorithm, thereby improving the accuracy of future recommendations.

[0823] The above is an embodiment of the present invention. This system allows users to shop efficiently, maximize sales information, and receive optimal product recommendations based on their current emotional state.

[0824] The processing flow will be explained below.

[0825] Step 1: Get your purchase history

[0826] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. This data includes the date and time of each purchase, the purchased items, and the purchased quantities. Specifically, the information might be something like "User ID: 12345, Purchased items: Tomato, lettuce, chicken, Purchase date and time: 2023-09-15 18:30."

[0827] Step 2: Get sale information

[0828] The server retrieves information about products currently on sale from the store's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[0829] Step 3: Analyze your purchase history

[0830] The server analyzes the acquired purchase history data and estimates which items may remain in the refrigerator based on the user's recent purchase frequency. Specifically, it estimates that items that have been purchased three or more times in the last two weeks remain in the refrigerator. For example, if the user has recently purchased tomatoes, lettuce, and chicken multiple times, it estimates that these items remain in the refrigerator.

[0831] Step 4: Obtaining emotion data

[0832] The device (mobile device) uses a camera and microphone to recognize the user's emotions and transmits the data to a server. For example, if the user is tired or stressed, the device can detect that emotional state.

[0833] Step 5: Generate a list of recommended products

[0834] The server generates a list of recommended products based on the sale product information, estimated refrigerator inventory, and emotional data. From the sale products, it selects products to recommend based on the user's preferences and current emotional state. For example, if the user is tired, it prioritizes products with a relaxing effect (such as herbal tea) in the list.

[0835] Step 6: Submit your recommended products list

[0836] The server sends the generated recommended product list to the user's mobile device or to a display device in the store. The device (mobile device) receives this information and visually presents it to the user. Specifically, the smartphone app displays "Today's Recommended Product List" as follows: 1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Herbal Tea (Based on User Emotion Data)."

[0837] Step 7: Gather feedback

[0838] When a user actually purchases a product, that information is automatically added to their purchase history. The server collects feedback data provided by the user (e.g., purchase history) and fine-tunes the recommendation algorithm, thereby improving the accuracy of future product recommendations.

[0839] The above is the specific processing flow of the product recommendation system for users that combines an emotion engine. This enables users to receive optimal product recommendations based on their current emotional state, enabling them to shop efficiently.

[0840] Example 2

[0841] 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."

[0842] The present invention aims to provide an optimal product recommendation system that takes into account not only a user's purchase history and sale product information, but also the user's emotional state. Conventional recommendation systems generally rely on a user's preferences and purchase history, but there is a demand for more accurate product recommendations that meet the user's needs by taking the user's emotional state into account. Therefore, it is necessary to recognize the user's emotional state and adjust the product list based on that.

[0843] 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.

[0844] In this invention, the server includes means for acquiring a purchase history from a user's purchase history database, means for acquiring sale item information from a store's sale item database, means for analyzing the user's purchase history and estimating items that are likely to still be in the refrigerator, means for generating a list of recommended items for the user based on the acquired sale item information and the estimated refrigerator inventory information, means for transmitting the generated recommended item list to the user's mobile device or an in-store display device, means for recognizing the user's emotions and acquiring the data, means for adjusting the recommended item list based on the recognized emotion data, and means for collecting feedback data provided by the user and fine-tuning the recommendation algorithm, thereby enabling more accurate product recommendations that take the user's emotional state into consideration.

[0845] "Purchase history" is data containing information about products purchased by a user in the past, specifically including the purchase date and time, product name, and purchase quantity.

[0846] "Special sale product information" is data containing information about products that a store is offering at special prices, and specifically includes the names of the products on sale, the sale prices, the sale periods, and so on.

[0847] The "purchase history database" is a database for storing data on a user's past purchase history.

[0848] The "sales product database" is a database for storing information about sales products at a store.

[0849] "Refrigerator inventory" is a concept for estimating products that are likely to still be in a user's refrigerator, and is estimated based on the user's purchase history data.

[0850] The "recommended product list" is a list of products recommended to the user, and is generated based on sale product information, refrigerator inventory, and the user's emotional state.

[0851] A "user's mobile terminal" is an electronic device that a user carries and uses, such as a smartphone or tablet.

[0852] The "display device in the store" refers to a display device such as a display or monitor installed in the store.

[0853] "Emotion recognition" is a technology that uses devices such as cameras and microphones to detect a user's emotional state.

[0854] "Feedback data" is data provided by a user after purchasing a product, and includes purchase history, impressions, and the like.

[0855] A "recommendation algorithm" is an algorithm that recommends products based on a user's purchase history, sale information, emotional data, etc.

[0856] "Emotional state" indicates the type and intensity of the emotion the user is feeling, and includes fatigue, stress, happiness, and the like.

[0857] The present invention is a system that recommends optimal products to individuals by combining a user's purchase history, sale product information, and an engine that recognizes the user's emotions. This system includes a user purchase history database, a sale product database, data analysis means, a recommended product generation means, information provision means, feedback collection means, and emotion recognition means.

[0858] Data Acquisition

[0859] Obtaining a user's purchase history

[0860] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. This data includes the date and time of each purchase, the purchased item, and the purchased quantity. For example, the user ID is "12345," the purchased items are "tomato, lettuce, chicken," and the purchase date and time is "2023-09-15 18:30."

[0861] Obtaining special sale information

[0862] The server retrieves information about the products currently on sale from the store's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, the information might be "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[0863] Analyzing the data

[0864] Analysis of purchase history and estimation of refrigerator inventory

[0865] The server analyzes the acquired purchase history data and estimates which items may remain in the refrigerator based on the user's recent purchase frequency. For example, if a product has been purchased three or more times in the past two weeks, it is estimated that the item is likely to remain in the refrigerator. If the user has recently purchased tomatoes, lettuce, and chicken multiple times, it is estimated that these items remain in the refrigerator.

[0866] Generate recommended products

[0867] Generate recommended product lists based on sale items and refrigerator inventory

[0868] The server generates a list of recommended products for the user based on the sale product information and the estimated refrigerator inventory. From the sale products, it selects products to recommend preferentially based on the user's preferences and past purchase history. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, these will be included in the recommended product list.

[0869] emotion recognition

[0870] User Emotion Recognition

[0871] The device (mobile device) uses a camera and microphone to recognize the user's emotions. This information is sent to the server in real time. For example, if the user is tired or stressed, the device can sense their emotional state.

[0872] Adjusting product listings based on sentiment data

[0873] The server adjusts the recommended product list based on the user's emotional data. For example, if the user is feeling stressed, the server can prioritize products with a relaxing effect (such as herbal tea) in the list.

[0874] Providing information

[0875] Submit a recommended product list

[0876] The server sends the generated recommended product list to the user's mobile device or a display device in the store. The device (mobile device) receives this information and visually presents it to the user. For example, a smartphone app might display "Today's Recommended Product List" as "1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Croutons, etc."

[0877] Collecting feedback

[0878] Purchase History Updates and Feedback

[0879] When a user actually purchases a product, that information is automatically added to their purchase history. The server collects feedback data provided by the user (e.g., purchase history) and fine-tunes the recommendation algorithm, thereby improving the accuracy of future recommendations.

[0880] Examples of prompt statements

[0881] Below is an example of a prompt sentence for a generative AI model to recommend products based on a user's purchase history, sale information, and emotional data:

[0882] User ID: 12345

[0883] Recent purchase history: Tomato, lettuce, chicken (2023-09-15 18:30)

[0884] Special Offer:

[0885] 1. Tomato Sauce (Special Sale Period: 2023-10-10 to 2023-10-12)

[0886] 2. Cheese (Special Sale Period: 2023-10-10 to 2023-10-12)

[0887] User emotion data: Stress state (via emotion engine)

[0888] This enables more accurate product recommendations that take into account the user's emotional state.

[0889] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0890] Step 1:

[0891] The server receives the user ID as input and retrieves the user's purchase history data from the purchase history database. This data includes the date and time of each purchase, the purchased items, and the purchase quantity. Specifically, using the user ID "12345," it retrieves "Purchase date and time: 2023-09-15 18:30, purchased items: tomato, lettuce, chicken, purchase quantity: 1 each." The retrieved data is sent to the next analysis step.

[0892] Step 2:

[0893] The server uses the acquired purchase history data as input and applies an analysis algorithm to calculate the frequency of items recently purchased by the user. For example, items purchased three or more times in the past two weeks are estimated as refrigerator inventory. The output is estimated refrigerator inventory information; if "tomatoes, lettuce, and chicken" are included, they are estimated to be left in the refrigerator.

[0894] Step 3:

[0895] The server sends a query to the store's special sale database to retrieve information about the current sale items. The input is a query statement to the database, and the output is "Special sale item name: Tomato sauce, Special sale price: 200 yen, Special sale period: 2023-10-10 to 2023-10-12."

[0896] Step 4:

[0897] The server combines the sale product information and estimated refrigerator inventory information as input, and generates a list of recommended products based on the user's preferences and purchase history. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, the server prioritizes tomato sauce and cheese. The output is the generated list of recommended products.

[0898] Step 5:

[0899] The device (mobile device) captures the user's facial expressions and voice data using a camera and microphone, and inputs this data into an emotion recognition engine. The engine analyzes this data and recognizes the user's emotional state (e.g., stress level). The output is real-time emotion data, which is sent to a server.

[0900] Step 6:

[0901] The server adjusts the recommended product list based on the emotional data sent by the user. For example, if the user is under stress, it adds relaxing herbal tea to the list. This adjustment generates a final recommended product list that reflects the emotional data.

[0902] Step 7:

[0903] The server sends the generated recommended product list to the user's mobile device or a display device in the store. The device (mobile device) receives this information and visually presents it to the user. For example, a smartphone app might display "Today's Recommended Product List" as "1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Herbal Tea (Reflecting Emotional Data)."

[0904] Step 8:

[0905] When a user makes a purchase, that information is automatically added to the purchase history database, and the server collects this new purchase history data. The server also uses the feedback data provided by the user to fine-tune the recommendation algorithm, which improves the accuracy of future recommendations.

[0906] (Application example 2)

[0907] 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."

[0908] Today's consumers are extremely busy and need assistance in efficiently purchasing daily necessities and food. Furthermore, a system that allows users to purchase items without missing out on special offers would respond to consumers' desire to save money. However, conventional recommendation systems have difficulty recommending optimal products because they do not fully consider users' emotions or individual purchasing habits. Furthermore, providing information in real time is crucial to effectively take advantage of special offers in the market.

[0909] 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.

[0910] In this invention, the server includes means for acquiring a purchase history from a purchase history database of the user, means for acquiring sale item information from a sale item database of the commercial facility, means for analyzing the user's purchase history and estimating items that are likely to still be in the refrigerator, means for generating a list of recommended items for the user based on the acquired sale item information and the estimated refrigerator inventory information, means for transmitting the generated recommended item list to the user's mobile terminal or a display device in the commercial facility, means for collecting feedback data provided by the user and fine-tuning a recommendation algorithm, emotion recognition means for collecting user emotion data, and means for adjusting the recommended item list based on the emotion data. This makes it possible to quickly and accurately recommend optimal products based on the user's emotional state and individual purchasing characteristics while effectively utilizing sale information.

[0911] The "user purchase history database" is an accessible database that records the history of products that a user has purchased in the past.

[0912] A "sales product database" is a database that records and provides access to information about products on sale at commercial facilities.

[0913] The "emotion recognition means" is a means for recognizing the user's emotions using sensors such as a camera or microphone, and acquiring that information.

[0914] The "means for acquiring purchase history" is a means for accessing a purchase history database of a user and acquiring information on products that the user has purchased in the past.

[0915] The "means for acquiring sale item information" refers to a means for accessing a sale item database and acquiring information about items on sale at commercial facilities.

[0916] The "means for analyzing purchase history" is a means for analyzing the user's purchasing patterns based on the acquired purchase history and estimating items that are likely to remain in the refrigerator.

[0917] The "means for generating a recommended product list" is a means for creating an optimal product list for a user based on sale product information and estimated refrigerator inventory information.

[0918] The "means for transmitting a recommended product list" is a means for transmitting the generated recommended product list to a user's mobile terminal or a display device in a commercial facility.

[0919] "Means for collecting feedback data" refers to means for collecting post-purchase opinions and purchase information provided by users and using them to improve recommendation algorithms.

[0920] The "means for adjusting the recommended product list based on emotion data" refers to a means for adjusting the contents of the recommended product list based on the user's emotion data acquired by the emotion recognition means, and recommending optimal products to the user.

[0921] This invention relates to a system that recommends optimal products to individuals by combining a user's purchase history, sale item information, and an emotion engine that recognizes the user's emotions. The main elements are a purchase history database, a sale item database, data analysis means, a recommended product generation means, information provision means, feedback collection means, and emotion recognition means.

[0922] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. This data includes the date and time of each purchase, the purchased item, and the purchased quantity. For example, the user ID is "12345," the purchased items are "tomato, lettuce, chicken," and the purchase date and time is "2023-09-15 18:30."

[0923] Next, the server retrieves information about products currently on sale from the commercial facility's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[0924] Based on this, the server analyzes the purchase history data and estimates which items may remain in the refrigerator based on the user's recent purchase frequency. For example, if an item has been purchased three or more times in the past two weeks, it is assumed that the item is likely to remain in the refrigerator. If the user has recently purchased tomatoes, lettuce, and chicken multiple times, it is assumed that these items remain in the refrigerator.

[0925] Based on the estimated refrigerator inventory, the server compares it with sale item information to generate a list of recommended items. From the sale items, it selects items to recommend preferentially based on the user's preferences and past purchase history. For example, tomato sauce and cheese are on sale, and the user frequently purchases tomatoes, so these are included in the recommended items list.

[0926] Furthermore, the mobile device uses a camera and microphone to recognize the user's emotions in real time, and this information is sent to a server to measure the user's emotional state, for example, if they are tired or stressed.

[0927] The server adjusts the recommended product list based on the user's emotional data. For example, if the user is feeling stressed, the server can prioritize products with a relaxing effect (such as herbal tea) in the list.

[0928] The generated recommended product list is sent from the server to the user's mobile device or to a display device within the commercial facility. The mobile device receives this information and visually presents it to the user. For example, a smartphone app might display "Today's Recommended Product List" as "1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Croutons, etc."

[0929] Finally, when a user actually purchases a product, that information is automatically added to their purchase history. The server collects the feedback data provided by the user (e.g., purchase history) and fine-tunes the recommendation algorithm, thereby improving the accuracy of future recommendations.

[0930] For example and prompt purposes, we will use the following information as input:

[0931] Specific prompt examples:

[0932] User ID: 12345

[0933] Purchase History API URL: http: / / example.com / api / purchase_history

[0934] Special Offers API URL: http: / / example.com / api / special_offers

[0935] Recommendation API URL: http: / / example.com / api / recommendation

[0936] Emotion: stressed

[0937] Generate a list of recommended products

[0938] As a result, users can shop efficiently, make the most of sale information, and receive optimal product recommendations based on their emotions. This system simultaneously satisfies consumers' desire for savings and convenience, and is expected to improve customer satisfaction in commercial facilities.

[0939] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0940] Step 1:

[0941] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. The input is the user ID and the output is the purchase history data. This data includes the date and time of each purchase, the purchased item, and the purchased quantity. Specifically, it sends a request to the API endpoint and retrieves the purchase history data as a response.

[0942] Step 2:

[0943] The server retrieves information about products currently on sale from the commercial facility's sale product database. The input is the API URL of the sale product database, and the output is the sale product information. This information includes the name of the sale product, the sale price, and the sale period. Specifically, it sends a request to the API endpoint and retrieves the sale product data as a response.

[0944] Step 3:

[0945] The server analyzes the acquired purchase history data and estimates which items may remain in the refrigerator based on the user's most recent purchase frequency. The input is the purchase history data, and the output is a list of items estimated to remain in the refrigerator. Specifically, it calculates the purchase frequency of each product and lists items that have been frequently purchased within a certain period of time.

[0946] Step 4:

[0947] The server collects the user's emotional data through an emotion recognition means. The input is the user's real-time video and audio data, and the output is the judged emotional data. Specifically, it analyzes the data input from the camera and microphone and identifies the emotion using a generative AI model.

[0948] Step 5:

[0949] The server generates a recommended product list based on the acquired sale product information, estimated refrigerator inventory information, and emotional data. The inputs are sale product information, refrigerator inventory information, and emotional data, and the output is a recommended product list. Specifically, the server selects products from the sale products that match the user's preferences and emotional state, and generates the list.

[0950] Step 6:

[0951] The server then sends the generated recommended product list to the user's mobile device or a display device within the commercial facility. The input is the recommended product list, and the output is the information displayed on the user's device or display device. Specifically, the list is sent to the device so that the user can visually confirm it.

[0952] Step 7:

[0953] When a user actually purchases a product, the purchase information is added to the purchase history. The input is the information about the purchased product, and the output is an updated purchase history database. Specifically, the purchase information is added to the database, and the server keeps the data as up-to-date.

[0954] Step 8:

[0955] The server collects post-purchase feedback data and fine-tunes the recommendation algorithm. The input is the feedback data provided by the user, and the output is an improved recommendation algorithm. Specifically, the server analyzes the collected feedback and adjusts the algorithm parameters.

[0956] 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.

[0957] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0958] In the above embodiment, an example 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.

[0959] [Fourth embodiment]

[0960] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0961] 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.

[0962] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0963] The 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.

[0964] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0965] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

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

[0967] 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.

[0968] 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.

[0969] 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.

[0970] 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.

[0971] 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.

[0972] 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."

[0973] The present invention relates to a system that combines a user's purchase history and sale item information to individually recommend optimal products. This system includes a purchase history database, a sale item database, data analysis means, a recommended product generation means, an information provision means, and a feedback collection means.

[0974] Data Acquisition

[0975] Obtaining a user's purchase history

[0976] The server accesses the purchase history database linked to the user ID and retrieves past purchase history data. This data includes the names and quantities of products purchased in the past, as well as the purchase dates and times. For example, the information might be "User ID: 12345, Purchased items: Tomato, lettuce, chicken, Purchase date and time: 2023-09-15 18:30."

[0977] Obtaining special sale information

[0978] The server retrieves information about products currently on sale from the store's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[0979] Analyzing the data

[0980] Analysis of purchase history and estimation of refrigerator inventory

[0981] The server estimates which items are likely to remain in the user's refrigerator based on the acquired purchase history. For example, if a user has purchased tomatoes, lettuce, and chicken three times in the last two weeks, the server estimates that these items are likely to remain in the refrigerator.

[0982] Generate recommended products

[0983] Generate recommended product lists based on sale items and refrigerator inventory

[0984] The server generates a list of recommended products that are optimal for the user based on the acquired sale item information and estimated refrigerator inventory information. Among the sale items, it prioritizes and recommends items that match the user's past purchase history and preferences. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, it determines that these items are suitable.

[0985] Providing information

[0986] Submit a recommended product list

[0987] The server sends the generated recommended product list to the user's mobile device or a display device in the store. The device (mobile device) receives this information and visually presents it to the user. Specifically, a "Today's Recommended Product List" is displayed on the smartphone app via push notification. For example, "Recommended Product List: 1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Croutons, etc."

[0988] Collecting feedback

[0989] Purchase History Updates and Feedback

[0990] When a user actually purchases a product, that information is automatically added to their purchase history. The server collects the feedback data provided by the user and fine-tunes the recommendation algorithm, which can then provide even better recommendations to the user in the future.

[0991] The above is an embodiment of the present invention. This system allows users to shop efficiently, avoid missing out on needed products, and make the most of sales information.

[0992] The processing flow will be explained below.

[0993] Step 1: Get the data

[0994] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. This data includes the date and time of each purchase, the purchased item, and the purchased quantity. For example, the user ID is "12345," the purchased items are "tomato, lettuce, chicken," and the purchase date and time is "2023-09-15 18:30."

[0995] Step 2: Get sale information

[0996] The server retrieves information about products currently on sale from the store's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, the information might be "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[0997] Step 3: Analyze your purchase history

[0998] The server analyzes the acquired purchase history data and estimates which items may remain in the refrigerator based on the user's recent purchase frequency. For example, if an item has been purchased three or more times in the past two weeks, it is assumed that the item is likely to remain in the refrigerator. If the user has recently purchased tomatoes, lettuce, and chicken multiple times, it is assumed that these items remain in the refrigerator.

[0999] Step 4: Generate a list of recommended products

[1000] The server generates a list of recommended products for the user based on the sale product information and the estimated refrigerator inventory. From the sale products, it selects products to recommend preferentially based on the user's preferences and past purchase history. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, these will be included in the recommended product list.

[1001] Step 5: Submit your recommended products list

[1002] The server sends the generated recommended product list to the user's mobile device or a display device in the store. The device (mobile device) receives this information and visually presents it to the user. For example, a smartphone app might display "Today's Recommended Product List" as "1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Croutons, etc."

[1003] Step 6: Gather feedback

[1004] When a user actually purchases a product, that information is automatically added to their purchase history. The server collects feedback data provided by the user (e.g., purchase history) and fine-tunes the recommendation algorithm, thereby improving the accuracy of future recommendations.

[1005] These are the specific processing steps that allow users to shop efficiently and take full advantage of sales information.

[1006] Example 1

[1007] 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."

[1008] Conventional recommendation systems recommend products based solely on a user's purchasing history, which makes it difficult to fully consider the user's recent purchasing behavior or sales information, making it difficult to recommend appropriate products in a timely manner. Furthermore, they have low accuracy in identifying products that are likely to interest users, which prevents them from fully motivating users to purchase. Furthermore, the mechanisms for efficiently collecting user feedback and incorporating it into the recommendation algorithm are insufficient, leaving a need for an improved user experience. Therefore, there is a need for a system that can combine a user's purchasing history, sales information, and feedback to make more accurate product recommendations.

[1009] 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.

[1010] In this invention, the server includes means for acquiring a purchase history from a purchase history data storage acquired based on a user identifier, means for acquiring sale item information from a retailer's sale item data storage, means for analyzing the purchase history and estimating items that are likely to still be stored in the refrigerator, means for generating an optimal recommended product list for the user based on the acquired sale item information and the estimated refrigerator inventory information, means for transmitting the generated recommended product list to the user's mobile communication terminal or an in-store display device, and means for collecting evaluation data provided by the user and adjusting the recommendation algorithm. This makes it possible to integrate the user's purchase history, sale information, and feedback to make more accurate and timely product recommendations.

[1011] A "user identifier" is unique information used to identify a specific user, such as an ID or account number.

[1012] "Purchase history data storage" is data storage that stores information about products purchased by users in the past, including product names, quantities, purchase dates, and so on.

[1013] "Sale product data storage" is a data storage that stores information about products on sale at a retail store, including the name, price, and sale period of the sale product.

[1014] "Refrigeration equipment" refers to equipment used to store food and other items at low temperatures. Generally, this includes refrigerators and freezers.

[1015] A "recommended product list" is a list of products recommended to a user. It is generated based on the user's purchase history and special sale information.

[1016] A "mobile communication terminal" is a communication device that can be carried and used by a user. This includes smartphones and tablet terminals.

[1017] "In-store display devices" are devices installed in stores to display information. These include digital signage and information display screens.

[1018] "Evaluation data" refers to data related to evaluations of products provided by users, including product ratings and feedback.

[1019] A "recommendation algorithm" is a set of calculation procedures and rules for recommending optimal products to users. The algorithm operates based on purchase history and sale information.

[1020] The present invention is a system for recommending optimal products to individual users by utilizing their purchasing history and sale product information. This system is implemented mainly by a server, a terminal, and a user.

[1021] The server accesses multiple databases to retrieve the user's purchase history data and sale item data. Based on the user identifier, the server issues a query to the purchase history data storage to retrieve information such as the name, quantity, and purchase date and time of items previously purchased by the user. The server then accesses the retailer's sale item data storage to retrieve information such as the name, sale price, and sale period of the sale item.

[1022] The server analyzes the acquired purchase history data and estimates which items are likely to still be stored in the refrigerator. This analysis takes into account factors such as the user's recent purchase frequency. For example, if a user has purchased tomatoes, lettuce, and chicken three times in the last two weeks, it estimates that these items are likely to remain in the refrigerator.

[1023] Next, the server generates a list of recommended products that are optimal for the user based on the acquired sale product information and estimated cooling equipment inventory information. This list prioritizes and recommends products that match the user's past purchase history and preferences from among the sale products. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, these products will be included in the recommended product list.

[1024] The generated recommended product list is sent from the server to the user's mobile communication device or to a display device in the store. The device receives this information and visually presents it to the user. Specifically, the "Today's Recommended Product List" is displayed via push notification on the user's smartphone app. For example, the recommended product list might be: 1. Tomato sauce (on sale) 2. Cheese (on sale) 3. Croutons.

[1025] When a user actually purchases a product, that information is automatically added to the purchase history. The server collects the user's rating data and adjusts the recommendation algorithm, thereby further improving the accuracy of the product recommendations provided to the user in the future.

[1026] Examples and prompts

[1027] Examples:

[1028] If a user has purchased tomatoes three times and lettuce twice in the last two weeks, the server will infer that these items are likely to remain in the refrigerator.

[1029] The server generates a list of recommended products because "tomato sauce" and "cheese" are on sale and these products match the user's purchase history.

[1030] Display the following recommended product list on your device: 1. Tomato sauce (on sale) 2. Cheese (on sale) 3. Croutons.

[1031] Example prompt:

[1032] 1. "How can I estimate the inventory in a cooling device based on a user's purchasing history?"

[1033] 2. "Explain how to generate a list of recommended products by combining special offers and user preferences."

[1034] 3. "Please give me a concrete example of how a list of recommended products can be displayed on a user's mobile device."

[1035] The above is an embodiment of the present invention. This system allows users to shop efficiently, avoid missing out on needed products, and make the most of sales information.

[1036] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1037] Step 1:

[1038] Obtaining a user's purchase history

[1039] The server accesses the purchase history data storage based on the user identifier. The server retrieves the user's past purchase history using a database query. For example, it executes the SQL query "SELECT product name, quantity, purchase date and time FROM purchase history WHERE user ID = '12345'".

[1040] Input: User Identifier

[1041] Output: Purchase history data (e.g., "User ID: 12345, Purchased items: Tomato, lettuce, chicken, Purchase date and time: 2023-09-15 18:30")

[1042] Step 2:

[1043] Obtaining special sale information

[1044] The server accesses the retailer's sales data storage and retrieves information about products currently on sale. The server retrieves the sales information using a database query. For example, it executes the SQL query "SELECT product name, sale price, sale period FROM sale product WHERE current_date BETWEEN start_date AND end_date."

[1045] Input: Current date

[1046] Output: Special sale item data (e.g. "Special sale items: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12")

[1047] Step 3:

[1048] Analysis of purchase history and estimation of cooling equipment inventory

[1049] The server uses the acquired purchase history data to estimate which items are likely to still be stored in the refrigerator. This analysis takes into account the user's recent purchase frequency and purchase date and time. For example, if a user has purchased tomatoes, lettuce, and chicken three times in the last two weeks, it estimates that these items are likely to remain in the refrigerator.

[1050] Input: Purchase history data (output from Step 1)

[1051] Output: Estimated cooling equipment inventory (e.g., "Tomatoes, Lettuce, Chicken")

[1052] Step 4:

[1053] Generate recommended products

[1054] The server generates a list of recommended products for the user based on the sale product information and estimated cooling equipment inventory. This list prioritizes products that match the user's past purchase history and preferences.

[1055] Input: Sale item data (output of Step 2) and estimated cooling equipment inventory (output of Step 3)

[1056] Output: Recommended product list (e.g. "Recommended product list: 1. Tomato sauce (on sale) 2. Cheese (on sale) 3. Croutons")

[1057] Step 5:

[1058] Submit a recommended product list

[1059] The server then sends the generated recommended product list to the user's mobile communication device or to a display device in the store. The server then formats the data in JSON format and sends it as a POST request to the API endpoint.

[1060] Input: Recommended product list (output of step 4)

[1061] Output: A recommendation notification delivered to the user's device (e.g., "Recommended product list: 1. Tomato sauce (on sale) 2. Cheese (on sale) 3. Croutons")

[1062] Step 6:

[1063] Gathering feedback and adjusting recommendation algorithms

[1064] When a user actually purchases a product, that information is automatically added to the purchase history. The server collects user evaluation data and adjusts the recommendation algorithm, thereby improving the accuracy of the recommended products provided next time.

[1065] Input: User rating data and new purchase history (user purchase information)

[1066] Output: A fine-tuned recommendation algorithm

[1067] The above is the specific processing flow of the system.

[1068] (Application example 1)

[1069] 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."

[1070] Conventional purchasing support systems are limited to recommending products based on a user's purchase history, and are unable to optimally utilize sale items. Furthermore, they lack a means for users to efficiently search for sale items within a store, reducing the convenience of shopping. Furthermore, there are limited ways to improve the accuracy of recommendations using feedback, making it difficult to improve user satisfaction. A comprehensive solution to these issues was needed.

[1071] 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.

[1072] In this invention, the server includes means for acquiring a purchase history from a user's purchase history database, means for acquiring sale item information from a store's sale item database, means for analyzing the user's purchase history and estimating items that are likely to still be in the refrigerator, means for generating a list of recommended items for the user based on the acquired sale item information and the estimated refrigerator inventory information, means for transmitting the generated recommended item list to the user's mobile device or an in-store display device, means for collecting feedback data provided by the user and fine-tuning the recommendation algorithm, and means for guiding the user to navigate within the store to the sale items. This enables efficient shopping by making the most of sale information and can improve the user's overall purchasing experience.

[1073] The "user purchase history database" is an information management system for storing information on products purchased by a user in the past.

[1074] The "sale item database" is an information management system for storing information about items currently on sale at a store.

[1075] The "means for acquiring purchase history" refers to a method or system for accessing a user's purchase history database and acquiring past purchase information.

[1076] The "means for acquiring sale item information" refers to a method or system for accessing a sale item database and acquiring information on items currently on sale.

[1077] A "means for analyzing purchase history" is a method or system for analyzing a user's purchase history data and identifying specific purchasing trends or patterns.

[1078] The "means for estimating items that are likely to still be in the refrigerator" refers to a method or system for estimating products that are likely to currently be in stock in the user's refrigerator based on the user's purchase history.

[1079] The "means for generating a recommended product list" is a method or system for creating a list that recommends the most suitable products to the user based on the acquired sale product information and estimated refrigerator inventory information.

[1080] A "mobile device" is a device that a user can carry and use, such as a smartphone or tablet.

[1081] An "in-store display device" is a device that is installed in a store and displays information to users.

[1082] A "means for collecting feedback data" is a method or system for collecting user-provided ratings and opinions to improve the performance of the system.

[1083] A "means for fine-tuning recommendation algorithms" is a method or system for improving the performance of recommendation algorithms based on collected feedback data.

[1084] A "navigation guidance means" is a method or system that provides location information and route guidance to help users find special sale items within a store.

[1085] This invention relates to a system that combines a user's purchase history with sale item information to individually recommend optimal products. The system includes a purchase history database, a sale item database, data analysis means, a recommended product generation means, an information provision means, and a feedback collection means.

[1086] The server first accesses the user's purchase history database and retrieves past purchase history data linked to the user ID. This data includes the names and quantities of products the user has previously purchased, as well as the purchase dates and times. Next, the server retrieves information about products currently on sale from the store's sales product database. This information includes the names of the products on sale, the sale prices, and the sale periods.

[1087] The server estimates which items are likely to remain in the user's refrigerator based on the acquired purchase history data. For example, if a specific item has been purchased several times in the past two weeks, it can estimate that the item is likely to remain in the refrigerator. The estimated refrigerator inventory information is combined with the acquired sale item information to generate a list of recommended products that are optimal for the user.

[1088] The generated recommended product list is sent from the server to the user's mobile device (smartphone or tablet) or to a display device in the store. This information is displayed on the mobile device via push notification, providing a visual presentation to the user. For example, a "Today's Recommended Products List" may be displayed on a smartphone app. Furthermore, the system also has a function to navigate the user to specific sale items within the store, allowing users to efficiently find sale items.

[1089] Additionally, when a user actually purchases a product, that information is automatically added to the purchase history. The server collects feedback data provided by the user and fine-tunes the recommendation algorithm to improve the accuracy of product recommendations for future users.

[1090] For example, when a user opens an application, they receive a push notification that reads: "Today's featured items: 1. Tomato Sauce (On Sale) 2. Cheese (On Sale). Please use the in-app navigation feature to find special offers on the store map."

[1091] For example, you can use the following prompts for your generative AI model:

[1092] "Generate the best recommended product list based on the user's purchase history and special sale information. As an example, consider the following purchase history and special sale information: User ID: 12345, Purchased items: Tomato, lettuce, chicken, Purchase date and time: 2023-09-15 18:30, Special sale items: Tomato sauce, cheese, Sale period: 2023-10-10 to 2023-10-12."

[1093] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1094] Step 1:

[1095] The server accesses the user's purchase history database and retrieves past purchase history data linked to the user ID. The input is the user ID, and the output is purchase history data (e.g., product name, quantity, purchase date and time). Specifically, it uses the Python requests library to retrieve the purchase history from the database and parses it in JSON format.

[1096] Step 2:

[1097] The server accesses the store's sales database and retrieves information about products currently on sale. The input is a database access request, and the output is sales information (e.g., product name, sale price, sale period). Specifically, the server uses the same Python requests library to retrieve data from the sales database and parse it in JSON format.

[1098] Step 3:

[1099] The server analyzes the purchase history data and estimates the items that are likely to still be in the user's refrigerator. The input is the acquired purchase history data, and the output is the estimated refrigerator inventory data. Specifically, it aggregates the data using the Pandas library and calculates the items still remaining in the refrigerator based on past purchase frequency.

[1100] Step 4:

[1101] The server generates a list of recommended products based on the acquired sale item information and estimated refrigerator inventory information. The input is sale item information and refrigerator inventory data, and the output is a list of recommended products. Specifically, it uses a generative AI model (e.g., TensorFlow or PyTorch) to learn the user's purchasing trends and generate a list of recommended products.

[1102] Step 5:

[1103] The server sends the generated recommended product list to the user's mobile device or an in-store display device. The input is the recommended product list, and the output is a specific message to be sent to the mobile device or display device. Specifically, the server uses Firebase Cloud Messaging (FCM) to send the notification.

[1104] Step 6:

[1105] The device receives the recommended product list and visually presents it to the user. The input is the recommended product list sent from the server, and the output is the list displayed to the user. Specifically, a push notification is displayed on the smartphone app, and the list is presented as "Today's Recommended Product List."

[1106] Step 7:

[1107] The server collects user-provided feedback data and fine-tunes the recommendation algorithm. The input is the user feedback data, and the output is the adjusted model of the algorithm. Specifically, it analyzes the feedback data and adjusts the learning parameters of the generative AI model.

[1108] Step 8:

[1109] The device provides guidance so that the user can navigate within the store to the sale items. The input is the user's location information and sale item information, and the output is navigation information to the sale items. Specifically, it uses the Google Maps API to display a map of the store and provides guidance on the shortest route.

[1110] 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.

[1111] The present invention relates to a system that recommends optimal products to individuals by combining a user's purchase history, sale item information, and an emotion engine that recognizes the user's emotions. This system includes a purchase history database, a sale item database, data analysis means, a recommended product generation means, information provision means, feedback collection means, and emotion recognition means.

[1112] Data Acquisition

[1113] Obtaining a user's purchase history

[1114] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. This data includes the date and time of each purchase, the purchased item, and the purchased quantity. For example, the user ID is "12345," the purchased items are "tomato, lettuce, chicken," and the purchase date and time is "2023-09-15 18:30."

[1115] Obtaining special sale information

[1116] The server retrieves information about products currently on sale from the store's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, the information might be "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[1117] Analyzing the data

[1118] Analysis of purchase history and estimation of refrigerator inventory

[1119] The server analyzes the acquired purchase history data and estimates which items may remain in the refrigerator based on the user's recent purchase frequency. For example, if an item has been purchased three or more times in the past two weeks, it is assumed that the item is likely to remain in the refrigerator. If the user has recently purchased tomatoes, lettuce, and chicken multiple times, it is assumed that these items remain in the refrigerator.

[1120] Generate recommended products

[1121] Generate recommended product lists based on sale items and refrigerator inventory

[1122] The server generates a list of recommended products for the user based on the sale product information and the estimated refrigerator inventory. From the sale products, it selects products to recommend preferentially based on the user's preferences and past purchase history. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, these will be included in the recommended product list.

[1123] emotion recognition

[1124] User Emotion Recognition

[1125] The device (mobile device) uses a camera and microphone to recognize the user's emotions. This information is sent to the server in real time. For example, if the user is tired or stressed, the device can sense their emotional state.

[1126] Adjusting product listings based on sentiment data

[1127] The server adjusts the recommended product list based on the user's emotional data. For example, if the user is feeling stressed, the server can prioritize products with a relaxing effect (such as herbal tea) in the list.

[1128] Providing information

[1129] Submit a recommended product list

[1130] The server sends the generated recommended product list to the user's mobile device or a display device in the store. The device (mobile device) receives this information and visually presents it to the user. For example, a smartphone app might display "Today's Recommended Product List" as "1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Croutons, etc."

[1131] Collecting feedback

[1132] Purchase History Updates and Feedback

[1133] When a user actually purchases a product, that information is automatically added to their purchase history. The server collects feedback data provided by the user (e.g., purchase history) and fine-tunes the recommendation algorithm, thereby improving the accuracy of future recommendations.

[1134] The above is an embodiment of the present invention. This system allows users to shop efficiently, maximize sales information, and receive optimal product recommendations based on their current emotional state.

[1135] The processing flow will be explained below.

[1136] Step 1: Get your purchase history

[1137] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. This data includes the date and time of each purchase, the purchased items, and the purchased quantities. Specifically, the information might be something like "User ID: 12345, Purchased items: Tomato, lettuce, chicken, Purchase date and time: 2023-09-15 18:30."

[1138] Step 2: Get sale information

[1139] The server retrieves information about products currently on sale from the store's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[1140] Step 3: Analyze your purchase history

[1141] The server analyzes the acquired purchase history data and estimates which items may remain in the refrigerator based on the user's recent purchase frequency. Specifically, it estimates that items that have been purchased three or more times in the last two weeks remain in the refrigerator. For example, if the user has recently purchased tomatoes, lettuce, and chicken multiple times, it estimates that these items remain in the refrigerator.

[1142] Step 4: Obtaining emotion data

[1143] The device (mobile device) uses a camera and microphone to recognize the user's emotions and transmits the data to a server. For example, if the user is tired or stressed, the device can detect that emotional state.

[1144] Step 5: Generate a list of recommended products

[1145] The server generates a list of recommended products based on the sale product information, estimated refrigerator inventory, and emotional data. From the sale products, it selects products to recommend based on the user's preferences and current emotional state. For example, if the user is tired, it prioritizes products with a relaxing effect (such as herbal tea) in the list.

[1146] Step 6: Submit your recommended products list

[1147] The server sends the generated recommended product list to the user's mobile device or to a display device in the store. The device (mobile device) receives this information and visually presents it to the user. Specifically, the smartphone app displays "Today's Recommended Product List" as follows: 1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Herbal Tea (Based on User Emotion Data)."

[1148] Step 7: Gather feedback

[1149] When a user actually purchases a product, that information is automatically added to their purchase history. The server collects feedback data provided by the user (e.g., purchase history) and fine-tunes the recommendation algorithm, thereby improving the accuracy of future product recommendations.

[1150] The above is the specific processing flow of the product recommendation system for users that combines an emotion engine. This enables users to receive optimal product recommendations based on their current emotional state, enabling them to shop efficiently.

[1151] Example 2

[1152] 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."

[1153] The present invention aims to provide an optimal product recommendation system that takes into account not only a user's purchase history and sale product information, but also the user's emotional state. Conventional recommendation systems generally rely on a user's preferences and purchase history, but there is a demand for more accurate product recommendations that meet the user's needs by taking the user's emotional state into account. Therefore, it is necessary to recognize the user's emotional state and adjust the product list based on that.

[1154] 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.

[1155] In this invention, the server includes means for acquiring a purchase history from a user's purchase history database, means for acquiring sale item information from a store's sale item database, means for analyzing the user's purchase history and estimating items that are likely to still be in the refrigerator, means for generating a list of recommended items for the user based on the acquired sale item information and the estimated refrigerator inventory information, means for transmitting the generated recommended item list to the user's mobile device or an in-store display device, means for recognizing the user's emotions and acquiring the data, means for adjusting the recommended item list based on the recognized emotion data, and means for collecting feedback data provided by the user and fine-tuning the recommendation algorithm, thereby enabling more accurate product recommendations that take the user's emotional state into consideration.

[1156] "Purchase history" is data containing information about products purchased by a user in the past, specifically including the purchase date and time, product name, and purchase quantity.

[1157] "Special sale product information" is data containing information about products that a store is offering at special prices, and specifically includes the names of the products on sale, the sale prices, the sale periods, and so on.

[1158] The "purchase history database" is a database for storing data on a user's past purchase history.

[1159] The "sales product database" is a database for storing information about sales products at a store.

[1160] "Refrigerator inventory" is a concept for estimating products that are likely to still be in a user's refrigerator, and is estimated based on the user's purchase history data.

[1161] The "recommended product list" is a list of products recommended to the user, and is generated based on sale product information, refrigerator inventory, and the user's emotional state.

[1162] A "user's mobile terminal" is an electronic device that a user carries and uses, such as a smartphone or tablet.

[1163] The "display device in the store" refers to a display device such as a display or monitor installed in the store.

[1164] "Emotion recognition" is a technology that uses devices such as cameras and microphones to detect a user's emotional state.

[1165] "Feedback data" is data provided by a user after purchasing a product, and includes purchase history, impressions, and the like.

[1166] A "recommendation algorithm" is an algorithm that recommends products based on a user's purchase history, sale information, emotional data, etc.

[1167] "Emotional state" indicates the type and intensity of the emotion the user is feeling, and includes fatigue, stress, happiness, and the like.

[1168] The present invention is a system that recommends optimal products to individuals by combining a user's purchase history, sale product information, and an engine that recognizes the user's emotions. This system includes a user purchase history database, a sale product database, data analysis means, a recommended product generation means, information provision means, feedback collection means, and emotion recognition means.

[1169] Data Acquisition

[1170] Obtaining a user's purchase history

[1171] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. This data includes the date and time of each purchase, the purchased item, and the purchased quantity. For example, the user ID is "12345," the purchased items are "tomato, lettuce, chicken," and the purchase date and time is "2023-09-15 18:30."

[1172] Obtaining special sale information

[1173] The server retrieves information about the products currently on sale from the store's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, the information might be "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[1174] Analyzing the data

[1175] Analysis of purchase history and estimation of refrigerator inventory

[1176] The server analyzes the acquired purchase history data and estimates which items may remain in the refrigerator based on the user's recent purchase frequency. For example, if a product has been purchased three or more times in the past two weeks, it is estimated that the item is likely to remain in the refrigerator. If the user has recently purchased tomatoes, lettuce, and chicken multiple times, it is estimated that these items remain in the refrigerator.

[1177] Generate recommended products

[1178] Generate recommended product lists based on sale items and refrigerator inventory

[1179] The server generates a list of recommended products for the user based on the sale product information and the estimated refrigerator inventory. From the sale products, it selects products to recommend preferentially based on the user's preferences and past purchase history. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, these will be included in the recommended product list.

[1180] emotion recognition

[1181] User Emotion Recognition

[1182] The device (mobile device) uses a camera and microphone to recognize the user's emotions. This information is sent to the server in real time. For example, if the user is tired or stressed, the device can sense their emotional state.

[1183] Adjusting product listings based on sentiment data

[1184] The server adjusts the recommended product list based on the user's emotional data. For example, if the user is feeling stressed, the server can prioritize products with a relaxing effect (such as herbal tea) in the list.

[1185] Providing information

[1186] Submit a recommended product list

[1187] The server sends the generated recommended product list to the user's mobile device or a display device in the store. The device (mobile device) receives this information and visually presents it to the user. For example, a smartphone app might display "Today's Recommended Product List" as "1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Croutons, etc."

[1188] Collecting feedback

[1189] Purchase History Updates and Feedback

[1190] When a user actually purchases a product, that information is automatically added to their purchase history. The server collects feedback data provided by the user (e.g., purchase history) and fine-tunes the recommendation algorithm, thereby improving the accuracy of future recommendations.

[1191] Examples of prompt statements

[1192] Below is an example of a prompt sentence for a generative AI model to recommend products based on a user's purchase history, sale information, and emotional data:

[1193] User ID: 12345

[1194] Recent purchase history: Tomato, lettuce, chicken (2023-09-15 18:30)

[1195] Special Offer:

[1196] 1. Tomato Sauce (Special Sale Period: 2023-10-10 to 2023-10-12)

[1197] 2. Cheese (Special Sale Period: 2023-10-10 to 2023-10-12)

[1198] User emotion data: Stress state (via emotion engine)

[1199] This enables more accurate product recommendations that take into account the user's emotional state.

[1200] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1201] Step 1:

[1202] The server receives the user ID as input and retrieves the user's purchase history data from the purchase history database. This data includes the date and time of each purchase, the purchased items, and the purchase quantity. Specifically, using the user ID "12345," it retrieves "Purchase date and time: 2023-09-15 18:30, purchased items: tomato, lettuce, chicken, purchase quantity: 1 each." The retrieved data is sent to the next analysis step.

[1203] Step 2:

[1204] The server uses the acquired purchase history data as input and applies an analysis algorithm to calculate the frequency of items recently purchased by the user. For example, items purchased three or more times in the past two weeks are estimated as refrigerator inventory. The output is estimated refrigerator inventory information; if "tomatoes, lettuce, and chicken" are included, they are estimated to be left in the refrigerator.

[1205] Step 3:

[1206] The server sends a query to the store's special sale database to retrieve information about the current sale items. The input is a query statement to the database, and the output is "Special sale item name: Tomato sauce, Special sale price: 200 yen, Special sale period: 2023-10-10 to 2023-10-12."

[1207] Step 4:

[1208] The server combines the sale product information and estimated refrigerator inventory information as input, and generates a list of recommended products based on the user's preferences and purchase history. For example, if tomato sauce and cheese are on sale and the user frequently purchases tomatoes, the server prioritizes tomato sauce and cheese. The output is the generated list of recommended products.

[1209] Step 5:

[1210] The device (mobile device) captures the user's facial expressions and voice data using a camera and microphone, and inputs this data into an emotion recognition engine. The engine analyzes this data and recognizes the user's emotional state (e.g., stress level). The output is real-time emotion data, which is sent to a server.

[1211] Step 6:

[1212] The server adjusts the recommended product list based on the emotional data sent by the user. For example, if the user is under stress, it adds relaxing herbal tea to the list. This adjustment generates a final recommended product list that reflects the emotional data.

[1213] Step 7:

[1214] The server sends the generated recommended product list to the user's mobile device or a display device in the store. The device (mobile device) receives this information and visually presents it to the user. For example, a smartphone app might display "Today's Recommended Product List" as "1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Herbal Tea (Reflecting Emotional Data)."

[1215] Step 8:

[1216] When a user makes a purchase, that information is automatically added to the purchase history database, and the server collects this new purchase history data. The server also uses the feedback data provided by the user to fine-tune the recommendation algorithm, which improves the accuracy of future recommendations.

[1217] (Application example 2)

[1218] 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."

[1219] Today's consumers are extremely busy and need assistance in efficiently purchasing daily necessities and food. Furthermore, a system that allows users to purchase items without missing out on special offers would respond to consumers' desire to save money. However, conventional recommendation systems have difficulty recommending optimal products because they do not fully consider users' emotions or individual purchasing habits. Furthermore, providing information in real time is crucial to effectively take advantage of special offers in the market.

[1220] 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.

[1221] In this invention, the server includes means for acquiring a purchase history from a purchase history database of the user, means for acquiring sale item information from a sale item database of the commercial facility, means for analyzing the user's purchase history and estimating items that are likely to still be in the refrigerator, means for generating a list of recommended items for the user based on the acquired sale item information and the estimated refrigerator inventory information, means for transmitting the generated recommended item list to the user's mobile terminal or a display device in the commercial facility, means for collecting feedback data provided by the user and fine-tuning a recommendation algorithm, emotion recognition means for collecting user emotion data, and means for adjusting the recommended item list based on the emotion data. This makes it possible to quickly and accurately recommend optimal products based on the user's emotional state and individual purchasing characteristics while effectively utilizing sale information.

[1222] The "user purchase history database" is an accessible database that records the history of products that a user has purchased in the past.

[1223] A "sales product database" is a database that records and provides access to information about products on sale at commercial facilities.

[1224] The "emotion recognition means" is a means for recognizing the user's emotions using sensors such as a camera or microphone, and acquiring that information.

[1225] The "means for acquiring purchase history" is a means for accessing a purchase history database of a user and acquiring information on products that the user has purchased in the past.

[1226] The "means for acquiring sale item information" refers to a means for accessing a sale item database and acquiring information about items on sale at commercial facilities.

[1227] The "means for analyzing purchase history" is a means for analyzing the user's purchasing patterns based on the acquired purchase history and estimating items that are likely to remain in the refrigerator.

[1228] The "means for generating a recommended product list" is a means for creating an optimal product list for a user based on sale product information and estimated refrigerator inventory information.

[1229] The "means for transmitting a recommended product list" is a means for transmitting the generated recommended product list to a user's mobile terminal or a display device in a commercial facility.

[1230] "Means for collecting feedback data" refers to means for collecting post-purchase opinions and purchase information provided by users and using them to improve recommendation algorithms.

[1231] The "means for adjusting the recommended product list based on emotion data" refers to a means for adjusting the contents of the recommended product list based on the user's emotion data acquired by the emotion recognition means, and recommending optimal products to the user.

[1232] This invention relates to a system that recommends optimal products to individuals by combining a user's purchase history, sale item information, and an emotion engine that recognizes the user's emotions. The main elements are a purchase history database, a sale item database, data analysis means, a recommended product generation means, information provision means, feedback collection means, and emotion recognition means.

[1233] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. This data includes the date and time of each purchase, the purchased item, and the purchased quantity. For example, the user ID is "12345," the purchased items are "tomato, lettuce, chicken," and the purchase date and time is "2023-09-15 18:30."

[1234] Next, the server retrieves information about products currently on sale from the commercial facility's sale product database. This information includes the name of the sale product, the sale price, and the sale period. For example, "Sale products: Tomato sauce, Cheese, Sale period: 2023-10-10 to 2023-10-12."

[1235] Based on this, the server analyzes the purchase history data and estimates which items may remain in the refrigerator based on the user's recent purchase frequency. For example, if an item has been purchased three or more times in the past two weeks, it is assumed that the item is likely to remain in the refrigerator. If the user has recently purchased tomatoes, lettuce, and chicken multiple times, it is assumed that these items remain in the refrigerator.

[1236] Based on the estimated refrigerator inventory, the server compares it with sale item information to generate a list of recommended items. From the sale items, it selects items to recommend preferentially based on the user's preferences and past purchase history. For example, tomato sauce and cheese are on sale, and the user frequently purchases tomatoes, so these are included in the recommended items list.

[1237] Furthermore, the mobile device uses a camera and microphone to recognize the user's emotions in real time, and this information is sent to a server to measure the user's emotional state, for example, if they are tired or stressed.

[1238] The server adjusts the recommended product list based on the user's emotional data. For example, if the user is feeling stressed, the server can prioritize products with a relaxing effect (such as herbal tea) in the list.

[1239] The generated recommended product list is sent from the server to the user's mobile device or to a display device within the commercial facility. The mobile device receives this information and visually presents it to the user. For example, a smartphone app might display "Today's Recommended Product List" as "1. Tomato Sauce (On Sale) 2. Cheese (On Sale) 3. Croutons, etc."

[1240] Finally, when a user actually purchases a product, that information is automatically added to their purchase history. The server collects the feedback data provided by the user (e.g., purchase history) and fine-tunes the recommendation algorithm, thereby improving the accuracy of future recommendations.

[1241] For example and prompt purposes, we will use the following information as input:

[1242] Specific prompt examples:

[1243] User ID: 12345

[1244] Purchase History API URL: http: / / example.com / api / purchase_history

[1245] Special Offers API URL: http: / / example.com / api / special_offers

[1246] Recommendation API URL: http: / / example.com / api / recommendation

[1247] Emotion: stressed

[1248] Generate a list of recommended products

[1249] As a result, users can shop efficiently, make the most of sale information, and receive optimal product recommendations based on their emotions. This system simultaneously satisfies consumers' desire for savings and convenience, and is expected to improve customer satisfaction in commercial facilities.

[1250] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1251] Step 1:

[1252] The server accesses the purchase history database based on the user ID and retrieves past purchase history data. The input is the user ID and the output is the purchase history data. This data includes the date and time of each purchase, the purchased item, and the purchased quantity. Specifically, it sends a request to the API endpoint and retrieves the purchase history data as a response.

[1253] Step 2:

[1254] The server retrieves information about products currently on sale from the commercial facility's sale product database. The input is the API URL of the sale product database, and the output is the sale product information. This information includes the name of the sale product, the sale price, and the sale period. Specifically, it sends a request to the API endpoint and retrieves the sale product data as a response.

[1255] Step 3:

[1256] The server analyzes the acquired purchase history data and estimates which items may remain in the refrigerator based on the user's most recent purchase frequency. The input is the purchase history data, and the output is a list of items estimated to remain in the refrigerator. Specifically, it calculates the purchase frequency of each product and lists items that have been frequently purchased within a certain period of time.

[1257] Step 4:

[1258] The server collects the user's emotional data through an emotion recognition means. The input is the user's real-time video and audio data, and the output is the judged emotional data. Specifically, it analyzes the data input from the camera and microphone and identifies the emotion using a generative AI model.

[1259] Step 5:

[1260] The server generates a recommended product list based on the acquired sale product information, estimated refrigerator inventory information, and emotional data. The inputs are sale product information, refrigerator inventory information, and emotional data, and the output is a recommended product list. Specifically, the server selects products from the sale products that match the user's preferences and emotional state, and generates the list.

[1261] Step 6:

[1262] The server then sends the generated recommended product list to the user's mobile device or a display device within the commercial facility. The input is the recommended product list, and the output is the information displayed on the user's device or display device. Specifically, the list is sent to the device so that the user can visually confirm it.

[1263] Step 7:

[1264] When a user actually purchases a product, the purchase information is added to the purchase history. The input is the information about the purchased product, and the output is an updated purchase history database. Specifically, the purchase information is added to the database, and the server keeps the data as up-to-date.

[1265] Step 8:

[1266] The server collects post-purchase feedback data and fine-tunes the recommendation algorithm. The input is the feedback data provided by the user, and the output is an improved recommendation algorithm. Specifically, the server analyzes the collected feedback and adjusts the algorithm parameters.

[1267] 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.

[1268] 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.

[1269] 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.

[1270] 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.

[1271] 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.

[1272] 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.

[1273] 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).

[1274] 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.

[1275] 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."

[1276] 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.

[1277] 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).

[1278] 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.

[1279] 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.

[1280] 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.

[1281] 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.

[1282] 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.

[1283] 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.

[1284] 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.

[1285] 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.

[1286] 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.

[1287] 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.

[1288] The following is further disclosed regarding the above embodiment.

[1289] (Claim 1)

[1290] means for obtaining a purchase history from a user's purchase history database;

[1291] means for acquiring sale item information from a store's sale item database;

[1292] A means for analyzing a user's purchase history and estimating which items are likely to remain in the refrigerator;

[1293] a means for generating a list of recommended products for a user based on the acquired sale product information and estimated refrigerator inventory information;

[1294] means for transmitting the generated recommended product list to a user's mobile terminal or a display device in the store;

[1295] a means of collecting user-provided feedback data to fine-tune the recommendation algorithm; and

[1296] A system including:

[1297] (Claim 2)

[1298] The system according to claim 1, further comprising means for estimating items that are likely to still be in the refrigerator based on the user's most recent purchase frequency, and generating a recommended product list taking the estimation result into consideration.

[1299] (Claim 3)

[1300] 2. The system according to claim 1, further comprising means for preferentially including in the recommended product list products that match the user's preferences based on the sale product information.

[1301] "Example 1"

[1302] (Claim 1)

[1303] A means for acquiring a purchase history from a purchase history data storage acquired based on a user identifier;

[1304] means for acquiring sale product information from a sale product data storage of a retailer;

[1305] A means for analyzing purchase history to estimate items that are likely to still be held in the cooling equipment;

[1306] a means for generating a list of recommended products optimal for the user based on the acquired sale product information and estimated cooling device inventory information;

[1307] means for transmitting the generated recommended product list to a user's mobile communication terminal or an in-store display device;

[1308] a means for collecting user-provided rating data and adjusting the recommendation algorithm;

[1309] A system including:

[1310] (Claim 2)

[1311] The system according to claim 1, further comprising means for predicting items that are likely to still be stored in the cooling device based on recent purchase frequency, and generating a recommended product list taking the prediction result into consideration.

[1312] (Claim 3)

[1313] 2. The system according to claim 1, further comprising means for preferentially including products that match the user's preferences in the recommended product list based on the sale product information.

[1314] "Application Example 1"

[1315] New invention claims:

[1316] (Claim 1)

[1317] means for obtaining a purchase history from a user's purchase history database;

[1318] means for acquiring sale item information from a store's sale item database;

[1319] A means for analyzing a user's purchase history and estimating which items are likely to remain in the refrigerator;

[1320] a means for generating a list of recommended products for a user based on the acquired sale product information and estimated refrigerator inventory information;

[1321] means for transmitting the generated recommended product list to a user's mobile terminal or a display device in the store;

[1322] a means of collecting user-provided feedback data to fine-tune the recommendation algorithm; and

[1323] A means for guiding a user to navigate within the store to the sale items;

[1324] A system including:

[1325] (Claim 2)

[1326] The system according to claim 1, further comprising means for estimating items that are likely to still be in the refrigerator based on the user's most recent purchase frequency, and generating a recommended product list taking the estimation result into consideration.

[1327] (Claim 3)

[1328] 2. The system according to claim 1, further comprising means for preferentially including in the recommended product list products that match the user's preferences based on the sale product information.

[1329] "Example 2: Combining Emotion Engines"

[1330] (Claim 1)

[1331] means for obtaining a purchase history from a user's purchase history database;

[1332] means for acquiring sale item information from a store's sale item database;

[1333] A means for analyzing a user's purchase history and estimating which items are likely to remain in the refrigerator;

[1334] a means for generating a list of recommended products for a user based on the acquired sale product information and estimated refrigerator inventory information;

[1335] means for transmitting the generated recommended product list to a user's mobile terminal or a display device in the store;

[1336] means for recognizing and acquiring data on user emotions;

[1337] A means for adjusting the recommended product list based on the recognized emotion data; and

[1338] a means of collecting user-provided feedback data to fine-tune the recommendation algorithm; and

[1339] A system including:

[1340] (Claim 2)

[1341] The system according to claim 1, further comprising means for estimating items that are likely to still be in the refrigerator based on the user's most recent purchase frequency, and generating a recommended product list taking the estimation result into consideration.

[1342] (Claim 3)

[1343] 2. The system according to claim 1, further comprising means for preferentially including in the recommended product list products that match the user's preferences based on the sale product information.

[1344] "Application example 2 when combining emotion engines"

[1345] (Claim 1)

[1346] means for obtaining a purchase history from a user's purchase history database;

[1347] A means for acquiring sale item information from a sale item database of a commercial facility;

[1348] A means for analyzing a user's purchase history and estimating which items are likely to remain in the refrigerator;

[1349] a means for generating a list of recommended products for a user based on the acquired sale product information and estimated refrigerator inventory information;

[1350] means for transmitting the generated recommended product list to a user's mobile terminal or a display device in a commercial facility;

[1351] a means of collecting user-provided feedback data to fine-tune the recommendation algorithm; and

[1352] emotion recognition means for collecting emotion data of a user;

[1353] a means for adjusting the recommended product list based on sentiment data; and

[1354] A system including:

[1355] (Claim 2)

[1356] The system according to claim 1, further comprising means for estimating items that are likely to still be in the refrigerator based on the user's most recent purchase frequency, and generating a recommended product list taking the estimation result into consideration.

[1357] (Claim 3)

[1358] 2. The system according to claim 1, further comprising means for preferentially including in the recommended product list products that match the user's preferences based on the sale product information. [Explanation of symbols]

[1359] 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. means for obtaining a purchase history from a user's purchase history database; means for acquiring sale item information from a store's sale item database; A means for analyzing a user's purchase history and estimating which items are likely to remain in the refrigerator; a means for generating a list of recommended products for a user based on the acquired sale product information and estimated refrigerator inventory information; means for transmitting the generated recommended product list to a user's mobile terminal or a display device in the store; a means of collecting user-provided feedback data to fine-tune the recommendation algorithm; and A system including:

2. The system according to claim 1, further comprising means for estimating items that are likely to still be in the refrigerator based on the user's most recent purchase frequency, and generating a recommended product list taking the estimation result into consideration.

3. 2. The system according to claim 1, further comprising means for giving priority to products that match the user's preferences and including them in the recommended products list based on the sale product information.

Images