system

Abstract

Provide a system. A means for collecting user purchasing information; A means for analyzing the collected purchasing information; means for generating coupons based on the analysis results; A means for delivering the generated coupon to a user's terminal; A means for collecting coupon usage data of users; A means to conduct further data analysis based on the collected coupon usage data, 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] Digital payments are rapidly becoming more commonplace in modern times, but users often fail to fully enjoy their convenience. In particular, there is a lack of personalized discount information and coupons that take into account each user's purchasing patterns and preferences. Furthermore, there are no established methods for effectively promoting coupon usage, making it difficult to optimize the user experience. If this situation is left unchecked, the frequency of use of certain payment services may decline, potentially resulting in a loss of competitive advantage in the market. [Means for solving the problem]

[0005] To solve the above-mentioned problems, the present invention provides a system including the following means: means for collecting user purchase information, means for analyzing the collected purchase information, means for generating coupons based on the analysis results, means for distributing the generated coupons to the user's device, means for collecting user coupon usage data, and means for performing further data analysis based on the collected coupon usage data. This makes it possible to provide personalized discount information and coupons, optimizing the user experience and promoting the use of specific payment services. Furthermore, convenience can be further enhanced by optimizing the effectiveness of coupons through A / B testing.

[0006] "User purchase information" refers to information about product purchases made by a user, specifically data such as the type of product purchased, price, purchase date and time, and purchase location.

[0007] "Means of collection" refers to software or hardware functions for storing user purchasing information in a database or server.

[0008] "Analyzing means" refers to software and computer systems that run algorithms and machine learning models to process and analyze collected purchasing information.

[0009] "Means for generating coupons" refers to the software's functionality for automatically generating coupons to provide optimal discounts or offers to users based on the analysis results.

[0010] "Delivery means" refers to the functionality of the communication system and software for sending the generated coupon to the user's mobile device or email.

[0011] "Coupon usage data" refers to information when a user actually uses a coupon, specifically data such as the coupon ID, the date and time of use, the discount amount applied, and the store where the coupon was used.

[0012] The "means for re-analyzing data based on collected coupon usage data" refers to an algorithm and computer system for analyzing coupon usage data and evaluating the effectiveness and usage patterns of coupons.

[0013] "Clustering" is a data analysis technique that categorizes users with similar characteristics into groups based on their purchasing patterns and preferences.

[0014] "A / B testing" is an experimental method for offering different versions of a coupon or promotion to multiple user groups and comparing and evaluating their effectiveness. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] This invention relates to a system that collects and analyzes user purchasing information and generates and distributes individually optimized coupons. This system includes multiple software modules that run on a server, and effectively performs the collection of purchasing information, data analysis, coupon generation, coupon distribution, and reanalysis of usage data.

[0037] Explanation of program processing

[0038] The program of this system operates in conjunction with each step as follows:

[0039] 1. Data Collection

[0040] Server: Collects information about the products purchased by users and stores it in a database, including the type of product, price, purchase date and time, and location.

[0041] User: When making a purchase, purchase information is automatically sent to the server by using digital payment methods such as PayPay.

[0042] 2. Data analysis

[0043] Server: The collected purchasing information is analyzed using machine learning algorithms. Here, clustering techniques are applied to understand users' purchasing patterns and preferences.

[0044] User: No special action is required, everything is handled in the backend.

[0045] 3. Coupon Generation

[0046] Server: Generates the most suitable coupon for each user based on the data analysis results. For example, for a user who frequently buys milk on weekends, a discount coupon is created that can be used on the next purchase of milk.

[0047] Device: The coupon generation notification will be sent to the user's mobile device.

[0048] 4. Coupon distribution

[0049] Server: Send coupons via push notifications or emails at the optimal timing based on the user's purchasing patterns.

[0050] On the device: The coupon details are displayed and the user can review them.

[0051] 5. Coupon Usage and Data Collection

[0052] User: Uses the coupon provided to make a purchase. For example, uses the coupon to buy milk at the supermarket.

[0053] Terminal: When using a coupon, a QR code (registered trademark) or coupon code is displayed and scanned at the store.

[0054] Server: Information about coupon usage (e.g., usage date and time, discount amount, store used, etc.) is collected and stored in a database.

[0055] 6. Reanalysis of usage data

[0056] Server: Re-analyzes coupon usage data and reflects it in the next coupon generation algorithm, which also performs A / B testing and optimization to maximize coupon effectiveness.

[0057] Specific examples

[0058] 1. Data Collection

[0059] Server: When Tanaka purchases milk at the supermarket using digital payment, that information is collected and stored.

[0060] User: Tanaka doesn't have to do anything special; information is collected automatically when he uses digital payments.

[0061] 2. Data analysis

[0062] Server: Run Tanaka's purchasing history through a machine learning model and determine that he frequently purchases milk.

[0063] 3. Coupon Generation

[0064] Server: Generate a coupon for Tanaka to use on his next milk purchase for 100 yen off.

[0065] Device: A notification is sent to Tanaka's smartphone that a coupon has been generated.

[0066] 4. Coupon distribution

[0067] Server: When a triggering purchasing pattern is detected, a coupon is sent via push notification.

[0068] Device: Tanaka's smartphone displays a notification saying, "You've received a coupon for 100 yen off milk!"

[0069] 5. Coupon Usage and Data Collection

[0070] User: Tanaka uses the coupon to purchase milk.

[0071] Terminal: The coupon's QR code will be displayed and scanned by the store clerk.

[0072] Server: Receives coupon redemption information and stores it in a database.

[0073] 6. Reanalysis of usage data

[0074] Server: Reanalyzes the collected coupon usage data and reflects it in generating the next coupon for Tanaka. It also extracts the parameters of effective coupons and improves the overall coupon generation algorithm.

[0075] As a result, the present invention provides optimal coupons based on the user's purchasing behavior, promoting the use of specific payment services and improving the user experience.

[0076] The processing flow will be explained below.

[0077] Step 1: Data collection

[0078] Server: When a user makes a payment, the server collects information about the purchased product (product name, price, purchase date and time, purchase store information, etc.) and payment information in real time. It connects with digital payment platforms such as PayPay and automatically stores this information in a database.

[0079] Users: No special action is required to use digital payments.

[0080] Step 2: Data analysis

[0081] Server: Uses machine learning models and data analysis algorithms to analyze the collected purchasing information. Uses clustering techniques to create groups of users with similar purchasing patterns.

[0082] 1. Organize users' purchasing history over time to understand frequency and trends.

[0083] 2. For each user, analyze their past purchase preferences and predict what they are likely to buy next.

[0084] Step 3: Generate coupon

[0085] Server: Generates optimal coupons for users based on insights gained from data analysis. For example, if a user has recently purchased milk frequently, a discount coupon will be created for the next purchase of milk.

[0086] 1. Decide on the coupon content (discount rate, terms of use, expiration date, etc.).

[0087] 2. When generating a coupon, you can also create multiple versions for A / B testing.

[0088] Step 4: Coupon Delivery

[0089] Server: Delivers the generated coupons to the user's mobile device using different channels such as push notification, SMS, or email.

[0090] 1. Set optimal sending times for each communication channel.

[0091] 2. After sending, track whether the notification has been opened by the user.

[0092] Step 5: View and redeem coupons

[0093] Device: When a user receives a coupon, they will be notified and the QR code or coupon code will be displayed on the coupon details screen.

[0094] 1. The coupon screen will display details such as application conditions and expiration date.

[0095] 2. The user presents and uses the coupon when making a purchase at the store.

[0096] Step 6: Collect coupon usage data

[0097] Terminal: When a coupon is redeemed, usage information is generated in real time.

[0098] Server: Collects coupon usage data (date and time of use, store used, discount amount, etc.) and stores it in a database.

[0099] Step 7: Reanalyze usage data and provide feedback

[0100] Server: Reanalyze the coupon usage data collected, particularly to evaluate which types of coupons were most effective for which user groups.

[0101] 1. Calculate an index to evaluate coupon performance based on usage data.

[0102] 2. By providing feedback to the next coupon generation algorithm, more accurate coupons will be provided.

[0103] By repeating this series of steps, it is possible to constantly provide users with optimized deals and promote the use of digital payments.

[0104] Example 1

[0105] 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."

[0106] Conventional coupon issuing systems were unable to fully utilize users' purchasing history and patterns, making it difficult to provide optimal coupons tailored to their purchasing behavior. Furthermore, they were unable to distribute coupons at an effective timing, resulting in low coupon usage rates and low effectiveness in promoting purchases. Furthermore, they lacked a mechanism for evaluating the effectiveness of coupons and reflecting this in the generation of subsequent coupons, making it difficult to continuously improve and provide optimal coupons.

[0107] 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.

[0108] In this invention, the server includes means for collecting user purchasing information using digital payment methods, means for storing the collected purchasing information in a database, and means for analyzing the stored purchasing information using a machine learning algorithm, which makes it possible to understand the purchasing patterns and preferences of users and generate individually optimized coupons.

[0109] The server further includes a means for generating coupons using a rule-based or generative AI model based on the analysis results, a means for notifying or distributing the generated coupons to the user's terminal, a means for collecting usage data when the user uses the coupons, and a means for re-analyzing data based on the collected coupon usage data and optimizing the algorithm, thereby maximizing the effectiveness of the coupons and continuously providing optimized coupons.

[0110] A "digital payment instrument" is a means by which a user pays for goods or services electronically, such as mobile payments or online payment systems.

[0111] "User purchasing information" refers to data generated when a user purchases a product or service, and includes details such as the product name, price, purchase date and time, and store where the purchase was made.

[0112] A "database" is a collection of structured information that stores collected data in a centralized manner and makes it easy to search and analyze as needed.

[0113] A "machine learning algorithm" is a technology in which a computer program automatically learns patterns from data and uses that knowledge to make predictions and classifications.

[0114] "Rule-based" is a system design method that automatically processes data based on predefined rules and conditions.

[0115] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate new information from data, and is particularly used to generate and individually optimize coupons.

[0116] A "Coupon" is an electronic or paper certificate that provides a discount or special offer to a User.

[0117] "Terminal" refers to a device such as a computer, smartphone, or tablet that a user uses to interact with the system.

[0118] A "notification" is a message that conveys information from the system to the user, and is sent in the form of a push notification, email, etc.

[0119] "Coupon usage data" is data generated when a user uses a coupon, and includes information such as the date and time of use, the discount amount, and the store where the coupon was used.

[0120] "Re-data analysis" is the process of conducting analysis again based on the results of the initial data analysis or newly collected data, with the aim of improving the accuracy and effectiveness of the system.

[0121] "Optimization" is the process of adjusting parameters and conditions to maximize the performance of a system or process in order to achieve a specific objective.

[0122] This invention is a system that collects and analyzes user purchasing information and generates and distributes individually optimized coupons. This system includes multiple software modules that run on a server, and effectively collects purchasing information, analyzes data, generates coupons, distributes coupons, and reanalyzes usage data.

[0123] Hardware and Software Configuration

[0124] This system uses the following main hardware and software:

[0125] Server: Data processing and storage is performed using high-performance cloud servers (e.g., AWS (registered trademark), Azure (registered trademark)).

[0126] Database: A relational database (e.g., MySQL (registered trademark), PostgreSQL) is used to store purchase information and coupon usage data.

[0127] Machine learning algorithms: Use algorithms (e.g., K-means clustering) to analyze purchasing patterns.

[0128] Generative AI model: Uses a generative AI model to generate the best coupons for each user.

[0129] User device: Notifications and coupons are received and used on smartphones and tablets (e.g., iOS, ANDROID (registered trademark)).

[0130] Specific operation of the system

[0131] The operation of this system is as follows.

[0132] 1. Data Collection

[0133] When a user purchases a product using digital payment (e.g., PayPay), the server receives the purchase information in real time and stores it in a database. The purchase information includes details such as the product name, price, purchase date and time, and the store where the purchase was made.

[0134] Users simply use normal digital payments without taking any special action and data is collected.

[0135] 2. Data analysis

[0136] The server analyzes the collected purchasing history using machine learning algorithms (e.g., K-means clustering) to group users' purchasing patterns and preferences.

[0137] No user interaction is required - all analysis is handled in the backend.

[0138] 3. Coupon Generation

[0139] Based on the analysis results, the server generates personalized coupons using rule-based or generative AI models. For example, if a user frequently buys milk on weekends, the server generates a discount coupon for the next milk purchase.

[0140] The terminal is notified of the generated coupon.

[0141] 4. Coupon distribution

[0142] The server delivers coupons at appropriate times based on the user's purchasing patterns, using methods including push notifications and emails.

[0143] Users can check the coupon details through a notification on their device, such as "You've received a coupon for 100 yen off milk!"

[0144] 5. Coupon Usage and Data Collection

[0145] When users use a coupon at a physical store, they ask the store clerk to scan the QR code displayed on their smartphone screen.

[0146] The server collects information about when the coupon was used (e.g., the date and time of use, the discount amount, and the store where the coupon was purchased) and stores this information in a database.

[0147] 6. Reanalysis of usage data

[0148] The server reanalyzes the collected coupon usage data and reflects it in the next coupon generation. Coupon effectiveness is evaluated and optimized through A / B testing.

[0149] The user does not need to take any special action.

[0150] Examples of concrete examples and prompts

[0151] For example, when Tanaka purchases milk using digital payment, the purchase information is sent to the server in real time and stored in a database. The server analyzes Tanaka's purchasing patterns and generates a 100 yen discount coupon that can be used the next time Tanaka purchases milk. The coupon is sent to Tanaka's smartphone, and Tanaka uses the coupon to purchase milk again.

[0152] Prompt Sentence Examples

[0153] Please explain the system that uses user purchasing information to generate and distribute optimal coupons.

[0154] This system allows users to easily receive the most suitable coupons simply by making a purchase using digital payments, thereby improving the purchasing experience and encouraging the use of specific payment services.

[0155] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0156] Step 1:

[0157] Data collection

[0158] User: Uses digital payment methods (e.g. PayPay) when purchasing products.

[0159] Terminal: Purchase information (product name, price, purchase date and time, purchase store, etc.) is automatically collected and sent to the server.

[0160] Server: Receives the purchase information and stores it in a database.

[0161] Input: Purchase information (product name, price, purchase date and time, purchase store, etc.)

[0162] Output: Purchasing information stored in the database

[0163] Step 2:

[0164] Data analysis

[0165] Server: Retrieves data from the purchase history database and applies machine learning algorithms (e.g., K-means clustering) to analyze user purchasing patterns.

[0166] Input: Purchasing information stored in the database

[0167] Output: Analysis of user purchasing patterns

[0168] Specific operation: Features are extracted from purchase history data and classified into patterns using the K-means clustering algorithm.

[0169] Step 3:

[0170] Coupon Generation

[0171] Server: Based on the data analysis results, generate coupons for each user using rule-based or generative AI models.

[0172] Input: Analysis of user purchasing patterns

[0173] Output: Individually optimized coupons for each user

[0174] How it works: Based on purchasing patterns, coupon rules that are likely to lead to the next purchase are applied, and appropriate coupons are generated using a generative AI model.

[0175] Step 4:

[0176] Coupon distribution

[0177] Server: The generated coupon is sent to the user's device via push notification or email.

[0178] Terminal: Display received coupon notifications to users.

[0179] Input: User-optimized coupon

[0180] Output: Coupon notification delivered to user's device

[0181] Specific behavior: Push notifications and emails are sent depending on when the coupon is generated and the user's purchasing patterns.

[0182] Step 5:

[0183] Coupon usage and data collection

[0184] User: Uses a coupon when purchasing an item in a physical store.

[0185] Terminal: Displays the coupon's QR code or barcode and is scanned at the store.

[0186] Server: Collects coupon usage information (date and time of use, discount amount, store used, etc.) and stores it in a database.

[0187] Input: Coupon usage information (usage date and time, discount amount, store used, etc.)

[0188] Output: Coupon usage information stored in the database

[0189] Specific operation: Collects information generated when a user uses a coupon in real time and stores it in a database.

[0190] Step 6:

[0191] Reanalysis of usage data

[0192] Server: Re-analyze the collected coupon usage data together with purchase history data to optimize the parameters of the coupon generation algorithm.

[0193] Input: Coupon usage information and purchase history data stored in the database

[0194] Output: The new coupons reflected in the updated algorithm parameters and the next coupon generation.

[0195] What it does: Use the reanalyzed data to evaluate the performance of the algorithm and optimize it using techniques like A / B testing.

[0196] (Application example 1)

[0197] 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."

[0198] Conventional coupon distribution systems were able to generate and distribute coupons based on user purchasing information. However, there had been little research into how to generate and distribute individually optimized advertisements based on users' purchasing patterns. As a result, they were unable to provide information tailored to users' preferences or deliver effective advertisements, resulting in reduced advertising effectiveness.

[0199] 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.

[0200] In this invention, the server includes means for collecting user purchasing information, means for analyzing the collected purchasing information, means for generating coupons based on the analysis results, means for distributing the generated coupons to user terminals, means for collecting user coupon usage data, means for performing data analysis again based on the collected coupon usage data, means for generating individually optimized advertisements based on the collected and analyzed purchasing information, and means for distributing the generated advertisements to user terminals. This makes it possible to provide optimal coupons and advertisements based on the user's purchasing patterns and to deliver information that matches the user's interests and preferences in a timely manner.

[0201] "Means for collecting user purchasing information" refers to devices or software for collecting purchasing data including information on the products purchased by users, the date and time of purchase, and the place of purchase.

[0202] "Means for analyzing collected purchasing information" refers to devices or software that analyze collected purchasing data and understand users' preferences and purchasing patterns.

[0203] The "means for generating coupons based on the analysis results" refers to a device or software for creating coupons suited to users based on the analysis results of purchase data.

[0204] The "means for delivering the generated coupon to the user's terminal" refers to a device or software for sending the generated coupon to the user's smartphone or other terminal.

[0205] "Means for collecting user coupon usage data" refers to a device or software for collecting coupon usage information used by users.

[0206] The "means for re-analyzing data based on collected coupon usage data" refers to a device or software for analyzing coupon usage data and determining the effectiveness and optimization of coupons.

[0207] "Means for generating individually optimized advertisements based on collected and analyzed purchasing information" refers to a device or software for creating advertisements that are optimal for users based on the results of collecting and analyzing purchasing data.

[0208] "Means for delivering the generated advertisement to the user's terminal" means a device or software for sending the generated advertisement to the user's smartphone or other terminal.

[0209] The present invention is a system for generating and distributing advertisements and coupons that are individually optimized based on a user's purchasing information and preferences. An embodiment of the system will be described in detail below.

[0210] composition

[0211] The system mainly consists of a server and a user terminal. The server collects and analyzes purchase information, and generates and distributes coupons and advertisements. The user terminal receives and displays coupons and advertisements.

[0212] Hardware used

[0213] server

[0214] High-performance computer or cloud server (e.g. AWS, Google® Cloud, Azure)

[0215] User Device

[0216] Smartphone

[0217] tablet

[0218] Software used

[0219] Machine learning algorithms (e.g., scikit-learn, TENSORFLOW(registered trademark))

[0220] Digital payment apps (e.g., PayPay)

[0221] Push notification API (e.g. Firebase Cloud Messaging)

[0222] Ad generator (e.g. Python script)

[0223] Algorithms for analyzing advertising effectiveness (e.g., R language, Python)

[0224] System Operation

[0225] 1. Data Collection

[0226] The server collects information when a user makes a purchase using the digital payment app, including the type of product purchased, the price, the date and time of the purchase, and the location of the purchase.

[0227] The collected purchasing information is stored in a database.

[0228] 2. Data analysis

[0229] The server analyzes the collected purchasing information using machine learning algorithms and clustering techniques (e.g., K-means) to understand users' purchasing patterns and interests.

[0230] The analysis results are used as data to generate optimal advertisements and coupons based on each user's different purchasing history and preferences.

[0231] 3. Coupon generation and distribution

[0232] The server generates the most suitable coupon for each user based on the analysis results and delivers it to the user's device via push notification, allowing the user to receive rewards based on their purchasing behavior.

[0233] 4. Ad generation and delivery

[0234] The server generates individually optimized advertisements based on the collected and analyzed purchasing information and delivers them to the user's device.

[0235] Advertisements are designed to be delivered to users at the right time.

[0236] 5. Data Reanalysis

[0237] The server collects and reanalyzes coupon and advertisement usage data, which can be reflected in the next coupon and advertisement generation.

[0238] In addition, the effectiveness of coupons and advertisements is optimized through A / B testing to improve the next generation algorithm.

[0239] Specific examples

[0240] A specific example of the operation of the system will be shown below.

[0241] 1. Data Collection

[0242] Server: A user purchases clothing from an online store using a digital payment app. The server collects and stores this purchase information.

[0243] User: Information is collected automatically when users make digital payments, without any action on their part.

[0244] 2. Data analysis

[0245] Server: Based on the user's purchasing history, a machine learning model (e.g., K-means clustering) is used to determine the user's interest in fashion products.

[0246] 3. Coupon generation and distribution

[0247] Server: Generate a coupon for the user to redeem for 10% off their next fashion purchase.

[0248] Device: A notification of coupon generation will be sent to the user's smartphone.

[0249] 4. Ad generation and delivery

[0250] Server: Generates the most suitable fashion sale ad for the user and delivers it to their smartphone via push notification.

[0251] Device: A user sees an ad on their phone saying, "Sale at your local store!"

[0252] 5. Data Reanalysis

[0253] Server: Collects information about purchases made by users using coupons and reflects it in the next coupon and ad generation. Also, reanalyzes ad click rates and conversion rates to extract optimal ad delivery patterns.

[0254] Prompt Sentence Examples

[0255] "Create a program that generates the best fashion sale ads for users and analyzes the data to improve the ads for the next time."

[0256] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0257] Step 1:

[0258] The server collects purchase information when a user purchases a product using a digital payment app. The input data includes product information, purchase date and time, purchase location, and payment information. This data is stored in a database. For example, when a user purchases clothing from an online shop using a smartphone, the server collects and stores the purchase information.

[0259] Step 2:

[0260] The server analyzes the collected purchasing information using machine learning algorithms. The collected purchasing data is used as input. Data processing involves filtering out unnecessary data and converting it into an appropriate format. Data calculation involves applying clustering techniques (e.g., K-means) to identify the user's purchasing patterns and preferences. The output is the analysis results (such as the product categories the user is interested in). For example, it may be analyzed that the user frequently purchases fashion items.

[0261] Step 3:

[0262] The server generates the most suitable coupon for the user based on the results of the data analysis. The data analysis results are used as input. The data is processed by referring to the user's purchasing history and preferences to create coupon data related to specific products and categories. The generated coupon data is obtained as output. For example, a 10% discount coupon that can be used on the next purchase of fashion products is generated.

[0263] Step 4:

[0264] The server delivers the generated coupon to the user's device. The generated coupon data is used as input. The data is calculated using a push notification API (e.g., Firebase Cloud Messaging) to send the data. The output is a coupon notification displayed on the user's smartphone. For example, a notification may be delivered to the user's smartphone stating, "You've received a 10% discount coupon that can be used on your next fashion purchase!"

[0265] Step 5:

[0266] The server generates individually optimized advertisements based on the collected and analyzed purchasing information. It uses the purchasing information and analysis results as input. It processes the data by creating advertising content tailored to the user's preferences. It calculates the data by using an advertisement generation program to generate advertising data. It obtains the generated advertising data as output. For example, it generates an advertisement for a fashion sale that the user is interested in.

[0267] Step 6:

[0268] The server delivers the generated advertisement to the user's device. The generated advertisement data is used as input. The data calculation uses a push notification API to send the advertisement data. The output is the advertisement displayed on the user's smartphone. For example, a notification saying "There's a fashion sale at a nearby shop!" is delivered.

[0269] Step 7:

[0270] The server collects coupon and ad usage data and reanalyzes it. It uses user coupon usage information and ad click information as input. It processes the data by appropriately filtering it and creating a dataset for reanalysis. It performs data calculations, including reanalysis of the results of A / B testing, and reflects them in the next coupon and ad generation algorithm. It obtains optimized algorithm parameters as output. For example, it analyzes the types and durations of coupons used by users in the past and extracts elements for optimal coupon generation.

[0271] 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.

[0272] This invention relates to a system that collects user purchasing information and emotional data, and generates and distributes optimized coupons based on the analysis results. This system operates in cooperation with a server, terminals, and users, with the aim of improving the user experience.

[0273] Explanation of program processing

[0274] The program for this system consists of a series of processes that collect and analyze users' purchasing information and emotional data, and then deliver the most appropriate coupons at the right time. The specific processing flow is explained below.

[0275] 1. Data Collection

[0276] Server: When a user makes a payment, information about the purchased item (product name, price, purchase date and time, purchase location, etc.) and the user's emotional data (for example, facial expression analysis using facial recognition or emotional state obtained from voice analysis) are collected and stored in a database.

[0277] User: Uses digital payments and also provides emotional data via the device's camera and microphone, which is automatically sent to the server.

[0278] 2. Data analysis

[0279] Server: Analyzes the collected purchasing information and sentiment data using machine learning models and data analysis algorithms. Applying clustering techniques, the server creates groups of users with similar purchasing patterns and sentiment data.

[0280] User: No action is required, everything is handled automatically in the backend.

[0281] 3. Coupon Generation

[0282] Server: Based on the analysis results, generate coupons that best fit the user's purchasing history and emotional state. For example, if a user shows signs of joy when purchasing milk, generate a discount coupon for that user that can be used on their next purchase.

[0283] Device: The user will receive a notification on their smartphone that a coupon has been generated.

[0284] 4. Coupon distribution

[0285] Server: Generates and delivers the coupon to the user's mobile device via push notification, SMS, or email.

[0286] On the device: The coupon details are displayed and the user can view them.

[0287] 5. Displaying and Using Coupons

[0288] User: Purchases a product using a coupon. For example, they use a coupon to buy milk at the supermarket.

[0289] Terminal: The coupon's QR code or coupon code is displayed and can be scanned at the store to be used.

[0290] 6. Coupon usage data collection

[0291] Terminal: When a coupon is used, usage information is generated in real time.

[0292] Server: Collects coupon usage data (date and time of use, store used, discount amount, etc.) and stores it in a database.

[0293] 7. Reanalysis of usage data and feedback

[0294] Server: Reanalyzes the collected coupon usage data and emotional data and reflects it in the next coupon generation algorithm. In particular, it evaluates how emotional state affects coupon usage, enabling it to provide coupons with optimal timing and content.

[0295] Specific examples

[0296] 1. Data Collection

[0297] Server: Mr. Sato purchases chocolate at a supermarket using digital payment, and facial expression data is collected using a camera. It is recorded that Mr. Sato has a surprised expression on his face when he makes the purchase.

[0298] Users: No action is required; information is automatically transmitted via the smartphone camera and payment app.

[0299] 2. Data analysis

[0300] Server: Analyzes Mr. Sato's purchasing history and facial expression data and finds out that he enjoys buying chocolate.

[0301] 3. Coupon Generation

[0302] Server: Generate a coupon for Sam for 10% off her next chocolate purchase.

[0303] Device: Send a notification to Sato's smartphone saying, "Your next chocolate purchase will be 10% off!"

[0304] 4. Coupon distribution

[0305] Server: Once the coupon is generated, it is sent to Mr. Sato's smartphone.

[0306] Device: A notification appears and Sato checks the coupon details.

[0307] 5. Displaying and Using Coupons

[0308] User: The next time Sam buys chocolate at the supermarket, he uses the coupon displayed on his smartphone.

[0309] Terminal: A QR code or coupon code is displayed and can be used by the store clerk by scanning it.

[0310] 6. Coupon usage data collection

[0311] Server: Information about when Sato used the 10% off coupon (date and time of use, store used, discount amount) is saved in the database.

[0312] 7. Reanalysis of usage data and feedback

[0313] Server: Reanalyzes Sato's coupon usage data and facial expression data and reflects them in the next coupon generation. It also evaluates the effectiveness of coupons based on facial expressions and provides the most appropriate coupon.

[0314] This will allow for the use of emotional data to create a more personalized user experience and encourage greater adoption of digital payments.

[0315] The processing flow will be explained below.

[0316] Step 1: Data collection

[0317] Server: When a user makes a payment, information about the purchased item (product name, price, purchase date and time, purchase location, etc.) is collected. Emotional data is also collected at the same time. This includes facial recognition technology using the user's smartphone camera and estimation of emotional state through voice analysis. All information is automatically stored in a database.

[0318] User: When making a digital payment, the smartphone camera and microphone are activated to collect emotional data from facial expressions and voice, without any action required.

[0319] Step 2: Data analysis

[0320] Server: Analyzes the collected purchasing information and sentiment data. Machine learning algorithms are used to identify trends in users' purchasing patterns and sentiment, and clustering techniques are used to form user groups with similar characteristics.

[0321] 1. Aggregate each user's purchasing history and calculate frequency and average spending.

[0322] 2. Analyze emotional data to identify typical emotional states at the time of purchase (e.g., joy, surprise, sadness, etc.).

[0323] Step 3: Generate coupon

[0324] Server: Based on the results of data analysis, the server generates personalized coupons for each user, taking into account the user's purchasing history and emotional state. For example, if a user always looks happy when buying milk, the server generates a discount coupon for the next milk purchase.

[0325] 1. Set details such as the coupon discount rate, terms of use, and expiration date.

[0326] 2. Generate different versions of the coupon using A / B testing, if necessary.

[0327] Step 4: Coupon Delivery

[0328] Server: Delivers the generated coupons to the user's device via channels such as push notification, SMS, or email.

[0329] 1. Calculate and set the optimal transmission timing for each user.

[0330] 2. After sending, use a tracking system to check whether the user received the notification.

[0331] Step 5: View and redeem coupons

[0332] On your device: Open the notification you received and check the coupon details. The coupon's QR code and coupon code will be displayed.

[0333] 1. The coupon details clearly state the applicable conditions and expiration date.

[0334] 2. Allow users to present and redeem coupons at the time of purchase.

[0335] Step 6: Collect coupon usage data

[0336] Terminal: When a coupon is used, usage information (date and time of use, store used, discount amount, etc.) is generated in real time.

[0337] Server: Stores the collected coupon redemption data in a database for subsequent analysis.

[0338] Step 7: Reanalyze usage data and provide feedback

[0339] Server: Reanalyze the collected coupon usage data and emotion data to determine which coupons were most effective for users in which emotional states.

[0340] 1. Calculate coupon performance evaluation indicators based on usage data.

[0341] 2. Reflect this data in the next coupon generation to provide effective coupons.

[0342] Specific processing examples

[0343] Step 1:

[0344] Server: When Mr. Sato makes a payment at the supermarket, his chocolate purchase information and facial expression data captured by the camera at the time are collected.

[0345] Step 2:

[0346] Server: Analyzes Mr. Sato's viewing data to see that he enjoys chocolate when he buys it. Also, based on his past purchase history, we know that he buys chocolate regularly.

[0347] Step 3:

[0348] Server: Generate a 10% off coupon for your next chocolate purchase.

[0349] Step 4:

[0350] Server: Send a notification to Mr. Sato's smartphone saying, "Your next chocolate purchase will be 10% off!"

[0351] Step 5:

[0352] Device: A notification appears and Sato checks the coupon details.

[0353] Step 6:

[0354] Device: The next time Sato buys chocolate at the supermarket, he will present and use the coupon.

[0355] Step 7:

[0356] Server: Collects data on Sato's coupon usage (date and time of use, store used, discount amount, etc.) and reflects this in the next coupon generation. It also associates emotional data with the effectiveness of coupon usage and reanalyzes it.

[0357] Example 2

[0358] 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."

[0359] In modern society, the spread of digital payments has created a demand for personalized services based on user purchasing behavior. However, conventional systems have focused on analyzing only purchase information, making it difficult to provide personalized services that take user emotions into account. Furthermore, optimization to increase the effectiveness of coupons has been insufficient. This has created challenges in improving user experience and promoting service usage.

[0360] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting user purchase information, means for collecting user emotion data, means for analyzing the collected purchase information and emotion data, means for generating coupons based on the analysis results, means for distributing the generated coupons to the user's terminal, means for collecting user coupon usage data, and means for performing data re-analysis based on the collected coupon usage data. This makes it possible to timely distribute personalized coupons that take user emotions into consideration, maximize the effectiveness of coupon usage, and improve the user experience.

[0361] "User purchasing information" refers to information about the products purchased by the user (product name, price, purchase date and time, purchase location, etc.).

[0362] "User emotional data" refers to data that indicates the user's emotional state, including facial expression analysis using facial recognition, voice analysis, and other sensor data.

[0363] "Collection Method" refers to the technology or device that obtains information from users and stores it in a database or other storage medium.

[0364] "Analytical means" refers to software algorithms and data analysis tools used to analyze collected data and extract meaningful information and patterns.

[0365] "Coupon Generation Means" means software and algorithms for generating coupons containing offers or discounts to offer to Users based on the results of data analysis.

[0366] "Means for delivering coupons to users' devices" refers to the technology or method for sending generated coupons to users' devices such as smartphones or tablets.

[0367] "Means for collecting coupon usage data" refers to a system or device that collects and records information when a user uses a coupon (such as the date and time of use, the store where the coupon was used, and the discount amount).

[0368] "Means for re-analyzing data" refers to technologies and methods for analyzing newly collected coupon usage data, separate from the initial data collection, and reflecting the results in generating the next coupon.

[0369] MODE FOR CARRYING OUT THE INVENTION

[0370] The present invention relates to a system that collects user purchasing information and emotional data, and generates and distributes optimized coupons based on that information. This system operates in cooperation with a server, terminals, and users, with the aim of improving the user experience. Specific embodiments are described below.

[0371] Data collection

[0372] The server works in conjunction with the electronic payment system to collect information on products purchased by users in real time (product name, price, purchase date and time, purchase location, etc.). This is done using an API linked to the POS system. The server also uses the device's camera and microphone to obtain user emotional data (facial expression analysis and voice analysis) and stores this in a database. Possible tools used include Python's OpenCV library and voice analysis library.

[0373] Users provide the necessary emotional data by using the device's camera and microphone in a natural way when making digital payments, so data is collected without any special action required.

[0374] Data analysis

[0375] The server integrates the collected purchasing information and sentiment data and performs analysis using machine learning models and data analysis algorithms. Specifically, it uses Python's Scikit-learn library to form user groups using clustering algorithms (K-means and DBSCAN). This makes it possible to identify users with similar purchasing patterns and sentiment data.

[0376] Coupon Generation

[0377] The server generates the most suitable coupon for the user based on the data analysis results. For example, if the user has a happy expression when purchasing chocolate, the server generates a coupon for 10% off the next chocolate purchase. This process is performed using software with a coupon generation algorithm.

[0378] Example prompt for coupon generation: "If the user purchases chocolate and has a happy expression when purchasing, generate a coupon for 10% off."

[0379] Coupon distribution

[0380] The server then delivers the generated coupon to the user's mobile device via push notification, SMS, or email. APIs used include Firebase Cloud Messaging (FCM) and Amazon SNS (Simple Notification Service).

[0381] The device will then display the details of the coupon to the user, using a mobile app to receive and display notifications.

[0382] Viewing and Using Coupons

[0383] Users can use the coupons they receive to purchase products, such as milk at a supermarket, by using the coupon displayed on their smartphone screen.

[0384] The terminal displays the coupon's QR code or barcode, which can then be scanned at the store using the mobile device's camera.

[0385] Coupon usage data collection

[0386] The server collects information when a user uses a coupon (such as the date and time of use, the store where it was used, and the discount amount) and stores it in a database. By linking with the POS system, usage information is collected in real time.

[0387] Reanalysis of usage data and feedback

[0388] The server re-analyzes the collected coupon usage data and sentiment data and reflects it in the next coupon generation algorithm. This allows for more effective and personalized coupons to be provided. Specific analysis is performed using the aforementioned Python library and analysis tools.

[0389] Through this series of processes, the system can generate and distribute personalized coupons in a timely manner that takes into account the user's purchasing behavior and emotional state, which is expected to improve the user experience and promote the use of digital payments.

[0390] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0391] Step 1: Data collection

[0392] The server collects data from the POS system and the terminal's camera and microphone. The POS system receives the user's purchase information (product name, price, purchase date and time, purchase location, etc.), and the camera and microphone collect the user's emotional data (facial expression data and voice data). This data is stored in a secure database.

[0393] Input: Purchase information from the POS system, emotion data from the device's camera and microphone.

[0394] Output: A database containing purchasing information and sentiment data.

[0395] Specific operation: The server communicates with the POS system via API to obtain real-time purchase data. Emotion data from the device is captured using the camera and microphone and sent to the server.

[0396] Step 2: Data analysis

[0397] The server integrates the collected purchasing information and emotional data and analyzes them using data analysis algorithms and machine learning models (for example, clustering algorithms using Python's Scikit-learn library). This allows the server to cluster users' purchasing patterns and emotional states and form specific user groups.

[0398] Input: Purchase information and sentiment data stored in a database.

[0399] Output: Clustered user population data.

[0400] How it works: The server extracts purchasing information and emotional data from the database and inputs them into a clustering algorithm, which then forms groups of users with similar purchasing patterns and emotional states.

[0401] Step 3: Generate coupon

[0402] The server generates the most suitable coupon for the user based on the analysis results. For example, if a user has a happy expression when purchasing chocolate, the server generates a 10% off coupon for the user's next chocolate purchase.

[0403] Input: Clustered user group data and analysis results of each user's purchasing and sentiment data.

[0404] Output: The generated coupon data.

[0405] How it works: The server determines which coupon is best suited to which user based on purchasing patterns and sentiment data, then runs a coupon generation algorithm to generate coupons, which are then stored in a coupon database.

[0406] Step 4: Coupon Delivery

[0407] The server then delivers the generated coupon to the user's mobile device via push notification, SMS, or email.

[0408] Input: Generated coupon data and user contact information.

[0409] Output: The coupon notification delivered.

[0410] Specific operation: The server uses the user's contact information to select the appropriate delivery method (push notification, SMS, email) and send the coupon. The notification is delivered to the user's device using Firebase Cloud Messaging (FCM) or Amazon SNS.

[0411] Step 5: View and redeem coupons

[0412] Users can use the coupons they receive to purchase products, such as milk at a supermarket, by using the coupon displayed on their smartphone screen.

[0413] Input: The coupon notification the user received.

[0414] Output: Purchase data using coupons.

[0415] What it does: The user shows the coupon displayed on the device to the store clerk and has them scan the QR code or barcode, which applies the discount.

[0416] Step 6: Collect coupon usage data

[0417] The server collects information when a user uses a coupon and stores it in a database, including the date and time of use, the store where the coupon was used, and the discount amount.

[0418] Input: Transaction information when the coupon was redeemed.

[0419] Output: A database containing coupon redemption data.

[0420] Specific operation: The server obtains coupon usage data from the POS system and stores it in a database. Since usage data is collected in real time, it is updated immediately.

[0421] Step 7: Reanalyze usage data and provide feedback

[0422] The server reanalyzes the collected coupon usage data and emotional data and incorporates it into the next coupon generation algorithm, particularly evaluating how emotional states affect coupon usage.

[0423] Input: Coupon redemption data and sentiment data stored in a database.

[0424] Output: An improved coupon generation algorithm.

[0425] How it works: The server retrains the machine learning model based on newly collected coupon usage data to improve the accuracy of the next coupon generation, enabling it to provide more effective personalized coupons.

[0426] Through each of these processing steps, the system can improve the user experience and promote the use of digital payments.

[0427] (Application example 2)

[0428] 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."

[0429] Conventional coupon distribution systems generate coupons based only on a user's purchase history, making it difficult to provide coupons that reflect the user's current emotional state and purchasing patterns. This has led to challenges in delivering coupons at the optimal time for users and generating more effective coupons.

[0430] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user purchasing information, means for analyzing the collected purchasing information and emotional data, means for clustering purchasing patterns and emotional data using a machine learning model, means for generating coupons based on the analysis results, means for delivering the generated coupons to the user's terminal, means for displaying the delivered coupons, means for collecting user coupon usage data, and means for performing further data analysis based on the collected coupon usage data. This makes it possible to provide more personalized and effective coupons based on the user's current emotional state and purchasing patterns.

[0431] "Purchase information" refers to information obtained when a user purchases a product or service, and specifically includes data such as the product name, price, purchase date and time, and purchase location.

[0432] "Emotional data" refers to data that represents the emotional state of the user, and specifically includes information on the emotional state obtained from facial expression recognition and voice analysis.

[0433] A "machine learning model" refers to an algorithm or method that learns patterns and rules based on collected data and makes future predictions and classifications.

[0434] "Clustering" is a method of grouping data with similar characteristics, and is used to analyze user purchasing patterns and emotional data to form similar user groups.

[0435] "Coupon" refers to a ticket or code that allows a user to receive a discount or benefit on their next purchase.

[0436] The term "terminal" refers to an electronic device used by a user, including a smartphone, which in the present invention is used to receive and display coupons.

[0437] The "database" is a system for efficiently storing and managing collected purchasing information, emotional data, and coupon usage data.

[0438] "Analysis results" refers to conclusions and insights derived from collected purchasing information and sentiment data using machine learning models and data analysis algorithms.

[0439] "Coupon usage data" refers to data when a user actually uses a coupon, and includes information such as the date and time of use, the store where the coupon was used, and the discount amount.

[0440] "Push notification" is a function in which a server sends information to a user's device in real time, and is used to distribute generated coupons.

[0441] "Reanalysis" is the process of conducting further analysis based on data that has already been collected to find new insights and areas for improvement.

[0442] The present invention provides a system for collecting user purchasing information and emotional data, analyzing the data, and generating personalized coupons. This system has the following configuration.

[0443] Hardware and Software Configuration

[0444] The server includes means for collecting user purchasing information, means for analyzing the collected purchasing information and emotional data, means for clustering purchasing patterns and emotional data using a machine learning model (such as TensorFlow or PyTorch), means for generating coupons based on the analysis results, means for delivering the generated coupons to the user's device, means for displaying the delivered coupons, means for collecting coupon usage data from users, and means for performing data analysis again based on the collected coupon usage data.

[0445] Processing the data

[0446] When a user purchases an item on an online shopping site, the server collects information about the purchased item (item name, price, purchase date and time, purchase location, etc.) and the item being viewed. It also obtains the user's emotional data (emotional state obtained from facial expression recognition and voice analysis) via the camera and microphone and stores it in a database (MySQL, MongoDB, etc.).

[0447] The server then analyzes the collected purchasing information and sentiment data using machine learning models and data analysis algorithms (e.g., clustering techniques). This process forms groups of users with similar purchasing patterns and sentiment data.

[0448] Based on the analysis, the server generates coupons that best fit the user's purchasing history and emotional state. For example, if a user is excited about buying a new gadget, the server generates a discount coupon for the user's next gadget purchase.

[0449] The generated coupon is sent from the server to the user's device via push notification (e.g., Firebase Cloud Messaging). Detailed coupon information is displayed on the user's device, allowing the user to check and use the coupon. When the user uses the coupon during their next purchase, usage information is generated in real time and stored in a database.

[0450] The collected coupon usage data will be analyzed again and reflected in the next coupon generation algorithm, allowing for more personalized coupons based on the user's emotional state and purchasing patterns.

[0451] Specific examples

[0452] For example, when User A purchases a gadget on an online shopping site, the camera captures his or her excited facial expression. The server then generates a 10% off coupon that can be applied to User A's future gadget purchases and sends it to User A's smartphone via push notification. When User A uses the coupon on their next purchase, information such as the date and time of use, the store where it was used, and the discount amount is collected and stored in a database. This data is used for the next analysis to help regenerate the most appropriate coupon for User A.

[0453] Prompt Sentence Examples

[0454] "Please propose an algorithm that analyzes user purchasing patterns based on emotional data and generates optimal coupons."

[0455] "Generate the best coupon using the following user data: User A: Purchase history [gadgets, books], Emotion data [excitement, joy]"

[0456] In this way, the present invention can provide more personalized coupons based on a user's emotional state and purchasing patterns.

[0457] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0458] Step 1:

[0459] The server collects the user's purchasing information and emotional data. The purchasing information includes the product name, price, purchase date and time, and purchase location. The emotional data is facial recognition and voice analysis data obtained through the device's camera and microphone. This data is sent to the server and stored in a database. The input is the information obtained when the user purchases a product on an online shopping site, and the output is the purchasing information and emotional data stored in the database.

[0460] Step 2:

[0461] The server analyzes the purchasing information and emotional data stored in the database using machine learning models (such as TensorFlow or PyTorch) and data analysis algorithms. It uses clustering techniques to form user groups with similar purchasing patterns and emotional data. The input is the purchasing information and emotional data stored in the database, and the output is the clustering results. Specifically, the machine learning algorithm analyzes the data and forms user groups.

[0462] Step 3:

[0463] The server generates a coupon that best suits the user's purchase history and emotional state based on the clustering results. For example, if a user is excited while purchasing a gadget, it generates a coupon that can be used for the user's next gadget purchase. The input is the clustering results and the user's emotional data, and the output is the generated coupon. Specifically, the server runs a coupon generation algorithm to create the optimal coupon.

[0464] Step 4:

[0465] The server delivers the generated coupon to the user's device via push notification (e.g., Firebase Cloud Messaging). The input is the generated coupon, and the output is the coupon notification delivered to the user's device. Specifically, the server sends detailed coupon information using a push notification service.

[0466] Step 5:

[0467] The terminal displays detailed coupon information to the user, who can then check and use the coupon. The input is the delivered coupon notification, and the output is the displayed coupon information. Specifically, the terminal activates a function to display coupon details on the screen.

[0468] Step 6:

[0469] When a user uses a coupon to purchase a product, the terminal displays the coupon code and automatically applies it at the time of purchase. The input is the coupon information the user wants to use, and the output is the applied coupon information. Specifically, the terminal's coupon code display function is activated and the code is entered.

[0470] Step 7:

[0471] When a coupon is used, the server collects usage information (date and time of use, store used, discount amount, etc.) in real time and stores it in a database. The input is the information at the time of coupon use, and the output is the coupon usage information stored in the database. Specifically, the server's data collection function is activated and the information is added to the database.

[0472] Step 8:

[0473] The server reanalyzes the collected coupon usage data and sentiment data and reflects it in the next coupon generation algorithm. The input is the coupon usage data and sentiment data stored in the database, and the output is the reanalysis results. Specifically, the server runs the data analysis algorithm again and uses the insights gained to help generate the next coupon.

[0474] 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.

[0475] 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.

[0476] 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.

[0477] [Second embodiment]

[0478] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0479] 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.

[0480] 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).

[0481] 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.

[0482] 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.

[0483] 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).

[0484] 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.

[0485] 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.

[0486] 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.

[0487] 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.

[0488] 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.

[0489] 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."

[0490] This invention relates to a system that collects and analyzes user purchasing information and generates and distributes individually optimized coupons. This system includes multiple software modules that run on a server, and effectively performs the collection of purchasing information, data analysis, coupon generation, coupon distribution, and reanalysis of usage data.

[0491] Explanation of program processing

[0492] The program of this system operates in conjunction with each step as follows:

[0493] 1. Data Collection

[0494] Server: Collects information about the products purchased by users and stores it in a database, including the type of product, price, purchase date and time, and location.

[0495] User: When making a purchase, purchase information is automatically sent to the server by using digital payment methods such as PayPay.

[0496] 2. Data analysis

[0497] Server: The collected purchasing information is analyzed using machine learning algorithms. Here, clustering techniques are applied to understand users' purchasing patterns and preferences.

[0498] User: No special action is required, everything is handled in the backend.

[0499] 3. Coupon Generation

[0500] Server: Generates the most suitable coupon for each user based on the data analysis results. For example, for a user who frequently buys milk on weekends, a discount coupon is created that can be used on the next purchase of milk.

[0501] Device: The coupon generation notification will be sent to the user's mobile device.

[0502] 4. Coupon distribution

[0503] Server: Send coupons via push notifications or emails at the optimal timing based on the user's purchasing patterns.

[0504] On the device: The coupon details are displayed and the user can review them.

[0505] 5. Coupon Usage and Data Collection

[0506] User: Uses the coupon provided to make a purchase. For example, uses the coupon to buy milk at the supermarket.

[0507] Terminal: When using a coupon, the QR code or coupon code is displayed and scanned at the store.

[0508] Server: Information about coupon usage (e.g., usage date and time, discount amount, store used, etc.) is collected and stored in a database.

[0509] 6. Reanalysis of usage data

[0510] Server: Re-analyzes coupon usage data and reflects it in the next coupon generation algorithm, which also performs A / B testing and optimization to maximize coupon effectiveness.

[0511] Specific examples

[0512] 1. Data Collection

[0513] Server: When Tanaka purchases milk at the supermarket using digital payment, that information is collected and stored.

[0514] User: Tanaka doesn't have to do anything special; information is collected automatically when he uses digital payments.

[0515] 2. Data analysis

[0516] Server: Run Tanaka's purchasing history through a machine learning model and determine that he frequently purchases milk.

[0517] 3. Coupon Generation

[0518] Server: Generate a coupon for Tanaka to use on his next milk purchase for 100 yen off.

[0519] Device: A notification is sent to Tanaka's smartphone that a coupon has been generated.

[0520] 4. Coupon distribution

[0521] Server: When a triggering purchasing pattern is detected, a coupon is sent via push notification.

[0522] Device: Tanaka's smartphone displays a notification saying, "You've received a coupon for 100 yen off milk!"

[0523] 5. Coupon Usage and Data Collection

[0524] User: Tanaka uses the coupon to purchase milk.

[0525] Terminal: The coupon's QR code will be displayed and scanned by the store clerk.

[0526] Server: Receives coupon redemption information and stores it in a database.

[0527] 6. Reanalysis of usage data

[0528] Server: Reanalyzes the collected coupon usage data and reflects it in generating the next coupon for Tanaka. It also extracts the parameters of effective coupons and improves the overall coupon generation algorithm.

[0529] As a result, the present invention provides optimal coupons based on the user's purchasing behavior, promoting the use of specific payment services and improving the user experience.

[0530] The processing flow will be explained below.

[0531] Step 1: Data collection

[0532] Server: When a user makes a payment, the server collects information about the purchased product (product name, price, purchase date and time, purchase store information, etc.) and payment information in real time. It connects with digital payment platforms such as PayPay and automatically stores this information in a database.

[0533] Users: No special action is required to use digital payments.

[0534] Step 2: Data analysis

[0535] Server: Uses machine learning models and data analysis algorithms to analyze the collected purchasing information. Uses clustering techniques to create groups of users with similar purchasing patterns.

[0536] 1. Organize users' purchasing history over time to understand frequency and trends.

[0537] 2. For each user, analyze their past purchase preferences and predict what they are likely to buy next.

[0538] Step 3: Generate coupon

[0539] Server: Generates optimal coupons for users based on insights gained from data analysis. For example, if a user has recently purchased milk frequently, a discount coupon will be created for the next purchase of milk.

[0540] 1. Decide on the coupon content (discount rate, terms of use, expiration date, etc.).

[0541] 2. When generating a coupon, you can also create multiple versions for A / B testing.

[0542] Step 4: Coupon Delivery

[0543] Server: Delivers the generated coupons to the user's mobile device using different channels such as push notification, SMS, or email.

[0544] 1. Set optimal sending times for each communication channel.

[0545] 2. After sending, track whether the notification has been opened by the user.

[0546] Step 5: View and redeem coupons

[0547] Device: When a user receives a coupon, they will be notified and the QR code or coupon code will be displayed on the coupon details screen.

[0548] 1. The coupon screen will display details such as application conditions and expiration date.

[0549] 2. The user presents and uses the coupon when making a purchase at the store.

[0550] Step 6: Collect coupon usage data

[0551] Terminal: When a coupon is redeemed, usage information is generated in real time.

[0552] Server: Collects coupon usage data (date and time of use, store used, discount amount, etc.) and stores it in a database.

[0553] Step 7: Reanalyze usage data and provide feedback

[0554] Server: Reanalyze the coupon usage data collected, particularly to evaluate which types of coupons were most effective for which user groups.

[0555] 1. Calculate an index to evaluate coupon performance based on usage data.

[0556] 2. By providing feedback to the next coupon generation algorithm, more accurate coupons will be provided.

[0557] By repeating this series of steps, it is possible to constantly provide users with optimized deals and promote the use of digital payments.

[0558] Example 1

[0559] 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."

[0560] Conventional coupon issuing systems were unable to fully utilize users' purchasing history and patterns, making it difficult to provide optimal coupons tailored to their purchasing behavior. Furthermore, they were unable to distribute coupons at an effective timing, resulting in low coupon usage rates and low effectiveness in promoting purchases. Furthermore, they lacked a mechanism for evaluating the effectiveness of coupons and reflecting this in the generation of subsequent coupons, making it difficult to continuously improve and provide optimal coupons.

[0561] 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.

[0562] In this invention, the server includes means for collecting user purchasing information using digital payment methods, means for storing the collected purchasing information in a database, and means for analyzing the stored purchasing information using a machine learning algorithm, which makes it possible to understand the purchasing patterns and preferences of users and generate individually optimized coupons.

[0563] The server further includes a means for generating coupons using a rule-based or generative AI model based on the analysis results, a means for notifying or distributing the generated coupons to the user's terminal, a means for collecting usage data when the user uses the coupons, and a means for re-analyzing data based on the collected coupon usage data and optimizing the algorithm, thereby maximizing the effectiveness of the coupons and continuously providing optimized coupons.

[0564] A "digital payment instrument" is a means by which a user pays for goods or services electronically, such as mobile payments or online payment systems.

[0565] "User purchasing information" refers to data generated when a user purchases a product or service, and includes details such as the product name, price, purchase date and time, and store where the purchase was made.

[0566] A "database" is a collection of structured information that stores collected data in a centralized manner and makes it easy to search and analyze as needed.

[0567] A "machine learning algorithm" is a technology in which a computer program automatically learns patterns from data and uses that knowledge to make predictions and classifications.

[0568] "Rule-based" is a system design method that automatically processes data based on predefined rules and conditions.

[0569] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate new information from data, and is particularly used to generate and individually optimize coupons.

[0570] A "Coupon" is an electronic or paper certificate that provides a discount or special offer to a User.

[0571] "Terminal" refers to a device such as a computer, smartphone, or tablet that a user uses to interact with the system.

[0572] A "notification" is a message that conveys information from the system to the user, and is sent in the form of a push notification, email, etc.

[0573] "Coupon usage data" is data generated when a user uses a coupon, and includes information such as the date and time of use, the discount amount, and the store where the coupon was used.

[0574] "Re-data analysis" is the process of conducting analysis again based on the results of the initial data analysis or newly collected data, with the aim of improving the accuracy and effectiveness of the system.

[0575] "Optimization" is the process of adjusting parameters and conditions to maximize the performance of a system or process in order to achieve a specific objective.

[0576] This invention is a system that collects and analyzes user purchasing information and generates and distributes individually optimized coupons. This system includes multiple software modules that run on a server, and effectively collects purchasing information, analyzes data, generates coupons, distributes coupons, and reanalyzes usage data.

[0577] Hardware and Software Configuration

[0578] This system uses the following main hardware and software:

[0579] Server: Use high-performance cloud servers (e.g., AWS, Azure) to process and store data.

[0580] Database: Use a relational database (e.g., MySQL, PostgreSQL) to store purchase information and coupon redemption data.

[0581] Machine learning algorithms: Use algorithms (e.g., K-means clustering) to analyze purchasing patterns.

[0582] Generative AI model: Uses a generative AI model to generate the best coupons for each user.

[0583] User device: Receive and use notifications and coupons on your smartphone or tablet (e.g., iOS, Android).

[0584] Specific operation of the system

[0585] The operation of this system is as follows.

[0586] 1. Data Collection

[0587] When a user purchases a product using digital payment (e.g., PayPay), the server receives the purchase information in real time and stores it in a database. The purchase information includes details such as the product name, price, purchase date and time, and the store where the purchase was made.

[0588] Users simply use normal digital payments without taking any special action and data is collected.

[0589] 2. Data analysis

[0590] The server analyzes the collected purchasing history using machine learning algorithms (e.g., K-means clustering) to group users' purchasing patterns and preferences.

[0591] No user interaction is required - all analysis is handled in the backend.

[0592] 3. Coupon Generation

[0593] Based on the analysis results, the server generates personalized coupons using rule-based or generative AI models. For example, if a user frequently buys milk on weekends, the server generates a discount coupon for the next milk purchase.

[0594] The terminal is notified of the generated coupon.

[0595] 4. Coupon distribution

[0596] The server delivers coupons at appropriate times based on the user's purchasing patterns, using methods including push notifications and emails.

[0597] Users can check the coupon details through a notification on their device, such as "You've received a coupon for 100 yen off milk!"

[0598] 5. Coupon Usage and Data Collection

[0599] When users use a coupon at a physical store, they ask the store clerk to scan the QR code displayed on their smartphone screen.

[0600] The server collects information about when the coupon was used (e.g., the date and time of use, the discount amount, and the store where the coupon was purchased) and stores this information in a database.

[0601] 6. Reanalysis of usage data

[0602] The server reanalyzes the collected coupon usage data and reflects it in the next coupon generation. Coupon effectiveness is evaluated and optimized through A / B testing.

[0603] The user does not need to take any special action.

[0604] Examples of concrete examples and prompts

[0605] For example, when Tanaka purchases milk using digital payment, the purchase information is sent to the server in real time and stored in a database. The server analyzes Tanaka's purchasing patterns and generates a 100 yen discount coupon that can be used the next time Tanaka purchases milk. The coupon is sent to Tanaka's smartphone, and Tanaka uses the coupon to purchase milk again.

[0606] Prompt Sentence Examples

[0607] Please explain the system that uses user purchasing information to generate and distribute optimal coupons.

[0608] This system allows users to easily receive the most suitable coupons simply by making a purchase using digital payments, thereby improving the purchasing experience and encouraging the use of specific payment services.

[0609] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0610] Step 1:

[0611] Data collection

[0612] User: Uses digital payment methods (e.g. PayPay) when purchasing products.

[0613] Terminal: Purchase information (product name, price, purchase date and time, purchase store, etc.) is automatically collected and sent to the server.

[0614] Server: Receives the purchase information and stores it in a database.

[0615] Input: Purchase information (product name, price, purchase date and time, purchase store, etc.)

[0616] Output: Purchasing information stored in the database

[0617] Step 2:

[0618] Data analysis

[0619] Server: Retrieves data from the purchase history database and applies machine learning algorithms (e.g., K-means clustering) to analyze user purchasing patterns.

[0620] Input: Purchasing information stored in the database

[0621] Output: Analysis of user purchasing patterns

[0622] Specific operation: Features are extracted from purchase history data and classified into patterns using the K-means clustering algorithm.

[0623] Step 3:

[0624] Coupon Generation

[0625] Server: Based on the data analysis results, generate coupons for each user using rule-based or generative AI models.

[0626] Input: Analysis of user purchasing patterns

[0627] Output: Individually optimized coupons for each user

[0628] How it works: Based on purchasing patterns, coupon rules that are likely to lead to the next purchase are applied, and appropriate coupons are generated using a generative AI model.

[0629] Step 4:

[0630] Coupon distribution

[0631] Server: The generated coupon is sent to the user's device via push notification or email.

[0632] Terminal: Display received coupon notifications to users.

[0633] Input: User-optimized coupon

[0634] Output: Coupon notification delivered to user's device

[0635] Specific behavior: Push notifications and emails are sent depending on when the coupon is generated and the user's purchasing patterns.

[0636] Step 5:

[0637] Coupon usage and data collection

[0638] User: Uses a coupon when purchasing an item in a physical store.

[0639] Terminal: Displays the coupon's QR code or barcode and is scanned at the store.

[0640] Server: Collects coupon usage information (date and time of use, discount amount, store used, etc.) and stores it in a database.

[0641] Input: Coupon usage information (usage date and time, discount amount, store used, etc.)

[0642] Output: Coupon usage information stored in the database

[0643] Specific operation: Collects information generated when a user uses a coupon in real time and stores it in a database.

[0644] Step 6:

[0645] Reanalysis of usage data

[0646] Server: Re-analyze the collected coupon usage data together with purchase history data to optimize the parameters of the coupon generation algorithm.

[0647] Input: Coupon usage information and purchase history data stored in the database

[0648] Output: The new coupons reflected in the updated algorithm parameters and the next coupon generation.

[0649] What it does: Use the reanalyzed data to evaluate the performance of the algorithm and optimize it using techniques like A / B testing.

[0650] (Application example 1)

[0651] 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."

[0652] Conventional coupon distribution systems were able to generate and distribute coupons based on user purchasing information. However, there had been little research into how to generate and distribute individually optimized advertisements based on users' purchasing patterns. As a result, they were unable to provide information tailored to users' preferences or deliver effective advertisements, resulting in reduced advertising effectiveness.

[0653] 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.

[0654] In this invention, the server includes means for collecting user purchasing information, means for analyzing the collected purchasing information, means for generating coupons based on the analysis results, means for distributing the generated coupons to user terminals, means for collecting user coupon usage data, means for performing data analysis again based on the collected coupon usage data, means for generating individually optimized advertisements based on the collected and analyzed purchasing information, and means for distributing the generated advertisements to user terminals. This makes it possible to provide optimal coupons and advertisements based on the user's purchasing patterns and to deliver information that matches the user's interests and preferences in a timely manner.

[0655] "Means for collecting user purchasing information" refers to devices or software for collecting purchasing data including information on the products purchased by users, the date and time of purchase, and the place of purchase.

[0656] "Means for analyzing collected purchasing information" refers to devices or software that analyze collected purchasing data and understand users' preferences and purchasing patterns.

[0657] The "means for generating coupons based on the analysis results" refers to a device or software for creating coupons suited to users based on the analysis results of purchase data.

[0658] The "means for delivering the generated coupon to the user's terminal" refers to a device or software for sending the generated coupon to the user's smartphone or other terminal.

[0659] "Means for collecting user coupon usage data" refers to a device or software for collecting coupon usage information used by users.

[0660] The "means for re-analyzing data based on collected coupon usage data" refers to a device or software for analyzing coupon usage data and determining the effectiveness and optimization of coupons.

[0661] "Means for generating individually optimized advertisements based on collected and analyzed purchasing information" refers to a device or software for creating advertisements that are optimal for users based on the results of collecting and analyzing purchasing data.

[0662] "Means for delivering the generated advertisement to the user's terminal" means a device or software for sending the generated advertisement to the user's smartphone or other terminal.

[0663] The present invention is a system for generating and distributing advertisements and coupons that are individually optimized based on a user's purchasing information and preferences. An embodiment of the system will be described in detail below.

[0664] composition

[0665] The system mainly consists of a server and a user terminal. The server collects and analyzes purchase information, and generates and distributes coupons and advertisements. The user terminal receives and displays coupons and advertisements.

[0666] Hardware used

[0667] server

[0668] High-performance computer or cloud server (e.g. AWS, Google Cloud, Azure)

[0669] User Device

[0670] Smartphone

[0671] tablet

[0672] Software used

[0673] Machine learning algorithms (e.g., scikit-learn, TensorFlow)

[0674] Digital payment apps (e.g., PayPay)

[0675] Push notification API (e.g. Firebase Cloud Messaging)

[0676] Ad generator (e.g. Python script)

[0677] Algorithms for analyzing advertising effectiveness (e.g., R language, Python)

[0678] System Operation

[0679] 1. Data Collection

[0680] The server collects information when a user makes a purchase using the digital payment app, including the type of product purchased, the price, the date and time of the purchase, and the location of the purchase.

[0681] The collected purchasing information is stored in a database.

[0682] 2. Data analysis

[0683] The server analyzes the collected purchasing information using machine learning algorithms and clustering techniques (e.g., K-means) to understand users' purchasing patterns and interests.

[0684] The analysis results are used as data to generate optimal advertisements and coupons based on each user's different purchasing history and preferences.

[0685] 3. Coupon generation and distribution

[0686] The server generates the most suitable coupon for each user based on the analysis results and delivers it to the user's device via push notification, allowing the user to receive rewards based on their purchasing behavior.

[0687] 4. Ad generation and delivery

[0688] The server generates individually optimized advertisements based on the collected and analyzed purchasing information and delivers them to the user's device.

[0689] Advertisements are designed to be delivered to users at the right time.

[0690] 5. Data Reanalysis

[0691] The server collects and reanalyzes coupon and advertisement usage data, which can be reflected in the next coupon and advertisement generation.

[0692] In addition, the effectiveness of coupons and advertisements is optimized through A / B testing to improve the next generation algorithm.

[0693] Specific examples

[0694] A specific example of the operation of the system will be shown below.

[0695] 1. Data Collection

[0696] Server: A user purchases clothing from an online store using a digital payment app. The server collects and stores this purchase information.

[0697] User: Information is collected automatically when users make digital payments, without any action on their part.

[0698] 2. Data analysis

[0699] Server: Based on the user's purchasing history, a machine learning model (e.g., K-means clustering) is used to determine the user's interest in fashion products.

[0700] 3. Coupon generation and distribution

[0701] Server: Generate a coupon for the user to redeem for 10% off their next fashion purchase.

[0702] Device: A notification of coupon generation will be sent to the user's smartphone.

[0703] 4. Ad generation and delivery

[0704] Server: Generates the most suitable fashion sale ad for the user and delivers it to their smartphone via push notification.

[0705] Device: A user sees an ad on their phone saying, "Sale at your local store!"

[0706] 5. Data Reanalysis

[0707] Server: Collects information about purchases made by users using coupons and reflects it in the next coupon and ad generation. Also, reanalyzes ad click rates and conversion rates to extract optimal ad delivery patterns.

[0708] Prompt Sentence Examples

[0709] "Create a program that generates the best fashion sale ads for users and analyzes the data to improve the ads for the next time."

[0710] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0711] Step 1:

[0712] The server collects purchase information when a user purchases a product using a digital payment app. The input data includes product information, purchase date and time, purchase location, and payment information. This data is stored in a database. For example, when a user purchases clothing from an online shop using a smartphone, the server collects and stores the purchase information.

[0713] Step 2:

[0714] The server analyzes the collected purchasing information using machine learning algorithms. The collected purchasing data is used as input. Data processing involves filtering out unnecessary data and converting it into an appropriate format. Data calculation involves applying clustering techniques (e.g., K-means) to identify the user's purchasing patterns and preferences. The output is the analysis results (such as the product categories the user is interested in). For example, it may be analyzed that the user frequently purchases fashion items.

[0715] Step 3:

[0716] The server generates the most suitable coupon for the user based on the results of the data analysis. The data analysis results are used as input. The data is processed by referring to the user's purchasing history and preferences to create coupon data related to specific products and categories. The generated coupon data is obtained as output. For example, a 10% discount coupon that can be used on the next purchase of fashion products is generated.

[0717] Step 4:

[0718] The server delivers the generated coupon to the user's device. The generated coupon data is used as input. The data is calculated using a push notification API (e.g., Firebase Cloud Messaging) to send the data. The output is a coupon notification displayed on the user's smartphone. For example, a notification may be delivered to the user's smartphone stating, "You've received a 10% discount coupon that can be used on your next fashion purchase!"

[0719] Step 5:

[0720] The server generates individually optimized advertisements based on the collected and analyzed purchasing information. It uses the purchasing information and analysis results as input. It processes the data by creating advertising content tailored to the user's preferences. It calculates the data by using an advertisement generation program to generate advertising data. It obtains the generated advertising data as output. For example, it generates an advertisement for a fashion sale that the user is interested in.

[0721] Step 6:

[0722] The server delivers the generated advertisement to the user's device. The generated advertisement data is used as input. The data calculation uses a push notification API to send the advertisement data. The output is the advertisement displayed on the user's smartphone. For example, a notification saying "There's a fashion sale at a nearby shop!" is delivered.

[0723] Step 7:

[0724] The server collects coupon and ad usage data and reanalyzes it. It uses user coupon usage information and ad click information as input. It processes the data by appropriately filtering it and creating a dataset for reanalysis. It performs data calculations, including reanalysis of the results of A / B testing, and reflects them in the next coupon and ad generation algorithm. It obtains optimized algorithm parameters as output. For example, it analyzes the types and durations of coupons used by users in the past and extracts elements for optimal coupon generation.

[0725] 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.

[0726] This invention relates to a system that collects user purchasing information and emotional data, and generates and distributes optimized coupons based on the analysis results. This system operates in cooperation with a server, terminals, and users, with the aim of improving the user experience.

[0727] Explanation of program processing

[0728] The program for this system consists of a series of processes that collect and analyze users' purchasing information and emotional data, and then deliver the most appropriate coupons at the right time. The specific processing flow is explained below.

[0729] 1. Data Collection

[0730] Server: When a user makes a payment, information about the purchased item (product name, price, purchase date and time, purchase location, etc.) and the user's emotional data (for example, facial expression analysis using facial recognition or emotional state obtained from voice analysis) are collected and stored in a database.

[0731] User: Uses digital payments and also provides emotional data via the device's camera and microphone, which is automatically sent to the server.

[0732] 2. Data analysis

[0733] Server: Analyzes the collected purchasing information and sentiment data using machine learning models and data analysis algorithms. Applying clustering techniques, the server creates groups of users with similar purchasing patterns and sentiment data.

[0734] User: No action is required, everything is handled automatically in the backend.

[0735] 3. Coupon Generation

[0736] Server: Based on the analysis results, generate coupons that best fit the user's purchasing history and emotional state. For example, if a user shows signs of joy when purchasing milk, generate a discount coupon for that user that can be used on their next purchase.

[0737] Device: The user will receive a notification on their smartphone that a coupon has been generated.

[0738] 4. Coupon distribution

[0739] Server: Generates and delivers the coupon to the user's mobile device via push notification, SMS, or email.

[0740] On the device: The coupon details are displayed and the user can view them.

[0741] 5. Displaying and Using Coupons

[0742] User: Purchases a product using a coupon. For example, they use a coupon to buy milk at the supermarket.

[0743] Terminal: The coupon's QR code or coupon code is displayed and can be scanned at the store to be used.

[0744] 6. Coupon usage data collection

[0745] Terminal: When a coupon is used, usage information is generated in real time.

[0746] Server: Collects coupon usage data (date and time of use, store used, discount amount, etc.) and stores it in a database.

[0747] 7. Reanalysis of usage data and feedback

[0748] Server: Reanalyzes the collected coupon usage data and emotional data and reflects it in the next coupon generation algorithm. In particular, it evaluates how emotional state affects coupon usage, enabling it to provide coupons with optimal timing and content.

[0749] Specific examples

[0750] 1. Data Collection

[0751] Server: Mr. Sato purchases chocolate at a supermarket using digital payment, and facial expression data is collected using a camera. It is recorded that Mr. Sato has a surprised expression on his face when he makes the purchase.

[0752] Users: No action is required; information is automatically transmitted via the smartphone camera and payment app.

[0753] 2. Data analysis

[0754] Server: Analyzes Mr. Sato's purchasing history and facial expression data and finds out that he enjoys buying chocolate.

[0755] 3. Coupon Generation

[0756] Server: Generate a coupon for Sam for 10% off her next chocolate purchase.

[0757] Device: Send a notification to Sato's smartphone saying, "Your next chocolate purchase will be 10% off!"

[0758] 4. Coupon distribution

[0759] Server: Once the coupon is generated, it is sent to Mr. Sato's smartphone.

[0760] Device: A notification appears and Sato checks the coupon details.

[0761] 5. Displaying and Using Coupons

[0762] User: The next time Sam buys chocolate at the supermarket, he uses the coupon displayed on his smartphone.

[0763] Terminal: A QR code or coupon code is displayed and can be used by the store clerk by scanning it.

[0764] 6. Coupon usage data collection

[0765] Server: Information about when Sato used the 10% off coupon (date and time of use, store used, discount amount) is saved in the database.

[0766] 7. Reanalysis of usage data and feedback

[0767] Server: Reanalyzes Sato's coupon usage data and facial expression data and reflects them in the next coupon generation. It also evaluates the effectiveness of coupons based on facial expressions and provides the most appropriate coupon.

[0768] This will allow for the use of emotional data to create a more personalized user experience and encourage greater adoption of digital payments.

[0769] The processing flow will be explained below.

[0770] Step 1: Data collection

[0771] Server: When a user makes a payment, information about the purchased item (product name, price, purchase date and time, purchase location, etc.) is collected. Emotional data is also collected at the same time. This includes facial recognition technology using the user's smartphone camera and estimation of emotional state through voice analysis. All information is automatically stored in a database.

[0772] User: When making a digital payment, the smartphone camera and microphone are activated to collect emotional data from facial expressions and voice, without any action required.

[0773] Step 2: Data analysis

[0774] Server: Analyzes the collected purchasing information and sentiment data. Machine learning algorithms are used to identify trends in users' purchasing patterns and sentiment, and clustering techniques are used to form user groups with similar characteristics.

[0775] 1. Aggregate each user's purchasing history and calculate frequency and average spending.

[0776] 2. Analyze emotional data to identify typical emotional states at the time of purchase (e.g., joy, surprise, sadness, etc.).

[0777] Step 3: Generate coupon

[0778] Server: Based on the results of data analysis, the server generates personalized coupons for each user, taking into account the user's purchasing history and emotional state. For example, if a user always looks happy when buying milk, the server generates a discount coupon for the next milk purchase.

[0779] 1. Set details such as the coupon discount rate, terms of use, and expiration date.

[0780] 2. Generate different versions of the coupon using A / B testing, if necessary.

[0781] Step 4: Coupon Delivery

[0782] Server: Delivers the generated coupons to the user's device via channels such as push notification, SMS, or email.

[0783] 1. Calculate and set the optimal transmission timing for each user.

[0784] 2. After sending, use a tracking system to check whether the user received the notification.

[0785] Step 5: View and redeem coupons

[0786] On your device: Open the notification you received and check the coupon details. The coupon's QR code and coupon code will be displayed.

[0787] 1. The coupon details clearly state the applicable conditions and expiration date.

[0788] 2. Allow users to present and redeem coupons at the time of purchase.

[0789] Step 6: Collect coupon usage data

[0790] Terminal: When a coupon is used, usage information (date and time of use, store used, discount amount, etc.) is generated in real time.

[0791] Server: Stores the collected coupon redemption data in a database for subsequent analysis.

[0792] Step 7: Reanalyze usage data and provide feedback

[0793] Server: Reanalyze the collected coupon usage data and emotion data to determine which coupons were most effective for users in which emotional states.

[0794] 1. Calculate coupon performance evaluation indicators based on usage data.

[0795] 2. Reflect this data in the next coupon generation to provide effective coupons.

[0796] Specific processing examples

[0797] Step 1:

[0798] Server: When Mr. Sato makes a payment at the supermarket, his chocolate purchase information and facial expression data captured by the camera at the time are collected.

[0799] Step 2:

[0800] Server: Analyzes Mr. Sato's viewing data to see that he enjoys chocolate when he buys it. Also, based on his past purchase history, we know that he buys chocolate regularly.

[0801] Step 3:

[0802] Server: Generate a 10% off coupon for your next chocolate purchase.

[0803] Step 4:

[0804] Server: Send a notification to Mr. Sato's smartphone saying, "Your next chocolate purchase will be 10% off!"

[0805] Step 5:

[0806] Device: A notification appears and Sato checks the coupon details.

[0807] Step 6:

[0808] Device: The next time Sato buys chocolate at the supermarket, he will present and use the coupon.

[0809] Step 7:

[0810] Server: Collects data on Sato's coupon usage (date and time of use, store used, discount amount, etc.) and reflects this in the next coupon generation. It also associates emotional data with the effectiveness of coupon usage and reanalyzes it.

[0811] Example 2

[0812] 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."

[0813] In modern society, the spread of digital payments has created a demand for personalized services based on user purchasing behavior. However, conventional systems have focused on analyzing only purchase information, making it difficult to provide personalized services that take user emotions into account. Furthermore, optimization to increase the effectiveness of coupons has been insufficient. This has created challenges in improving user experience and promoting service usage.

[0814] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting user purchase information, means for collecting user emotion data, means for analyzing the collected purchase information and emotion data, means for generating coupons based on the analysis results, means for distributing the generated coupons to the user's terminal, means for collecting user coupon usage data, and means for performing data re-analysis based on the collected coupon usage data. This makes it possible to timely distribute personalized coupons that take user emotions into consideration, maximize the effectiveness of coupon usage, and improve the user experience.

[0815] "User purchasing information" refers to information about the products purchased by the user (product name, price, purchase date and time, purchase location, etc.).

[0816] "User emotional data" refers to data that indicates the user's emotional state, including facial expression analysis using facial recognition, voice analysis, and other sensor data.

[0817] "Collection Method" refers to the technology or device that obtains information from users and stores it in a database or other storage medium.

[0818] "Analytical means" refers to software algorithms and data analysis tools used to analyze collected data and extract meaningful information and patterns.

[0819] "Coupon Generation Means" means software and algorithms for generating coupons containing offers or discounts to offer to Users based on the results of data analysis.

[0820] "Means for delivering coupons to users' devices" refers to the technology or method for sending generated coupons to users' devices such as smartphones or tablets.

[0821] "Means for collecting coupon usage data" refers to a system or device that collects and records information when a user uses a coupon (such as the date and time of use, the store where the coupon was used, and the discount amount).

[0822] "Means for re-analyzing data" refers to technologies and methods for analyzing newly collected coupon usage data, separate from the initial data collection, and reflecting the results in generating the next coupon.

[0823] MODE FOR CARRYING OUT THE INVENTION

[0824] The present invention relates to a system that collects user purchasing information and emotional data, and generates and distributes optimized coupons based on that information. This system operates in cooperation with a server, terminals, and users, with the aim of improving the user experience. Specific embodiments are described below.

[0825] Data collection

[0826] The server works in conjunction with the electronic payment system to collect information on products purchased by users in real time (product name, price, purchase date and time, purchase location, etc.). This is done using an API linked to the POS system. The server also uses the device's camera and microphone to obtain user emotional data (facial expression analysis and voice analysis) and stores this in a database. Possible tools used include Python's OpenCV library and voice analysis library.

[0827] Users provide the necessary emotional data by using the device's camera and microphone in a natural way when making digital payments, so data is collected without any special action required.

[0828] Data analysis

[0829] The server integrates the collected purchasing information and sentiment data and performs analysis using machine learning models and data analysis algorithms. Specifically, it uses Python's Scikit-learn library to form user groups using clustering algorithms (K-means and DBSCAN). This makes it possible to identify users with similar purchasing patterns and sentiment data.

[0830] Coupon Generation

[0831] The server generates the most suitable coupon for the user based on the data analysis results. For example, if the user has a happy expression when purchasing chocolate, the server generates a coupon for 10% off the next chocolate purchase. This process is performed using software with a coupon generation algorithm.

[0832] Example prompt for coupon generation: "If the user purchases chocolate and has a happy expression when purchasing, generate a coupon for 10% off."

[0833] Coupon distribution

[0834] The server then delivers the generated coupon to the user's mobile device via push notification, SMS, or email. APIs used include Firebase Cloud Messaging (FCM) and Amazon SNS (Simple Notification Service).

[0835] The device will then display the details of the coupon to the user, using a mobile app to receive and display notifications.

[0836] Viewing and Using Coupons

[0837] Users can use the coupons they receive to purchase products, such as milk at a supermarket, by using the coupon displayed on their smartphone screen.

[0838] The terminal displays the coupon's QR code or barcode, which can then be scanned at the store using the mobile device's camera.

[0839] Coupon usage data collection

[0840] The server collects information when a user uses a coupon (such as the date and time of use, the store where it was used, and the discount amount) and stores it in a database. By linking with the POS system, usage information is collected in real time.

[0841] Reanalysis of usage data and feedback

[0842] The server re-analyzes the collected coupon usage data and sentiment data and reflects it in the next coupon generation algorithm. This allows for more effective and personalized coupons to be provided. Specific analysis is performed using the aforementioned Python library and analysis tools.

[0843] Through this series of processes, the system can generate and distribute personalized coupons in a timely manner that takes into account the user's purchasing behavior and emotional state, which is expected to improve the user experience and promote the use of digital payments.

[0844] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0845] Step 1: Data collection

[0846] The server collects data from the POS system and the terminal's camera and microphone. The POS system receives the user's purchase information (product name, price, purchase date and time, purchase location, etc.), and the camera and microphone collect the user's emotional data (facial expression data and voice data). This data is stored in a secure database.

[0847] Input: Purchase information from the POS system, emotion data from the device's camera and microphone.

[0848] Output: A database containing purchasing information and sentiment data.

[0849] Specific operation: The server communicates with the POS system via API to obtain real-time purchase data. Emotion data from the device is captured using the camera and microphone and sent to the server.

[0850] Step 2: Data analysis

[0851] The server integrates the collected purchasing information and emotional data and analyzes them using data analysis algorithms and machine learning models (for example, clustering algorithms using Python's Scikit-learn library). This allows the server to cluster users' purchasing patterns and emotional states and form specific user groups.

[0852] Input: Purchase information and sentiment data stored in a database.

[0853] Output: Clustered user population data.

[0854] How it works: The server extracts purchasing information and emotional data from the database and inputs them into a clustering algorithm, which then forms groups of users with similar purchasing patterns and emotional states.

[0855] Step 3: Generate coupon

[0856] The server generates the most suitable coupon for the user based on the analysis results. For example, if a user has a happy expression when purchasing chocolate, the server generates a 10% off coupon for the user's next chocolate purchase.

[0857] Input: Clustered user group data and analysis results of each user's purchasing and sentiment data.

[0858] Output: The generated coupon data.

[0859] How it works: The server determines which coupon is best suited to which user based on purchasing patterns and sentiment data, then runs a coupon generation algorithm to generate coupons, which are then stored in a coupon database.

[0860] Step 4: Coupon Delivery

[0861] The server then delivers the generated coupon to the user's mobile device via push notification, SMS, or email.

[0862] Input: Generated coupon data and user contact information.

[0863] Output: The coupon notification delivered.

[0864] Specific operation: The server uses the user's contact information to select the appropriate delivery method (push notification, SMS, email) and send the coupon. The notification is delivered to the user's device using Firebase Cloud Messaging (FCM) or Amazon SNS.

[0865] Step 5: View and redeem coupons

[0866] Users can use the coupons they receive to purchase products, such as milk at a supermarket, by using the coupon displayed on their smartphone screen.

[0867] Input: The coupon notification the user received.

[0868] Output: Purchase data using coupons.

[0869] What it does: The user shows the coupon displayed on the device to the store clerk and has them scan the QR code or barcode, which applies the discount.

[0870] Step 6: Collect coupon usage data

[0871] The server collects information when a user uses a coupon and stores it in a database, including the date and time of use, the store where the coupon was used, and the discount amount.

[0872] Input: Transaction information when the coupon was redeemed.

[0873] Output: A database containing coupon redemption data.

[0874] Specific operation: The server obtains coupon usage data from the POS system and stores it in a database. Since usage data is collected in real time, it is updated immediately.

[0875] Step 7: Reanalyze usage data and provide feedback

[0876] The server reanalyzes the collected coupon usage data and emotional data and incorporates it into the next coupon generation algorithm, particularly evaluating how emotional states affect coupon usage.

[0877] Input: Coupon redemption data and sentiment data stored in a database.

[0878] Output: An improved coupon generation algorithm.

[0879] How it works: The server retrains the machine learning model based on newly collected coupon usage data to improve the accuracy of the next coupon generation, enabling it to provide more effective personalized coupons.

[0880] Through each of these processing steps, the system can improve the user experience and promote the use of digital payments.

[0881] (Application example 2)

[0882] 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."

[0883] Conventional coupon distribution systems generate coupons based only on a user's purchase history, making it difficult to provide coupons that reflect the user's current emotional state and purchasing patterns. This has led to challenges in delivering coupons at the optimal time for users and generating more effective coupons.

[0884] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user purchasing information, means for analyzing the collected purchasing information and emotional data, means for clustering purchasing patterns and emotional data using a machine learning model, means for generating coupons based on the analysis results, means for delivering the generated coupons to the user's terminal, means for displaying the delivered coupons, means for collecting user coupon usage data, and means for performing further data analysis based on the collected coupon usage data. This makes it possible to provide more personalized and effective coupons based on the user's current emotional state and purchasing patterns.

[0885] "Purchase information" refers to information obtained when a user purchases a product or service, and specifically includes data such as the product name, price, purchase date and time, and purchase location.

[0886] "Emotional data" refers to data that represents the emotional state of the user, and specifically includes information on the emotional state obtained from facial expression recognition and voice analysis.

[0887] A "machine learning model" refers to an algorithm or method that learns patterns and rules based on collected data and makes future predictions and classifications.

[0888] "Clustering" is a method of grouping data with similar characteristics, and is used to analyze user purchasing patterns and emotional data to form similar user groups.

[0889] "Coupon" refers to a ticket or code that allows a user to receive a discount or benefit on their next purchase.

[0890] The term "terminal" refers to an electronic device used by a user, including a smartphone, which in the present invention is used to receive and display coupons.

[0891] The "database" is a system for efficiently storing and managing collected purchasing information, emotional data, and coupon usage data.

[0892] "Analysis results" refers to conclusions and insights derived from collected purchasing information and sentiment data using machine learning models and data analysis algorithms.

[0893] "Coupon usage data" refers to data when a user actually uses a coupon, and includes information such as the date and time of use, the store where the coupon was used, and the discount amount.

[0894] "Push notification" is a function in which a server sends information to a user's device in real time, and is used to distribute generated coupons.

[0895] "Reanalysis" is the process of conducting further analysis based on data that has already been collected to find new insights and areas for improvement.

[0896] The present invention provides a system for collecting user purchasing information and emotional data, analyzing the data, and generating personalized coupons. This system has the following configuration.

[0897] Hardware and Software Configuration

[0898] The server includes means for collecting user purchasing information, means for analyzing the collected purchasing information and emotional data, means for clustering purchasing patterns and emotional data using a machine learning model (such as TensorFlow or PyTorch), means for generating coupons based on the analysis results, means for delivering the generated coupons to the user's device, means for displaying the delivered coupons, means for collecting coupon usage data from users, and means for performing data analysis again based on the collected coupon usage data.

[0899] Processing the data

[0900] When a user purchases an item on an online shopping site, the server collects information about the purchased item (item name, price, purchase date and time, purchase location, etc.) and the item being viewed. It also obtains the user's emotional data (emotional state obtained from facial expression recognition and voice analysis) via the camera and microphone and stores it in a database (MySQL, MongoDB, etc.).

[0901] The server then analyzes the collected purchasing information and sentiment data using machine learning models and data analysis algorithms (e.g., clustering techniques). This process forms groups of users with similar purchasing patterns and sentiment data.

[0902] Based on the analysis, the server generates coupons that best fit the user's purchasing history and emotional state. For example, if a user is excited about buying a new gadget, the server generates a discount coupon for the user's next gadget purchase.

[0903] The generated coupon is sent from the server to the user's device via push notification (e.g., Firebase Cloud Messaging). Detailed coupon information is displayed on the user's device, allowing the user to check and use the coupon. When the user uses the coupon during their next purchase, usage information is generated in real time and stored in a database.

[0904] The collected coupon usage data will be analyzed again and reflected in the next coupon generation algorithm, allowing for more personalized coupons based on the user's emotional state and purchasing patterns.

[0905] Specific examples

[0906] For example, when User A purchases a gadget on an online shopping site, the camera captures his or her excited facial expression. The server then generates a 10% off coupon that can be applied to User A's future gadget purchases and sends it to User A's smartphone via push notification. When User A uses the coupon on their next purchase, information such as the date and time of use, the store where it was used, and the discount amount is collected and stored in a database. This data is used for the next analysis to help regenerate the most appropriate coupon for User A.

[0907] Prompt Sentence Examples

[0908] "Please propose an algorithm that analyzes user purchasing patterns based on emotional data and generates optimal coupons."

[0909] "Generate the best coupon using the following user data: User A: Purchase history [gadgets, books], Emotion data [excitement, joy]"

[0910] In this way, the present invention can provide more personalized coupons based on a user's emotional state and purchasing patterns.

[0911] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0912] Step 1:

[0913] The server collects the user's purchasing information and emotional data. The purchasing information includes the product name, price, purchase date and time, and purchase location. The emotional data is facial recognition and voice analysis data obtained through the device's camera and microphone. This data is sent to the server and stored in a database. The input is the information obtained when the user purchases a product on an online shopping site, and the output is the purchasing information and emotional data stored in the database.

[0914] Step 2:

[0915] The server analyzes the purchasing information and emotional data stored in the database using machine learning models (such as TensorFlow or PyTorch) and data analysis algorithms. It uses clustering techniques to form user groups with similar purchasing patterns and emotional data. The input is the purchasing information and emotional data stored in the database, and the output is the clustering results. Specifically, the machine learning algorithm analyzes the data and forms user groups.

[0916] Step 3:

[0917] The server generates a coupon that best suits the user's purchase history and emotional state based on the clustering results. For example, if a user is excited while purchasing a gadget, it generates a coupon that can be used for the user's next gadget purchase. The input is the clustering results and the user's emotional data, and the output is the generated coupon. Specifically, the server runs a coupon generation algorithm to create the optimal coupon.

[0918] Step 4:

[0919] The server delivers the generated coupon to the user's device via push notification (e.g., Firebase Cloud Messaging). The input is the generated coupon, and the output is the coupon notification delivered to the user's device. Specifically, the server sends detailed coupon information using a push notification service.

[0920] Step 5:

[0921] The terminal displays detailed coupon information to the user, who can then check and use the coupon. The input is the delivered coupon notification, and the output is the displayed coupon information. Specifically, the terminal activates a function to display coupon details on the screen.

[0922] Step 6:

[0923] When a user uses a coupon to purchase a product, the terminal displays the coupon code and automatically applies it at the time of purchase. The input is the coupon information the user wants to use, and the output is the applied coupon information. Specifically, the terminal's coupon code display function is activated and the code is entered.

[0924] Step 7:

[0925] When a coupon is used, the server collects usage information (date and time of use, store used, discount amount, etc.) in real time and stores it in a database. The input is the information at the time of coupon use, and the output is the coupon usage information stored in the database. Specifically, the server's data collection function is activated and the information is added to the database.

[0926] Step 8:

[0927] The server reanalyzes the collected coupon usage data and sentiment data and reflects it in the next coupon generation algorithm. The input is the coupon usage data and sentiment data stored in the database, and the output is the reanalysis results. Specifically, the server runs the data analysis algorithm again and uses the insights gained to help generate the next coupon.

[0928] 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.

[0929] 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.

[0930] 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.

[0931] [Third embodiment]

[0932] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0933] 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.

[0934] 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).

[0935] 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.

[0936] 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.

[0937] 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).

[0938] 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.

[0939] 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.

[0940] 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.

[0941] 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.

[0942] 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.

[0943] 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."

[0944] This invention relates to a system that collects and analyzes user purchasing information and generates and distributes individually optimized coupons. This system includes multiple software modules that run on a server, and effectively performs the collection of purchasing information, data analysis, coupon generation, coupon distribution, and reanalysis of usage data.

[0945] Explanation of program processing

[0946] The program of this system operates in conjunction with each step as follows:

[0947] 1. Data Collection

[0948] Server: Collects information about the products purchased by users and stores it in a database, including the type of product, price, purchase date and time, and location.

[0949] User: When making a purchase, purchase information is automatically sent to the server by using digital payment methods such as PayPay.

[0950] 2. Data analysis

[0951] Server: The collected purchasing information is analyzed using machine learning algorithms. Here, clustering techniques are applied to understand users' purchasing patterns and preferences.

[0952] User: No special action is required, everything is handled in the backend.

[0953] 3. Coupon Generation

[0954] Server: Generates the most suitable coupon for each user based on the data analysis results. For example, for a user who frequently buys milk on weekends, a discount coupon is created that can be used on the next purchase of milk.

[0955] Device: The coupon generation notification will be sent to the user's mobile device.

[0956] 4. Coupon distribution

[0957] Server: Send coupons via push notifications or emails at the optimal timing based on the user's purchasing patterns.

[0958] On the device: The coupon details are displayed and the user can review them.

[0959] 5. Coupon Usage and Data Collection

[0960] User: Uses the coupon provided to make a purchase. For example, uses the coupon to buy milk at the supermarket.

[0961] Terminal: When using a coupon, the QR code or coupon code is displayed and scanned at the store.

[0962] Server: Information about coupon usage (e.g., usage date and time, discount amount, store used, etc.) is collected and stored in a database.

[0963] 6. Reanalysis of usage data

[0964] Server: Re-analyzes coupon usage data and reflects it in the next coupon generation algorithm, which also performs A / B testing and optimization to maximize coupon effectiveness.

[0965] Specific examples

[0966] 1. Data Collection

[0967] Server: When Tanaka purchases milk at the supermarket using digital payment, that information is collected and stored.

[0968] User: Tanaka doesn't have to do anything special; information is collected automatically when he uses digital payments.

[0969] 2. Data analysis

[0970] Server: Run Tanaka's purchasing history through a machine learning model and determine that he frequently purchases milk.

[0971] 3. Coupon Generation

[0972] Server: Generate a coupon for Tanaka to use on his next milk purchase for 100 yen off.

[0973] Device: A notification is sent to Tanaka's smartphone that a coupon has been generated.

[0974] 4. Coupon distribution

[0975] Server: When a triggering purchasing pattern is detected, a coupon is sent via push notification.

[0976] Device: Tanaka's smartphone displays a notification saying, "You've received a coupon for 100 yen off milk!"

[0977] 5. Coupon Usage and Data Collection

[0978] User: Tanaka uses the coupon to purchase milk.

[0979] Terminal: The coupon's QR code will be displayed and scanned by the store clerk.

[0980] Server: Receives coupon redemption information and stores it in a database.

[0981] 6. Reanalysis of usage data

[0982] Server: Reanalyzes the collected coupon usage data and reflects it in generating the next coupon for Tanaka. It also extracts the parameters of effective coupons and improves the overall coupon generation algorithm.

[0983] As a result, the present invention provides optimal coupons based on the user's purchasing behavior, promoting the use of specific payment services and improving the user experience.

[0984] The processing flow will be explained below.

[0985] Step 1: Data collection

[0986] Server: When a user makes a payment, the server collects information about the purchased product (product name, price, purchase date and time, purchase store information, etc.) and payment information in real time. It connects with digital payment platforms such as PayPay and automatically stores this information in a database.

[0987] Users: No special action is required to use digital payments.

[0988] Step 2: Data analysis

[0989] Server: Uses machine learning models and data analysis algorithms to analyze the collected purchasing information. Uses clustering techniques to create groups of users with similar purchasing patterns.

[0990] 1. Organize users' purchasing history over time to understand frequency and trends.

[0991] 2. For each user, analyze their past purchase preferences and predict what they are likely to buy next.

[0992] Step 3: Generate coupon

[0993] Server: Generates optimal coupons for users based on insights gained from data analysis. For example, if a user has recently purchased milk frequently, a discount coupon will be created for the next purchase of milk.

[0994] 1. Decide on the coupon content (discount rate, terms of use, expiration date, etc.).

[0995] 2. When generating a coupon, you can also create multiple versions for A / B testing.

[0996] Step 4: Coupon Delivery

[0997] Server: Delivers the generated coupons to the user's mobile device using different channels such as push notification, SMS, or email.

[0998] 1. Set optimal sending times for each communication channel.

[0999] 2. After sending, track whether the notification has been opened by the user.

[1000] Step 5: View and redeem coupons

[1001] Device: When a user receives a coupon, they will be notified and the QR code or coupon code will be displayed on the coupon details screen.

[1002] 1. The coupon screen will display details such as application conditions and expiration date.

[1003] 2. The user presents and uses the coupon when making a purchase at the store.

[1004] Step 6: Collect coupon usage data

[1005] Terminal: When a coupon is redeemed, usage information is generated in real time.

[1006] Server: Collects coupon usage data (date and time of use, store used, discount amount, etc.) and stores it in a database.

[1007] Step 7: Reanalyze usage data and provide feedback

[1008] Server: Reanalyze the coupon usage data collected, particularly to evaluate which types of coupons were most effective for which user groups.

[1009] 1. Calculate an index to evaluate coupon performance based on usage data.

[1010] 2. By providing feedback to the next coupon generation algorithm, more accurate coupons will be provided.

[1011] By repeating this series of steps, it is possible to constantly provide users with optimized deals and promote the use of digital payments.

[1012] Example 1

[1013] 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."

[1014] Conventional coupon issuing systems were unable to fully utilize users' purchasing history and patterns, making it difficult to provide optimal coupons tailored to their purchasing behavior. Furthermore, they were unable to distribute coupons at an effective timing, resulting in low coupon usage rates and low effectiveness in promoting purchases. Furthermore, they lacked a mechanism for evaluating the effectiveness of coupons and reflecting this in the generation of subsequent coupons, making it difficult to continuously improve and provide optimal coupons.

[1015] 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.

[1016] In this invention, the server includes means for collecting user purchasing information using digital payment methods, means for storing the collected purchasing information in a database, and means for analyzing the stored purchasing information using a machine learning algorithm, which makes it possible to understand the purchasing patterns and preferences of users and generate individually optimized coupons.

[1017] The server further includes a means for generating coupons using a rule-based or generative AI model based on the analysis results, a means for notifying or distributing the generated coupons to the user's terminal, a means for collecting usage data when the user uses the coupons, and a means for re-analyzing data based on the collected coupon usage data and optimizing the algorithm, thereby maximizing the effectiveness of the coupons and continuously providing optimized coupons.

[1018] A "digital payment instrument" is a means by which a user pays for goods or services electronically, such as mobile payments or online payment systems.

[1019] "User purchasing information" refers to data generated when a user purchases a product or service, and includes details such as the product name, price, purchase date and time, and store where the purchase was made.

[1020] A "database" is a collection of structured information that stores collected data in a centralized manner and makes it easy to search and analyze as needed.

[1021] A "machine learning algorithm" is a technology in which a computer program automatically learns patterns from data and uses that knowledge to make predictions and classifications.

[1022] "Rule-based" is a system design method that automatically processes data based on predefined rules and conditions.

[1023] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate new information from data, and is particularly used to generate and individually optimize coupons.

[1024] A "Coupon" is an electronic or paper certificate that provides a discount or special offer to a User.

[1025] "Terminal" refers to a device such as a computer, smartphone, or tablet that a user uses to interact with the system.

[1026] A "notification" is a message that conveys information from the system to the user, and is sent in the form of a push notification, email, etc.

[1027] "Coupon usage data" is data generated when a user uses a coupon, and includes information such as the date and time of use, the discount amount, and the store where the coupon was used.

[1028] "Re-data analysis" is the process of conducting analysis again based on the results of the initial data analysis or newly collected data, with the aim of improving the accuracy and effectiveness of the system.

[1029] "Optimization" is the process of adjusting parameters and conditions to maximize the performance of a system or process in order to achieve a specific objective.

[1030] This invention is a system that collects and analyzes user purchasing information and generates and distributes individually optimized coupons. This system includes multiple software modules that run on a server, and effectively collects purchasing information, analyzes data, generates coupons, distributes coupons, and reanalyzes usage data.

[1031] Hardware and Software Configuration

[1032] This system uses the following main hardware and software:

[1033] Server: Use high-performance cloud servers (e.g., AWS, Azure) to process and store data.

[1034] Database: Use a relational database (e.g., MySQL, PostgreSQL) to store purchase information and coupon redemption data.

[1035] Machine learning algorithms: Use algorithms (e.g., K-means clustering) to analyze purchasing patterns.

[1036] Generative AI model: Uses a generative AI model to generate the best coupons for each user.

[1037] User device: Receive and use notifications and coupons on your smartphone or tablet (e.g., iOS, Android).

[1038] Specific operation of the system

[1039] The operation of this system is as follows.

[1040] 1. Data Collection

[1041] When a user purchases a product using digital payment (e.g., PayPay), the server receives the purchase information in real time and stores it in a database. The purchase information includes details such as the product name, price, purchase date and time, and the store where the purchase was made.

[1042] Users simply use normal digital payments without taking any special action and data is collected.

[1043] 2. Data analysis

[1044] The server analyzes the collected purchasing history using machine learning algorithms (e.g., K-means clustering) to group users' purchasing patterns and preferences.

[1045] No user interaction is required - all analysis is handled in the backend.

[1046] 3. Coupon Generation

[1047] Based on the analysis results, the server generates personalized coupons using rule-based or generative AI models. For example, if a user frequently buys milk on weekends, the server generates a discount coupon for the next milk purchase.

[1048] The terminal is notified of the generated coupon.

[1049] 4. Coupon distribution

[1050] The server delivers coupons at appropriate times based on the user's purchasing patterns, using methods including push notifications and emails.

[1051] Users can check the coupon details through a notification on their device, such as "You've received a coupon for 100 yen off milk!"

[1052] 5. Coupon Usage and Data Collection

[1053] When users use a coupon at a physical store, they ask the store clerk to scan the QR code displayed on their smartphone screen.

[1054] The server collects information about when the coupon was used (e.g., the date and time of use, the discount amount, and the store where the coupon was purchased) and stores this information in a database.

[1055] 6. Reanalysis of usage data

[1056] The server reanalyzes the collected coupon usage data and reflects it in the next coupon generation. Coupon effectiveness is evaluated and optimized through A / B testing.

[1057] The user does not need to take any special action.

[1058] Examples of concrete examples and prompts

[1059] For example, when Tanaka purchases milk using digital payment, the purchase information is sent to the server in real time and stored in a database. The server analyzes Tanaka's purchasing patterns and generates a 100 yen discount coupon that can be used the next time Tanaka purchases milk. The coupon is sent to Tanaka's smartphone, and Tanaka uses the coupon to purchase milk again.

[1060] Prompt Sentence Examples

[1061] Please explain the system that uses user purchasing information to generate and distribute optimal coupons.

[1062] This system allows users to easily receive the most suitable coupons simply by making a purchase using digital payments, thereby improving the purchasing experience and encouraging the use of specific payment services.

[1063] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1064] Step 1:

[1065] Data collection

[1066] User: Uses digital payment methods (e.g. PayPay) when purchasing products.

[1067] Terminal: Purchase information (product name, price, purchase date and time, purchase store, etc.) is automatically collected and sent to the server.

[1068] Server: Receives the purchase information and stores it in a database.

[1069] Input: Purchase information (product name, price, purchase date and time, purchase store, etc.)

[1070] Output: Purchasing information stored in the database

[1071] Step 2:

[1072] Data analysis

[1073] Server: Retrieves data from the purchase history database and applies machine learning algorithms (e.g., K-means clustering) to analyze user purchasing patterns.

[1074] Input: Purchasing information stored in the database

[1075] Output: Analysis of user purchasing patterns

[1076] Specific operation: Features are extracted from purchase history data and classified into patterns using the K-means clustering algorithm.

[1077] Step 3:

[1078] Coupon Generation

[1079] Server: Based on the data analysis results, generate coupons for each user using rule-based or generative AI models.

[1080] Input: Analysis of user purchasing patterns

[1081] Output: Individually optimized coupons for each user

[1082] How it works: Based on purchasing patterns, coupon rules that are likely to lead to the next purchase are applied, and appropriate coupons are generated using a generative AI model.

[1083] Step 4:

[1084] Coupon distribution

[1085] Server: The generated coupon is sent to the user's device via push notification or email.

[1086] Terminal: Display received coupon notifications to users.

[1087] Input: User-optimized coupon

[1088] Output: Coupon notification delivered to user's device

[1089] Specific behavior: Push notifications and emails are sent depending on when the coupon is generated and the user's purchasing patterns.

[1090] Step 5:

[1091] Coupon usage and data collection

[1092] User: Uses a coupon when purchasing an item in a physical store.

[1093] Terminal: Displays the coupon's QR code or barcode and is scanned at the store.

[1094] Server: Collects coupon usage information (date and time of use, discount amount, store used, etc.) and stores it in a database.

[1095] Input: Coupon usage information (usage date and time, discount amount, store used, etc.)

[1096] Output: Coupon usage information stored in the database

[1097] Specific operation: Collects information generated when a user uses a coupon in real time and stores it in a database.

[1098] Step 6:

[1099] Reanalysis of usage data

[1100] Server: Re-analyze the collected coupon usage data together with purchase history data to optimize the parameters of the coupon generation algorithm.

[1101] Input: Coupon usage information and purchase history data stored in the database

[1102] Output: The new coupons reflected in the updated algorithm parameters and the next coupon generation.

[1103] What it does: Use the reanalyzed data to evaluate the performance of the algorithm and optimize it using techniques like A / B testing.

[1104] (Application example 1)

[1105] 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."

[1106] Conventional coupon distribution systems were able to generate and distribute coupons based on user purchasing information. However, there had been little research into how to generate and distribute individually optimized advertisements based on users' purchasing patterns. As a result, they were unable to provide information tailored to users' preferences or deliver effective advertisements, resulting in reduced advertising effectiveness.

[1107] 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.

[1108] In this invention, the server includes means for collecting user purchasing information, means for analyzing the collected purchasing information, means for generating coupons based on the analysis results, means for distributing the generated coupons to user terminals, means for collecting user coupon usage data, means for performing data analysis again based on the collected coupon usage data, means for generating individually optimized advertisements based on the collected and analyzed purchasing information, and means for distributing the generated advertisements to user terminals. This makes it possible to provide optimal coupons and advertisements based on the user's purchasing patterns and to deliver information that matches the user's interests and preferences in a timely manner.

[1109] "Means for collecting user purchasing information" refers to devices or software for collecting purchasing data including information on the products purchased by users, the date and time of purchase, and the place of purchase.

[1110] "Means for analyzing collected purchasing information" refers to devices or software that analyze collected purchasing data and understand users' preferences and purchasing patterns.

[1111] The "means for generating coupons based on the analysis results" refers to a device or software for creating coupons suited to users based on the analysis results of purchase data.

[1112] The "means for delivering the generated coupon to the user's terminal" refers to a device or software for sending the generated coupon to the user's smartphone or other terminal.

[1113] "Means for collecting user coupon usage data" refers to a device or software for collecting coupon usage information used by users.

[1114] The "means for re-analyzing data based on collected coupon usage data" refers to a device or software for analyzing coupon usage data and determining the effectiveness and optimization of coupons.

[1115] "Means for generating individually optimized advertisements based on collected and analyzed purchasing information" refers to a device or software for creating advertisements that are optimal for users based on the results of collecting and analyzing purchasing data.

[1116] "Means for delivering the generated advertisement to the user's terminal" means a device or software for sending the generated advertisement to the user's smartphone or other terminal.

[1117] The present invention is a system for generating and distributing advertisements and coupons that are individually optimized based on a user's purchasing information and preferences. An embodiment of the system will be described in detail below.

[1118] composition

[1119] The system mainly consists of a server and a user terminal. The server collects and analyzes purchase information, and generates and distributes coupons and advertisements. The user terminal receives and displays coupons and advertisements.

[1120] Hardware used

[1121] server

[1122] High-performance computer or cloud server (e.g. AWS, Google Cloud, Azure)

[1123] User Device

[1124] Smartphone

[1125] tablet

[1126] Software used

[1127] Machine learning algorithms (e.g., scikit-learn, TensorFlow)

[1128] Digital payment apps (e.g., PayPay)

[1129] Push notification API (e.g. Firebase Cloud Messaging)

[1130] Ad generator (e.g. Python script)

[1131] Algorithms for analyzing advertising effectiveness (e.g., R language, Python)

[1132] System Operation

[1133] 1. Data Collection

[1134] The server collects information when a user makes a purchase using the digital payment app, including the type of product purchased, the price, the date and time of the purchase, and the location of the purchase.

[1135] The collected purchasing information is stored in a database.

[1136] 2. Data analysis

[1137] The server analyzes the collected purchasing information using machine learning algorithms and clustering techniques (e.g., K-means) to understand users' purchasing patterns and interests.

[1138] The analysis results are used as data to generate optimal advertisements and coupons based on each user's different purchasing history and preferences.

[1139] 3. Coupon generation and distribution

[1140] The server generates the most suitable coupon for each user based on the analysis results and delivers it to the user's device via push notification, allowing the user to receive rewards based on their purchasing behavior.

[1141] 4. Ad generation and delivery

[1142] The server generates individually optimized advertisements based on the collected and analyzed purchasing information and delivers them to the user's device.

[1143] Advertisements are designed to be delivered to users at the right time.

[1144] 5. Data Reanalysis

[1145] The server collects and reanalyzes coupon and advertisement usage data, which can be reflected in the next coupon and advertisement generation.

[1146] In addition, the effectiveness of coupons and advertisements is optimized through A / B testing to improve the next generation algorithm.

[1147] Specific examples

[1148] A specific example of the operation of the system will be shown below.

[1149] 1. Data Collection

[1150] Server: A user purchases clothing from an online store using a digital payment app. The server collects and stores this purchase information.

[1151] User: Information is collected automatically when users make digital payments, without any action on their part.

[1152] 2. Data analysis

[1153] Server: Based on the user's purchasing history, a machine learning model (e.g., K-means clustering) is used to determine the user's interest in fashion products.

[1154] 3. Coupon generation and distribution

[1155] Server: Generate a coupon for the user to redeem for 10% off their next fashion purchase.

[1156] Device: A notification of coupon generation will be sent to the user's smartphone.

[1157] 4. Ad generation and delivery

[1158] Server: Generates the most suitable fashion sale ad for the user and delivers it to their smartphone via push notification.

[1159] Device: A user sees an ad on their phone saying, "Sale at your local store!"

[1160] 5. Data Reanalysis

[1161] Server: Collects information about purchases made by users using coupons and reflects it in the next coupon and ad generation. Also, reanalyzes ad click rates and conversion rates to extract optimal ad delivery patterns.

[1162] Prompt Sentence Examples

[1163] "Create a program that generates the best fashion sale ads for users and analyzes the data to improve the ads for the next time."

[1164] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1165] Step 1:

[1166] The server collects purchase information when a user purchases a product using a digital payment app. The input data includes product information, purchase date and time, purchase location, and payment information. This data is stored in a database. For example, when a user purchases clothing from an online shop using a smartphone, the server collects and stores the purchase information.

[1167] Step 2:

[1168] The server analyzes the collected purchasing information using machine learning algorithms. The collected purchasing data is used as input. Data processing involves filtering out unnecessary data and converting it into an appropriate format. Data calculation involves applying clustering techniques (e.g., K-means) to identify the user's purchasing patterns and preferences. The output is the analysis results (such as the product categories the user is interested in). For example, it may be analyzed that the user frequently purchases fashion items.

[1169] Step 3:

[1170] The server generates the most suitable coupon for the user based on the results of the data analysis. The data analysis results are used as input. The data is processed by referring to the user's purchasing history and preferences to create coupon data related to specific products and categories. The generated coupon data is obtained as output. For example, a 10% discount coupon that can be used on the next purchase of fashion products is generated.

[1171] Step 4:

[1172] The server delivers the generated coupon to the user's device. The generated coupon data is used as input. The data is calculated using a push notification API (e.g., Firebase Cloud Messaging) to send the data. The output is a coupon notification displayed on the user's smartphone. For example, a notification may be delivered to the user's smartphone stating, "You've received a 10% discount coupon that can be used on your next fashion purchase!"

[1173] Step 5:

[1174] The server generates individually optimized advertisements based on the collected and analyzed purchasing information. It uses the purchasing information and analysis results as input. It processes the data by creating advertising content tailored to the user's preferences. It calculates the data by using an advertisement generation program to generate advertising data. It obtains the generated advertising data as output. For example, it generates an advertisement for a fashion sale that the user is interested in.

[1175] Step 6:

[1176] The server delivers the generated advertisement to the user's device. The generated advertisement data is used as input. The data calculation uses a push notification API to send the advertisement data. The output is the advertisement displayed on the user's smartphone. For example, a notification saying "There's a fashion sale at a nearby shop!" is delivered.

[1177] Step 7:

[1178] The server collects coupon and ad usage data and reanalyzes it. It uses user coupon usage information and ad click information as input. It processes the data by appropriately filtering it and creating a dataset for reanalysis. It performs data calculations, including reanalysis of the results of A / B testing, and reflects them in the next coupon and ad generation algorithm. It obtains optimized algorithm parameters as output. For example, it analyzes the types and durations of coupons used by users in the past and extracts elements for optimal coupon generation.

[1179] 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.

[1180] This invention relates to a system that collects user purchasing information and emotional data, and generates and distributes optimized coupons based on the analysis results. This system operates in cooperation with a server, terminals, and users, with the aim of improving the user experience.

[1181] Explanation of program processing

[1182] The program for this system consists of a series of processes that collect and analyze users' purchasing information and emotional data, and then deliver the most appropriate coupons at the right time. The specific processing flow is explained below.

[1183] 1. Data Collection

[1184] Server: When a user makes a payment, information about the purchased item (product name, price, purchase date and time, purchase location, etc.) and the user's emotional data (for example, facial expression analysis using facial recognition or emotional state obtained from voice analysis) are collected and stored in a database.

[1185] User: Uses digital payments and also provides emotional data via the device's camera and microphone, which is automatically sent to the server.

[1186] 2. Data analysis

[1187] Server: Analyzes the collected purchasing information and sentiment data using machine learning models and data analysis algorithms. Applying clustering techniques, the server creates groups of users with similar purchasing patterns and sentiment data.

[1188] User: No action is required, everything is handled automatically in the backend.

[1189] 3. Coupon Generation

[1190] Server: Based on the analysis results, generate coupons that best fit the user's purchasing history and emotional state. For example, if a user shows signs of joy when purchasing milk, generate a discount coupon for that user that can be used on their next purchase.

[1191] Device: The user will receive a notification on their smartphone that a coupon has been generated.

[1192] 4. Coupon distribution

[1193] Server: Generates and delivers the coupon to the user's mobile device via push notification, SMS, or email.

[1194] On the device: The coupon details are displayed and the user can view them.

[1195] 5. Displaying and Using Coupons

[1196] User: Purchases a product using a coupon. For example, they use a coupon to buy milk at the supermarket.

[1197] Terminal: The coupon's QR code or coupon code is displayed and can be scanned at the store to be used.

[1198] 6. Coupon usage data collection

[1199] Terminal: When a coupon is used, usage information is generated in real time.

[1200] Server: Collects coupon usage data (date and time of use, store used, discount amount, etc.) and stores it in a database.

[1201] 7. Reanalysis of usage data and feedback

[1202] Server: Reanalyzes the collected coupon usage data and emotional data and reflects it in the next coupon generation algorithm. In particular, it evaluates how emotional state affects coupon usage, enabling it to provide coupons with optimal timing and content.

[1203] Specific examples

[1204] 1. Data Collection

[1205] Server: Mr. Sato purchases chocolate at a supermarket using digital payment, and facial expression data is collected using a camera. It is recorded that Mr. Sato has a surprised expression on his face when he makes the purchase.

[1206] Users: No action is required; information is automatically transmitted via the smartphone camera and payment app.

[1207] 2. Data analysis

[1208] Server: Analyzes Mr. Sato's purchasing history and facial expression data and finds out that he enjoys buying chocolate.

[1209] 3. Coupon Generation

[1210] Server: Generate a coupon for Sam for 10% off her next chocolate purchase.

[1211] Device: Send a notification to Sato's smartphone saying, "Your next chocolate purchase will be 10% off!"

[1212] 4. Coupon distribution

[1213] Server: Once the coupon is generated, it is sent to Mr. Sato's smartphone.

[1214] Device: A notification appears and Sato checks the coupon details.

[1215] 5. Displaying and Using Coupons

[1216] User: The next time Sam buys chocolate at the supermarket, he uses the coupon displayed on his smartphone.

[1217] Terminal: A QR code or coupon code is displayed and can be used by the store clerk by scanning it.

[1218] 6. Coupon usage data collection

[1219] Server: Information about when Sato used the 10% off coupon (date and time of use, store used, discount amount) is saved in the database.

[1220] 7. Reanalysis of usage data and feedback

[1221] Server: Reanalyzes Sato's coupon usage data and facial expression data and reflects them in the next coupon generation. It also evaluates the effectiveness of coupons based on facial expressions and provides the most appropriate coupon.

[1222] This will allow for the use of emotional data to create a more personalized user experience and encourage greater adoption of digital payments.

[1223] The processing flow will be explained below.

[1224] Step 1: Data collection

[1225] Server: When a user makes a payment, information about the purchased item (product name, price, purchase date and time, purchase location, etc.) is collected. Emotional data is also collected at the same time. This includes facial recognition technology using the user's smartphone camera and estimation of emotional state through voice analysis. All information is automatically stored in a database.

[1226] User: When making a digital payment, the smartphone camera and microphone are activated to collect emotional data from facial expressions and voice, without any action required.

[1227] Step 2: Data analysis

[1228] Server: Analyzes the collected purchasing information and sentiment data. Machine learning algorithms are used to identify trends in users' purchasing patterns and sentiment, and clustering techniques are used to form user groups with similar characteristics.

[1229] 1. Aggregate each user's purchasing history and calculate frequency and average spending.

[1230] 2. Analyze emotional data to identify typical emotional states at the time of purchase (e.g., joy, surprise, sadness, etc.).

[1231] Step 3: Generate coupon

[1232] Server: Based on the results of data analysis, the server generates personalized coupons for each user, taking into account the user's purchasing history and emotional state. For example, if a user always looks happy when buying milk, the server generates a discount coupon for the next milk purchase.

[1233] 1. Set details such as the coupon discount rate, terms of use, and expiration date.

[1234] 2. Generate different versions of the coupon using A / B testing, if necessary.

[1235] Step 4: Coupon Delivery

[1236] Server: Delivers the generated coupons to the user's device via channels such as push notification, SMS, or email.

[1237] 1. Calculate and set the optimal transmission timing for each user.

[1238] 2. After sending, use a tracking system to check whether the user received the notification.

[1239] Step 5: View and redeem coupons

[1240] On your device: Open the notification you received and check the coupon details. The coupon's QR code and coupon code will be displayed.

[1241] 1. The coupon details clearly state the applicable conditions and expiration date.

[1242] 2. Allow users to present and redeem coupons at the time of purchase.

[1243] Step 6: Collect coupon usage data

[1244] Terminal: When a coupon is used, usage information (date and time of use, store used, discount amount, etc.) is generated in real time.

[1245] Server: Stores the collected coupon redemption data in a database for subsequent analysis.

[1246] Step 7: Reanalyze usage data and provide feedback

[1247] Server: Reanalyze the collected coupon usage data and emotion data to determine which coupons were most effective for users in which emotional states.

[1248] 1. Calculate coupon performance evaluation indicators based on usage data.

[1249] 2. Reflect this data in the next coupon generation to provide effective coupons.

[1250] Specific processing examples

[1251] Step 1:

[1252] Server: When Mr. Sato makes a payment at the supermarket, his chocolate purchase information and facial expression data captured by the camera at the time are collected.

[1253] Step 2:

[1254] Server: Analyzes Mr. Sato's viewing data to see that he enjoys chocolate when he buys it. Also, based on his past purchase history, we know that he buys chocolate regularly.

[1255] Step 3:

[1256] Server: Generate a 10% off coupon for your next chocolate purchase.

[1257] Step 4:

[1258] Server: Send a notification to Mr. Sato's smartphone saying, "Your next chocolate purchase will be 10% off!"

[1259] Step 5:

[1260] Device: A notification appears and Sato checks the coupon details.

[1261] Step 6:

[1262] Device: The next time Sato buys chocolate at the supermarket, he will present and use the coupon.

[1263] Step 7:

[1264] Server: Collects data on Sato's coupon usage (date and time of use, store used, discount amount, etc.) and reflects this in the next coupon generation. It also associates emotional data with the effectiveness of coupon usage and reanalyzes it.

[1265] Example 2

[1266] 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."

[1267] In modern society, the spread of digital payments has created a demand for personalized services based on user purchasing behavior. However, conventional systems have focused on analyzing only purchase information, making it difficult to provide personalized services that take user emotions into account. Furthermore, optimization to increase the effectiveness of coupons has been insufficient. This has created challenges in improving user experience and promoting service usage.

[1268] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting user purchase information, means for collecting user emotion data, means for analyzing the collected purchase information and emotion data, means for generating coupons based on the analysis results, means for distributing the generated coupons to the user's terminal, means for collecting user coupon usage data, and means for performing data re-analysis based on the collected coupon usage data. This makes it possible to timely distribute personalized coupons that take user emotions into consideration, maximize the effectiveness of coupon usage, and improve the user experience.

[1269] "User purchasing information" refers to information about the products purchased by the user (product name, price, purchase date and time, purchase location, etc.).

[1270] "User emotional data" refers to data that indicates the user's emotional state, including facial expression analysis using facial recognition, voice analysis, and other sensor data.

[1271] "Collection Method" refers to the technology or device that obtains information from users and stores it in a database or other storage medium.

[1272] "Analytical means" refers to software algorithms and data analysis tools used to analyze collected data and extract meaningful information and patterns.

[1273] "Coupon Generation Means" means software and algorithms for generating coupons containing offers or discounts to offer to Users based on the results of data analysis.

[1274] "Means for delivering coupons to users' devices" refers to the technology or method for sending generated coupons to users' devices such as smartphones or tablets.

[1275] "Means for collecting coupon usage data" refers to a system or device that collects and records information when a user uses a coupon (such as the date and time of use, the store where the coupon was used, and the discount amount).

[1276] "Means for re-analyzing data" refers to technologies and methods for analyzing newly collected coupon usage data, separate from the initial data collection, and reflecting the results in generating the next coupon.

[1277] MODE FOR CARRYING OUT THE INVENTION

[1278] The present invention relates to a system that collects user purchasing information and emotional data, and generates and distributes optimized coupons based on that information. This system operates in cooperation with a server, terminals, and users, with the aim of improving the user experience. Specific embodiments are described below.

[1279] Data collection

[1280] The server works in conjunction with the electronic payment system to collect information on products purchased by users in real time (product name, price, purchase date and time, purchase location, etc.). This is done using an API linked to the POS system. The server also uses the device's camera and microphone to obtain user emotional data (facial expression analysis and voice analysis) and stores this in a database. Possible tools used include Python's OpenCV library and voice analysis library.

[1281] Users provide the necessary emotional data by using the device's camera and microphone in a natural way when making digital payments, so data is collected without any special action required.

[1282] Data analysis

[1283] The server integrates the collected purchasing information and sentiment data and performs analysis using machine learning models and data analysis algorithms. Specifically, it uses Python's Scikit-learn library to form user groups using clustering algorithms (K-means and DBSCAN). This makes it possible to identify users with similar purchasing patterns and sentiment data.

[1284] Coupon Generation

[1285] The server generates the most suitable coupon for the user based on the data analysis results. For example, if the user has a happy expression when purchasing chocolate, the server generates a coupon for 10% off the next chocolate purchase. This process is performed using software with a coupon generation algorithm.

[1286] Example prompt for coupon generation: "If the user purchases chocolate and has a happy expression when purchasing, generate a coupon for 10% off."

[1287] Coupon distribution

[1288] The server then delivers the generated coupon to the user's mobile device via push notification, SMS, or email. APIs used include Firebase Cloud Messaging (FCM) and Amazon SNS (Simple Notification Service).

[1289] The device will then display the details of the coupon to the user, using a mobile app to receive and display notifications.

[1290] Viewing and Using Coupons

[1291] Users can use the coupons they receive to purchase products, such as milk at a supermarket, by using the coupon displayed on their smartphone screen.

[1292] The terminal displays the coupon's QR code or barcode, which can then be scanned at the store using the mobile device's camera.

[1293] Coupon usage data collection

[1294] The server collects information when a user uses a coupon (such as the date and time of use, the store where it was used, and the discount amount) and stores it in a database. By linking with the POS system, usage information is collected in real time.

[1295] Reanalysis of usage data and feedback

[1296] The server re-analyzes the collected coupon usage data and sentiment data and reflects it in the next coupon generation algorithm. This allows for more effective and personalized coupons to be provided. Specific analysis is performed using the aforementioned Python library and analysis tools.

[1297] Through this series of processes, the system can generate and distribute personalized coupons in a timely manner that takes into account the user's purchasing behavior and emotional state, which is expected to improve the user experience and promote the use of digital payments.

[1298] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1299] Step 1: Data collection

[1300] The server collects data from the POS system and the terminal's camera and microphone. The POS system receives the user's purchase information (product name, price, purchase date and time, purchase location, etc.), and the camera and microphone collect the user's emotional data (facial expression data and voice data). This data is stored in a secure database.

[1301] Input: Purchase information from the POS system, emotion data from the device's camera and microphone.

[1302] Output: A database containing purchasing information and sentiment data.

[1303] Specific operation: The server communicates with the POS system via API to obtain real-time purchase data. Emotion data from the device is captured using the camera and microphone and sent to the server.

[1304] Step 2: Data analysis

[1305] The server integrates the collected purchasing information and emotional data and analyzes them using data analysis algorithms and machine learning models (for example, clustering algorithms using Python's Scikit-learn library). This allows the server to cluster users' purchasing patterns and emotional states and form specific user groups.

[1306] Input: Purchase information and sentiment data stored in a database.

[1307] Output: Clustered user population data.

[1308] How it works: The server extracts purchasing information and emotional data from the database and inputs them into a clustering algorithm, which then forms groups of users with similar purchasing patterns and emotional states.

[1309] Step 3: Generate coupon

[1310] The server generates the most suitable coupon for the user based on the analysis results. For example, if a user has a happy expression when purchasing chocolate, the server generates a 10% off coupon for the user's next chocolate purchase.

[1311] Input: Clustered user group data and analysis results of each user's purchasing and sentiment data.

[1312] Output: The generated coupon data.

[1313] How it works: The server determines which coupon is best suited to which user based on purchasing patterns and sentiment data, then runs a coupon generation algorithm to generate coupons, which are then stored in a coupon database.

[1314] Step 4: Coupon Delivery

[1315] The server then delivers the generated coupon to the user's mobile device via push notification, SMS, or email.

[1316] Input: Generated coupon data and user contact information.

[1317] Output: The coupon notification delivered.

[1318] Specific operation: The server uses the user's contact information to select the appropriate delivery method (push notification, SMS, email) and send the coupon. The notification is delivered to the user's device using Firebase Cloud Messaging (FCM) or Amazon SNS.

[1319] Step 5: View and redeem coupons

[1320] Users can use the coupons they receive to purchase products, such as milk at a supermarket, by using the coupon displayed on their smartphone screen.

[1321] Input: The coupon notification the user received.

[1322] Output: Purchase data using coupons.

[1323] What it does: The user shows the coupon displayed on the device to the store clerk and has them scan the QR code or barcode, which applies the discount.

[1324] Step 6: Collect coupon usage data

[1325] The server collects information when a user uses a coupon and stores it in a database, including the date and time of use, the store where the coupon was used, and the discount amount.

[1326] Input: Transaction information when the coupon was redeemed.

[1327] Output: A database containing coupon redemption data.

[1328] Specific operation: The server obtains coupon usage data from the POS system and stores it in a database. Since usage data is collected in real time, it is updated immediately.

[1329] Step 7: Reanalyze usage data and provide feedback

[1330] The server reanalyzes the collected coupon usage data and emotional data and incorporates it into the next coupon generation algorithm, particularly evaluating how emotional states affect coupon usage.

[1331] Input: Coupon redemption data and sentiment data stored in a database.

[1332] Output: An improved coupon generation algorithm.

[1333] How it works: The server retrains the machine learning model based on newly collected coupon usage data to improve the accuracy of the next coupon generation, enabling it to provide more effective personalized coupons.

[1334] Through each of these processing steps, the system can improve the user experience and promote the use of digital payments.

[1335] (Application example 2)

[1336] 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."

[1337] Conventional coupon distribution systems generate coupons based only on a user's purchase history, making it difficult to provide coupons that reflect the user's current emotional state and purchasing patterns. This has led to challenges in delivering coupons at the optimal time for users and generating more effective coupons.

[1338] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user purchasing information, means for analyzing the collected purchasing information and emotional data, means for clustering purchasing patterns and emotional data using a machine learning model, means for generating coupons based on the analysis results, means for delivering the generated coupons to the user's terminal, means for displaying the delivered coupons, means for collecting user coupon usage data, and means for performing further data analysis based on the collected coupon usage data. This makes it possible to provide more personalized and effective coupons based on the user's current emotional state and purchasing patterns.

[1339] "Purchase information" refers to information obtained when a user purchases a product or service, and specifically includes data such as the product name, price, purchase date and time, and purchase location.

[1340] "Emotional data" refers to data that represents the emotional state of the user, and specifically includes information on the emotional state obtained from facial expression recognition and voice analysis.

[1341] A "machine learning model" refers to an algorithm or method that learns patterns and rules based on collected data and makes future predictions and classifications.

[1342] "Clustering" is a method of grouping data with similar characteristics, and is used to analyze user purchasing patterns and emotional data to form similar user groups.

[1343] "Coupon" refers to a ticket or code that allows a user to receive a discount or benefit on their next purchase.

[1344] The term "terminal" refers to an electronic device used by a user, including a smartphone, which in the present invention is used to receive and display coupons.

[1345] The "database" is a system for efficiently storing and managing collected purchasing information, emotional data, and coupon usage data.

[1346] "Analysis results" refers to conclusions and insights derived from collected purchasing information and sentiment data using machine learning models and data analysis algorithms.

[1347] "Coupon usage data" refers to data when a user actually uses a coupon, and includes information such as the date and time of use, the store where the coupon was used, and the discount amount.

[1348] "Push notification" is a function in which a server sends information to a user's device in real time, and is used to distribute generated coupons.

[1349] "Reanalysis" is the process of conducting further analysis based on data that has already been collected to find new insights and areas for improvement.

[1350] The present invention provides a system for collecting user purchasing information and emotional data, analyzing the data, and generating personalized coupons. This system has the following configuration.

[1351] Hardware and Software Configuration

[1352] The server includes means for collecting user purchasing information, means for analyzing the collected purchasing information and emotional data, means for clustering purchasing patterns and emotional data using a machine learning model (such as TensorFlow or PyTorch), means for generating coupons based on the analysis results, means for delivering the generated coupons to the user's device, means for displaying the delivered coupons, means for collecting coupon usage data from users, and means for performing data analysis again based on the collected coupon usage data.

[1353] Processing the data

[1354] When a user purchases an item on an online shopping site, the server collects information about the purchased item (item name, price, purchase date and time, purchase location, etc.) and the item being viewed. It also obtains the user's emotional data (emotional state obtained from facial expression recognition and voice analysis) via the camera and microphone and stores it in a database (MySQL, MongoDB, etc.).

[1355] The server then analyzes the collected purchasing information and sentiment data using machine learning models and data analysis algorithms (e.g., clustering techniques). This process forms groups of users with similar purchasing patterns and sentiment data.

[1356] Based on the analysis, the server generates coupons that best fit the user's purchasing history and emotional state. For example, if a user is excited about buying a new gadget, the server generates a discount coupon for the user's next gadget purchase.

[1357] The generated coupon is sent from the server to the user's device via push notification (e.g., Firebase Cloud Messaging). Detailed coupon information is displayed on the user's device, allowing the user to check and use the coupon. When the user uses the coupon during their next purchase, usage information is generated in real time and stored in a database.

[1358] The collected coupon usage data will be analyzed again and reflected in the next coupon generation algorithm, allowing for more personalized coupons based on the user's emotional state and purchasing patterns.

[1359] Specific examples

[1360] For example, when User A purchases a gadget on an online shopping site, the camera captures his or her excited facial expression. The server then generates a 10% off coupon that can be applied to User A's future gadget purchases and sends it to User A's smartphone via push notification. When User A uses the coupon on their next purchase, information such as the date and time of use, the store where it was used, and the discount amount is collected and stored in a database. This data is used for the next analysis to help regenerate the most appropriate coupon for User A.

[1361] Prompt Sentence Examples

[1362] "Please propose an algorithm that analyzes user purchasing patterns based on emotional data and generates optimal coupons."

[1363] "Generate the best coupon using the following user data: User A: Purchase history [gadgets, books], Emotion data [excitement, joy]"

[1364] In this way, the present invention can provide more personalized coupons based on a user's emotional state and purchasing patterns.

[1365] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1366] Step 1:

[1367] The server collects the user's purchasing information and emotional data. The purchasing information includes the product name, price, purchase date and time, and purchase location. The emotional data is facial recognition and voice analysis data obtained through the device's camera and microphone. This data is sent to the server and stored in a database. The input is the information obtained when the user purchases a product on an online shopping site, and the output is the purchasing information and emotional data stored in the database.

[1368] Step 2:

[1369] The server analyzes the purchasing information and emotional data stored in the database using machine learning models (such as TensorFlow or PyTorch) and data analysis algorithms. It uses clustering techniques to form user groups with similar purchasing patterns and emotional data. The input is the purchasing information and emotional data stored in the database, and the output is the clustering results. Specifically, the machine learning algorithm analyzes the data and forms user groups.

[1370] Step 3:

[1371] The server generates a coupon that best suits the user's purchase history and emotional state based on the clustering results. For example, if a user is excited while purchasing a gadget, it generates a coupon that can be used for the user's next gadget purchase. The input is the clustering results and the user's emotional data, and the output is the generated coupon. Specifically, the server runs a coupon generation algorithm to create the optimal coupon.

[1372] Step 4:

[1373] The server delivers the generated coupon to the user's device via push notification (e.g., Firebase Cloud Messaging). The input is the generated coupon, and the output is the coupon notification delivered to the user's device. Specifically, the server sends detailed coupon information using a push notification service.

[1374] Step 5:

[1375] The terminal displays detailed coupon information to the user, who can then check and use the coupon. The input is the delivered coupon notification, and the output is the displayed coupon information. Specifically, the terminal activates a function to display coupon details on the screen.

[1376] Step 6:

[1377] When a user uses a coupon to purchase a product, the terminal displays the coupon code and automatically applies it at the time of purchase. The input is the coupon information the user wants to use, and the output is the applied coupon information. Specifically, the terminal's coupon code display function is activated and the code is entered.

[1378] Step 7:

[1379] When a coupon is used, the server collects usage information (date and time of use, store used, discount amount, etc.) in real time and stores it in a database. The input is the information at the time of coupon use, and the output is the coupon usage information stored in the database. Specifically, the server's data collection function is activated and the information is added to the database.

[1380] Step 8:

[1381] The server reanalyzes the collected coupon usage data and sentiment data and reflects it in the next coupon generation algorithm. The input is the coupon usage data and sentiment data stored in the database, and the output is the reanalysis results. Specifically, the server runs the data analysis algorithm again and uses the insights gained to help generate the next coupon.

[1382] 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.

[1383] 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.

[1384] 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.

[1385] [Fourth embodiment]

[1386] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1387] 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.

[1388] 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).

[1389] 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.

[1390] 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.

[1391] 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).

[1392] 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.

[1393] 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.

[1394] 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.

[1395] 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.

[1396] 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.

[1397] 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.

[1398] 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."

[1399] This invention relates to a system that collects and analyzes user purchasing information and generates and distributes individually optimized coupons. This system includes multiple software modules that run on a server, and effectively performs the collection of purchasing information, data analysis, coupon generation, coupon distribution, and reanalysis of usage data.

[1400] Explanation of program processing

[1401] The program of this system operates in conjunction with each step as follows:

[1402] 1. Data Collection

[1403] Server: Collects information about the products purchased by users and stores it in a database, including the type of product, price, purchase date and time, and location.

[1404] User: When making a purchase, purchase information is automatically sent to the server by using digital payment methods such as PayPay.

[1405] 2. Data analysis

[1406] Server: The collected purchasing information is analyzed using machine learning algorithms. Here, clustering techniques are applied to understand users' purchasing patterns and preferences.

[1407] User: No special action is required, everything is handled in the backend.

[1408] 3. Coupon Generation

[1409] Server: Generates the most suitable coupon for each user based on the data analysis results. For example, for a user who frequently buys milk on weekends, a discount coupon is created that can be used on the next purchase of milk.

[1410] Device: The coupon generation notification will be sent to the user's mobile device.

[1411] 4. Coupon distribution

[1412] Server: Send coupons via push notifications or emails at the optimal timing based on the user's purchasing patterns.

[1413] On the device: The coupon details are displayed and the user can review them.

[1414] 5. Coupon Usage and Data Collection

[1415] User: Uses the coupon provided to make a purchase. For example, uses the coupon to buy milk at the supermarket.

[1416] Terminal: When using a coupon, the QR code or coupon code is displayed and scanned at the store.

[1417] Server: Information about coupon usage (e.g., usage date and time, discount amount, store used, etc.) is collected and stored in a database.

[1418] 6. Reanalysis of usage data

[1419] Server: Re-analyzes coupon usage data and reflects it in the next coupon generation algorithm, which also performs A / B testing and optimization to maximize coupon effectiveness.

[1420] Specific examples

[1421] 1. Data Collection

[1422] Server: When Tanaka purchases milk at the supermarket using digital payment, that information is collected and stored.

[1423] User: Tanaka doesn't have to do anything special; information is collected automatically when he uses digital payments.

[1424] 2. Data analysis

[1425] Server: Run Tanaka's purchasing history through a machine learning model and determine that he frequently purchases milk.

[1426] 3. Coupon Generation

[1427] Server: Generate a coupon for Tanaka to use on his next milk purchase for 100 yen off.

[1428] Device: A notification is sent to Tanaka's smartphone that a coupon has been generated.

[1429] 4. Coupon distribution

[1430] Server: When a triggering purchasing pattern is detected, a coupon is sent via push notification.

[1431] Device: Tanaka's smartphone displays a notification saying, "You've received a coupon for 100 yen off milk!"

[1432] 5. Coupon Usage and Data Collection

[1433] User: Tanaka uses the coupon to purchase milk.

[1434] Terminal: The coupon's QR code will be displayed and scanned by the store clerk.

[1435] Server: Receives coupon redemption information and stores it in a database.

[1436] 6. Reanalysis of usage data

[1437] Server: Reanalyzes the collected coupon usage data and reflects it in generating the next coupon for Tanaka. It also extracts the parameters of effective coupons and improves the overall coupon generation algorithm.

[1438] As a result, the present invention provides optimal coupons based on the user's purchasing behavior, promoting the use of specific payment services and improving the user experience.

[1439] The processing flow will be explained below.

[1440] Step 1: Data collection

[1441] Server: When a user makes a payment, the server collects information about the purchased product (product name, price, purchase date and time, purchase store information, etc.) and payment information in real time. It connects with digital payment platforms such as PayPay and automatically stores this information in a database.

[1442] Users: No special action is required to use digital payments.

[1443] Step 2: Data analysis

[1444] Server: Uses machine learning models and data analysis algorithms to analyze the collected purchasing information. Uses clustering techniques to create groups of users with similar purchasing patterns.

[1445] 1. Organize users' purchasing history over time to understand frequency and trends.

[1446] 2. For each user, analyze their past purchase preferences and predict what they are likely to buy next.

[1447] Step 3: Generate coupon

[1448] Server: Generates optimal coupons for users based on insights gained from data analysis. For example, if a user has recently purchased milk frequently, a discount coupon will be created for the next purchase of milk.

[1449] 1. Decide on the coupon content (discount rate, terms of use, expiration date, etc.).

[1450] 2. When generating a coupon, you can also create multiple versions for A / B testing.

[1451] Step 4: Coupon Delivery

[1452] Server: Delivers the generated coupons to the user's mobile device using different channels such as push notification, SMS, or email.

[1453] 1. Set optimal sending times for each communication channel.

[1454] 2. After sending, track whether the notification has been opened by the user.

[1455] Step 5: View and redeem coupons

[1456] Device: When a user receives a coupon, they will be notified and the QR code or coupon code will be displayed on the coupon details screen.

[1457] 1. The coupon screen will display details such as application conditions and expiration date.

[1458] 2. The user presents and uses the coupon when making a purchase at the store.

[1459] Step 6: Collect coupon usage data

[1460] Terminal: When a coupon is redeemed, usage information is generated in real time.

[1461] Server: Collects coupon usage data (date and time of use, store used, discount amount, etc.) and stores it in a database.

[1462] Step 7: Reanalyze usage data and provide feedback

[1463] Server: Reanalyze the coupon usage data collected, particularly to evaluate which types of coupons were most effective for which user groups.

[1464] 1. Calculate an index to evaluate coupon performance based on usage data.

[1465] 2. By providing feedback to the next coupon generation algorithm, more accurate coupons will be provided.

[1466] By repeating this series of steps, it is possible to constantly provide users with optimized deals and promote the use of digital payments.

[1467] Example 1

[1468] 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."

[1469] Conventional coupon issuing systems were unable to fully utilize users' purchasing history and patterns, making it difficult to provide optimal coupons tailored to their purchasing behavior. Furthermore, they were unable to distribute coupons at an effective timing, resulting in low coupon usage rates and low effectiveness in promoting purchases. Furthermore, they lacked a mechanism for evaluating the effectiveness of coupons and reflecting this in the generation of subsequent coupons, making it difficult to continuously improve and provide optimal coupons.

[1470] 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.

[1471] In this invention, the server includes means for collecting user purchasing information using digital payment methods, means for storing the collected purchasing information in a database, and means for analyzing the stored purchasing information using a machine learning algorithm, which makes it possible to understand the purchasing patterns and preferences of users and generate individually optimized coupons.

[1472] The server further includes a means for generating coupons using a rule-based or generative AI model based on the analysis results, a means for notifying or distributing the generated coupons to the user's terminal, a means for collecting usage data when the user uses the coupons, and a means for re-analyzing data based on the collected coupon usage data and optimizing the algorithm, thereby maximizing the effectiveness of the coupons and continuously providing optimized coupons.

[1473] A "digital payment instrument" is a means by which a user pays for goods or services electronically, such as mobile payments or online payment systems.

[1474] "User purchasing information" refers to data generated when a user purchases a product or service, and includes details such as the product name, price, purchase date and time, and store where the purchase was made.

[1475] A "database" is a collection of structured information that stores collected data in a centralized manner and makes it easy to search and analyze as needed.

[1476] A "machine learning algorithm" is a technology in which a computer program automatically learns patterns from data and uses that knowledge to make predictions and classifications.

[1477] "Rule-based" is a system design method that automatically processes data based on predefined rules and conditions.

[1478] A "generative AI model" is an algorithm that uses artificial intelligence technology to generate new information from data, and is particularly used to generate and individually optimize coupons.

[1479] A "Coupon" is an electronic or paper certificate that provides a discount or special offer to a User.

[1480] "Terminal" refers to a device such as a computer, smartphone, or tablet that a user uses to interact with the system.

[1481] A "notification" is a message that conveys information from the system to the user, and is sent in the form of a push notification, email, etc.

[1482] "Coupon usage data" is data generated when a user uses a coupon, and includes information such as the date and time of use, the discount amount, and the store where the coupon was used.

[1483] "Re-data analysis" is the process of conducting analysis again based on the results of the initial data analysis or newly collected data, with the aim of improving the accuracy and effectiveness of the system.

[1484] "Optimization" is the process of adjusting parameters and conditions to maximize the performance of a system or process in order to achieve a specific objective.

[1485] This invention is a system that collects and analyzes user purchasing information and generates and distributes individually optimized coupons. This system includes multiple software modules that run on a server, and effectively collects purchasing information, analyzes data, generates coupons, distributes coupons, and reanalyzes usage data.

[1486] Hardware and Software Configuration

[1487] This system uses the following main hardware and software:

[1488] Server: Use high-performance cloud servers (e.g., AWS, Azure) to process and store data.

[1489] Database: Use a relational database (e.g., MySQL, PostgreSQL) to store purchase information and coupon redemption data.

[1490] Machine learning algorithms: Use algorithms (e.g., K-means clustering) to analyze purchasing patterns.

[1491] Generative AI model: Uses a generative AI model to generate the best coupons for each user.

[1492] User device: Receive and use notifications and coupons on your smartphone or tablet (e.g., iOS, Android).

[1493] Specific operation of the system

[1494] The operation of this system is as follows.

[1495] 1. Data Collection

[1496] When a user purchases a product using digital payment (e.g., PayPay), the server receives the purchase information in real time and stores it in a database. The purchase information includes details such as the product name, price, purchase date and time, and the store where the purchase was made.

[1497] Users simply use normal digital payments without taking any special action and data is collected.

[1498] 2. Data analysis

[1499] The server analyzes the collected purchasing history using machine learning algorithms (e.g., K-means clustering) to group users' purchasing patterns and preferences.

[1500] No user interaction is required - all analysis is handled in the backend.

[1501] 3. Coupon Generation

[1502] Based on the analysis results, the server generates personalized coupons using rule-based or generative AI models. For example, if a user frequently buys milk on weekends, the server generates a discount coupon for the next milk purchase.

[1503] The terminal is notified of the generated coupon.

[1504] 4. Coupon distribution

[1505] The server delivers coupons at appropriate times based on the user's purchasing patterns, using methods including push notifications and emails.

[1506] Users can check the coupon details through a notification on their device, such as "You've received a coupon for 100 yen off milk!"

[1507] 5. Coupon Usage and Data Collection

[1508] When users use a coupon at a physical store, they ask the store clerk to scan the QR code displayed on their smartphone screen.

[1509] The server collects information about when the coupon was used (e.g., the date and time of use, the discount amount, and the store where the coupon was purchased) and stores this information in a database.

[1510] 6. Reanalysis of usage data

[1511] The server reanalyzes the collected coupon usage data and reflects it in the next coupon generation. Coupon effectiveness is evaluated and optimized through A / B testing.

[1512] The user does not need to take any special action.

[1513] Examples of concrete examples and prompts

[1514] For example, when Tanaka purchases milk using digital payment, the purchase information is sent to the server in real time and stored in a database. The server analyzes Tanaka's purchasing patterns and generates a 100 yen discount coupon that can be used the next time Tanaka purchases milk. The coupon is sent to Tanaka's smartphone, and Tanaka uses the coupon to purchase milk again.

[1515] Prompt Sentence Examples

[1516] Please explain the system that uses user purchasing information to generate and distribute optimal coupons.

[1517] This system allows users to easily receive the most suitable coupons simply by making a purchase using digital payments, thereby improving the purchasing experience and encouraging the use of specific payment services.

[1518] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1519] Step 1:

[1520] Data collection

[1521] User: Uses digital payment methods (e.g. PayPay) when purchasing products.

[1522] Terminal: Purchase information (product name, price, purchase date and time, purchase store, etc.) is automatically collected and sent to the server.

[1523] Server: Receives the purchase information and stores it in a database.

[1524] Input: Purchase information (product name, price, purchase date and time, purchase store, etc.)

[1525] Output: Purchasing information stored in the database

[1526] Step 2:

[1527] Data analysis

[1528] Server: Retrieves data from the purchase history database and applies machine learning algorithms (e.g., K-means clustering) to analyze user purchasing patterns.

[1529] Input: Purchasing information stored in the database

[1530] Output: Analysis of user purchasing patterns

[1531] Specific operation: Features are extracted from purchase history data and classified into patterns using the K-means clustering algorithm.

[1532] Step 3:

[1533] Coupon Generation

[1534] Server: Based on the data analysis results, generate coupons for each user using rule-based or generative AI models.

[1535] Input: Analysis of user purchasing patterns

[1536] Output: Individually optimized coupons for each user

[1537] How it works: Based on purchasing patterns, coupon rules that are likely to lead to the next purchase are applied, and appropriate coupons are generated using a generative AI model.

[1538] Step 4:

[1539] Coupon distribution

[1540] Server: The generated coupon is sent to the user's device via push notification or email.

[1541] Terminal: Display received coupon notifications to users.

[1542] Input: User-optimized coupon

[1543] Output: Coupon notification delivered to user's device

[1544] Specific behavior: Push notifications and emails are sent depending on when the coupon is generated and the user's purchasing patterns.

[1545] Step 5:

[1546] Coupon usage and data collection

[1547] User: Uses a coupon when purchasing an item in a physical store.

[1548] Terminal: Displays the coupon's QR code or barcode and is scanned at the store.

[1549] Server: Collects coupon usage information (date and time of use, discount amount, store used, etc.) and stores it in a database.

[1550] Input: Coupon usage information (usage date and time, discount amount, store used, etc.)

[1551] Output: Coupon usage information stored in the database

[1552] Specific operation: Collects information generated when a user uses a coupon in real time and stores it in a database.

[1553] Step 6:

[1554] Reanalysis of usage data

[1555] Server: Re-analyze the collected coupon usage data together with purchase history data to optimize the parameters of the coupon generation algorithm.

[1556] Input: Coupon usage information and purchase history data stored in the database

[1557] Output: The new coupons reflected in the updated algorithm parameters and the next coupon generation.

[1558] What it does: Use the reanalyzed data to evaluate the performance of the algorithm and optimize it using techniques like A / B testing.

[1559] (Application example 1)

[1560] 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."

[1561] Conventional coupon distribution systems were able to generate and distribute coupons based on user purchasing information. However, there had been little research into how to generate and distribute individually optimized advertisements based on users' purchasing patterns. As a result, they were unable to provide information tailored to users' preferences or deliver effective advertisements, resulting in reduced advertising effectiveness.

[1562] 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.

[1563] In this invention, the server includes means for collecting user purchasing information, means for analyzing the collected purchasing information, means for generating coupons based on the analysis results, means for distributing the generated coupons to user terminals, means for collecting user coupon usage data, means for performing data analysis again based on the collected coupon usage data, means for generating individually optimized advertisements based on the collected and analyzed purchasing information, and means for distributing the generated advertisements to user terminals. This makes it possible to provide optimal coupons and advertisements based on the user's purchasing patterns and to deliver information that matches the user's interests and preferences in a timely manner.

[1564] "Means for collecting user purchasing information" refers to devices or software for collecting purchasing data including information on the products purchased by users, the date and time of purchase, and the place of purchase.

[1565] "Means for analyzing collected purchasing information" refers to devices or software that analyze collected purchasing data and understand users' preferences and purchasing patterns.

[1566] The "means for generating coupons based on the analysis results" refers to a device or software for creating coupons suited to users based on the analysis results of purchase data.

[1567] The "means for delivering the generated coupon to the user's terminal" refers to a device or software for sending the generated coupon to the user's smartphone or other terminal.

[1568] "Means for collecting user coupon usage data" refers to a device or software for collecting coupon usage information used by users.

[1569] The "means for re-analyzing data based on collected coupon usage data" refers to a device or software for analyzing coupon usage data and determining the effectiveness and optimization of coupons.

[1570] "Means for generating individually optimized advertisements based on collected and analyzed purchasing information" refers to a device or software for creating advertisements that are optimal for users based on the results of collecting and analyzing purchasing data.

[1571] "Means for delivering the generated advertisement to the user's terminal" means a device or software for sending the generated advertisement to the user's smartphone or other terminal.

[1572] The present invention is a system for generating and distributing advertisements and coupons that are individually optimized based on a user's purchasing information and preferences. An embodiment of the system will be described in detail below.

[1573] composition

[1574] The system mainly consists of a server and a user terminal. The server collects and analyzes purchase information, and generates and distributes coupons and advertisements. The user terminal receives and displays coupons and advertisements.

[1575] Hardware used

[1576] server

[1577] High-performance computer or cloud server (e.g. AWS, Google Cloud, Azure)

[1578] User Device

[1579] Smartphone

[1580] tablet

[1581] Software used

[1582] Machine learning algorithms (e.g., scikit-learn, TensorFlow)

[1583] Digital payment apps (e.g., PayPay)

[1584] Push notification API (e.g. Firebase Cloud Messaging)

[1585] Ad generator (e.g. Python script)

[1586] Algorithms for analyzing advertising effectiveness (e.g., R language, Python)

[1587] System Operation

[1588] 1. Data Collection

[1589] The server collects information when a user makes a purchase using the digital payment app, including the type of product purchased, the price, the date and time of the purchase, and the location of the purchase.

[1590] The collected purchasing information is stored in a database.

[1591] 2. Data analysis

[1592] The server analyzes the collected purchasing information using machine learning algorithms and clustering techniques (e.g., K-means) to understand users' purchasing patterns and interests.

[1593] The analysis results are used as data to generate optimal advertisements and coupons based on each user's different purchasing history and preferences.

[1594] 3. Coupon generation and distribution

[1595] The server generates the most suitable coupon for each user based on the analysis results and delivers it to the user's device via push notification, allowing the user to receive rewards based on their purchasing behavior.

[1596] 4. Ad generation and delivery

[1597] The server generates individually optimized advertisements based on the collected and analyzed purchasing information and delivers them to the user's device.

[1598] Advertisements are designed to be delivered to users at the right time.

[1599] 5. Data Reanalysis

[1600] The server collects and reanalyzes coupon and advertisement usage data, which can be reflected in the next coupon and advertisement generation.

[1601] In addition, the effectiveness of coupons and advertisements is optimized through A / B testing to improve the next generation algorithm.

[1602] Specific examples

[1603] A specific example of the operation of the system will be shown below.

[1604] 1. Data Collection

[1605] Server: A user purchases clothing from an online store using a digital payment app. The server collects and stores this purchase information.

[1606] User: Information is collected automatically when users make digital payments, without any action on their part.

[1607] 2. Data analysis

[1608] Server: Based on the user's purchasing history, a machine learning model (e.g., K-means clustering) is used to determine the user's interest in fashion products.

[1609] 3. Coupon generation and distribution

[1610] Server: Generate a coupon for the user to redeem for 10% off their next fashion purchase.

[1611] Device: A notification of coupon generation will be sent to the user's smartphone.

[1612] 4. Ad generation and delivery

[1613] Server: Generates the most suitable fashion sale ad for the user and delivers it to their smartphone via push notification.

[1614] Device: A user sees an ad on their phone saying, "Sale at your local store!"

[1615] 5. Data Reanalysis

[1616] Server: Collects information about purchases made by users using coupons and reflects it in the next coupon and ad generation. Also, reanalyzes ad click rates and conversion rates to extract optimal ad delivery patterns.

[1617] Prompt Sentence Examples

[1618] "Create a program that generates the best fashion sale ads for users and analyzes the data to improve the ads for the next time."

[1619] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1620] Step 1:

[1621] The server collects purchase information when a user purchases a product using a digital payment app. The input data includes product information, purchase date and time, purchase location, and payment information. This data is stored in a database. For example, when a user purchases clothing from an online shop using a smartphone, the server collects and stores the purchase information.

[1622] Step 2:

[1623] The server analyzes the collected purchasing information using machine learning algorithms. The collected purchasing data is used as input. Data processing involves filtering out unnecessary data and converting it into an appropriate format. Data calculation involves applying clustering techniques (e.g., K-means) to identify the user's purchasing patterns and preferences. The output is the analysis results (such as the product categories the user is interested in). For example, it may be analyzed that the user frequently purchases fashion items.

[1624] Step 3:

[1625] The server generates the most suitable coupon for the user based on the results of the data analysis. The data analysis results are used as input. The data is processed by referring to the user's purchasing history and preferences to create coupon data related to specific products and categories. The generated coupon data is obtained as output. For example, a 10% discount coupon that can be used on the next purchase of fashion products is generated.

[1626] Step 4:

[1627] The server delivers the generated coupon to the user's device. The generated coupon data is used as input. The data is calculated using a push notification API (e.g., Firebase Cloud Messaging) to send the data. The output is a coupon notification displayed on the user's smartphone. For example, a notification may be delivered to the user's smartphone stating, "You've received a 10% discount coupon that can be used on your next fashion purchase!"

[1628] Step 5:

[1629] The server generates individually optimized advertisements based on the collected and analyzed purchasing information. It uses the purchasing information and analysis results as input. It processes the data by creating advertising content tailored to the user's preferences. It calculates the data by using an advertisement generation program to generate advertising data. It obtains the generated advertising data as output. For example, it generates an advertisement for a fashion sale that the user is interested in.

[1630] Step 6:

[1631] The server delivers the generated advertisement to the user's device. The generated advertisement data is used as input. The data calculation uses a push notification API to send the advertisement data. The output is the advertisement displayed on the user's smartphone. For example, a notification saying "There's a fashion sale at a nearby shop!" is delivered.

[1632] Step 7:

[1633] The server collects coupon and ad usage data and reanalyzes it. It uses user coupon usage information and ad click information as input. It processes the data by appropriately filtering it and creating a dataset for reanalysis. It performs data calculations, including reanalysis of the results of A / B testing, and reflects them in the next coupon and ad generation algorithm. It obtains optimized algorithm parameters as output. For example, it analyzes the types and durations of coupons used by users in the past and extracts elements for optimal coupon generation.

[1634] 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.

[1635] This invention relates to a system that collects user purchasing information and emotional data, and generates and distributes optimized coupons based on the analysis results. This system operates in cooperation with a server, terminals, and users, with the aim of improving the user experience.

[1636] Explanation of program processing

[1637] The program for this system consists of a series of processes that collect and analyze users' purchasing information and emotional data, and then deliver the most appropriate coupons at the right time. The specific processing flow is explained below.

[1638] 1. Data Collection

[1639] Server: When a user makes a payment, information about the purchased item (product name, price, purchase date and time, purchase location, etc.) and the user's emotional data (for example, facial expression analysis using facial recognition or emotional state obtained from voice analysis) are collected and stored in a database.

[1640] User: Uses digital payments and also provides emotional data via the device's camera and microphone, which is automatically sent to the server.

[1641] 2. Data analysis

[1642] Server: Analyzes the collected purchasing information and sentiment data using machine learning models and data analysis algorithms. Applying clustering techniques, the server creates groups of users with similar purchasing patterns and sentiment data.

[1643] User: No action is required, everything is handled automatically in the backend.

[1644] 3. Coupon Generation

[1645] Server: Based on the analysis results, generate coupons that best fit the user's purchasing history and emotional state. For example, if a user shows signs of joy when purchasing milk, generate a discount coupon for that user that can be used on their next purchase.

[1646] Device: The user will receive a notification on their smartphone that a coupon has been generated.

[1647] 4. Coupon distribution

[1648] Server: Generates and delivers the coupon to the user's mobile device via push notification, SMS, or email.

[1649] On the device: The coupon details are displayed and the user can view them.

[1650] 5. Displaying and Using Coupons

[1651] User: Purchases a product using a coupon. For example, they use a coupon to buy milk at the supermarket.

[1652] Terminal: The coupon's QR code or coupon code is displayed and can be scanned at the store to be used.

[1653] 6. Coupon usage data collection

[1654] Terminal: When a coupon is used, usage information is generated in real time.

[1655] Server: Collects coupon usage data (date and time of use, store used, discount amount, etc.) and stores it in a database.

[1656] 7. Reanalysis of usage data and feedback

[1657] Server: Reanalyzes the collected coupon usage data and emotional data and reflects it in the next coupon generation algorithm. In particular, it evaluates how emotional state affects coupon usage, enabling it to provide coupons with optimal timing and content.

[1658] Specific examples

[1659] 1. Data Collection

[1660] Server: Mr. Sato purchases chocolate at a supermarket using digital payment, and facial expression data is collected using a camera. It is recorded that Mr. Sato has a surprised expression on his face when he makes the purchase.

[1661] Users: No action is required; information is automatically transmitted via the smartphone camera and payment app.

[1662] 2. Data analysis

[1663] Server: Analyzes Mr. Sato's purchasing history and facial expression data and finds out that he enjoys buying chocolate.

[1664] 3. Coupon Generation

[1665] Server: Generate a coupon for Sam for 10% off her next chocolate purchase.

[1666] Device: Send a notification to Sato's smartphone saying, "Your next chocolate purchase will be 10% off!"

[1667] 4. Coupon distribution

[1668] Server: Once the coupon is generated, it is sent to Mr. Sato's smartphone.

[1669] Device: A notification appears and Sato checks the coupon details.

[1670] 5. Displaying and Using Coupons

[1671] User: The next time Sam buys chocolate at the supermarket, he uses the coupon displayed on his smartphone.

[1672] Terminal: A QR code or coupon code is displayed and can be used by the store clerk by scanning it.

[1673] 6. Coupon usage data collection

[1674] Server: Information about when Sato used the 10% off coupon (date and time of use, store used, discount amount) is saved in the database.

[1675] 7. Reanalysis of usage data and feedback

[1676] Server: Reanalyzes Sato's coupon usage data and facial expression data and reflects them in the next coupon generation. It also evaluates the effectiveness of coupons based on facial expressions and provides the most appropriate coupon.

[1677] This will allow for the use of emotional data to create a more personalized user experience and encourage greater adoption of digital payments.

[1678] The processing flow will be explained below.

[1679] Step 1: Data collection

[1680] Server: When a user makes a payment, information about the purchased item (product name, price, purchase date and time, purchase location, etc.) is collected. Emotional data is also collected at the same time. This includes facial recognition technology using the user's smartphone camera and estimation of emotional state through voice analysis. All information is automatically stored in a database.

[1681] User: When making a digital payment, the smartphone camera and microphone are activated to collect emotional data from facial expressions and voice, without any action required.

[1682] Step 2: Data analysis

[1683] Server: Analyzes the collected purchasing information and sentiment data. Machine learning algorithms are used to identify trends in users' purchasing patterns and sentiment, and clustering techniques are used to form user groups with similar characteristics.

[1684] 1. Aggregate each user's purchasing history and calculate frequency and average spending.

[1685] 2. Analyze emotional data to identify typical emotional states at the time of purchase (e.g., joy, surprise, sadness, etc.).

[1686] Step 3: Generate coupon

[1687] Server: Based on the results of data analysis, the server generates personalized coupons for each user, taking into account the user's purchasing history and emotional state. For example, if a user always looks happy when buying milk, the server generates a discount coupon for the next milk purchase.

[1688] 1. Set details such as the coupon discount rate, terms of use, and expiration date.

[1689] 2. Generate different versions of the coupon using A / B testing, if necessary.

[1690] Step 4: Coupon Delivery

[1691] Server: Delivers the generated coupons to the user's device via channels such as push notification, SMS, or email.

[1692] 1. Calculate and set the optimal transmission timing for each user.

[1693] 2. After sending, use a tracking system to check whether the user received the notification.

[1694] Step 5: View and redeem coupons

[1695] On your device: Open the notification you received and check the coupon details. The coupon's QR code and coupon code will be displayed.

[1696] 1. The coupon details clearly state the applicable conditions and expiration date.

[1697] 2. Allow users to present and redeem coupons at the time of purchase.

[1698] Step 6: Collect coupon usage data

[1699] Terminal: When a coupon is used, usage information (date and time of use, store used, discount amount, etc.) is generated in real time.

[1700] Server: Stores the collected coupon redemption data in a database for subsequent analysis.

[1701] Step 7: Reanalyze usage data and provide feedback

[1702] Server: Reanalyze the collected coupon usage data and emotion data to determine which coupons were most effective for users in which emotional states.

[1703] 1. Calculate coupon performance evaluation indicators based on usage data.

[1704] 2. Reflect this data in the next coupon generation to provide effective coupons.

[1705] Specific processing examples

[1706] Step 1:

[1707] Server: When Mr. Sato makes a payment at the supermarket, his chocolate purchase information and facial expression data captured by the camera at the time are collected.

[1708] Step 2:

[1709] Server: Analyzes Mr. Sato's viewing data to see that he enjoys chocolate when he buys it. Also, based on his past purchase history, we know that he buys chocolate regularly.

[1710] Step 3:

[1711] Server: Generate a 10% off coupon for your next chocolate purchase.

[1712] Step 4:

[1713] Server: Send a notification to Mr. Sato's smartphone saying, "Your next chocolate purchase will be 10% off!"

[1714] Step 5:

[1715] Device: A notification appears and Sato checks the coupon details.

[1716] Step 6:

[1717] Device: The next time Sato buys chocolate at the supermarket, he will present and use the coupon.

[1718] Step 7:

[1719] Server: Collects data on Sato's coupon usage (date and time of use, store used, discount amount, etc.) and reflects this in the next coupon generation. It also associates emotional data with the effectiveness of coupon usage and reanalyzes it.

[1720] Example 2

[1721] 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."

[1722] In modern society, the spread of digital payments has created a demand for personalized services based on user purchasing behavior. However, conventional systems have focused on analyzing only purchase information, making it difficult to provide personalized services that take user emotions into account. Furthermore, optimization to increase the effectiveness of coupons has been insufficient. This has created challenges in improving user experience and promoting service usage.

[1723] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting user purchase information, means for collecting user emotion data, means for analyzing the collected purchase information and emotion data, means for generating coupons based on the analysis results, means for distributing the generated coupons to the user's terminal, means for collecting user coupon usage data, and means for performing data re-analysis based on the collected coupon usage data. This makes it possible to timely distribute personalized coupons that take user emotions into consideration, maximize the effectiveness of coupon usage, and improve the user experience.

[1724] "User purchasing information" refers to information about the products purchased by the user (product name, price, purchase date and time, purchase location, etc.).

[1725] "User emotional data" refers to data that indicates the user's emotional state, including facial expression analysis using facial recognition, voice analysis, and other sensor data.

[1726] "Collection Method" refers to the technology or device that obtains information from users and stores it in a database or other storage medium.

[1727] "Analytical means" refers to software algorithms and data analysis tools used to analyze collected data and extract meaningful information and patterns.

[1728] "Coupon Generation Means" means software and algorithms for generating coupons containing offers or discounts to offer to Users based on the results of data analysis.

[1729] "Means for delivering coupons to users' devices" refers to the technology or method for sending generated coupons to users' devices such as smartphones or tablets.

[1730] "Means for collecting coupon usage data" refers to a system or device that collects and records information when a user uses a coupon (such as the date and time of use, the store where the coupon was used, and the discount amount).

[1731] "Means for re-analyzing data" refers to technologies and methods for analyzing newly collected coupon usage data, separate from the initial data collection, and reflecting the results in generating the next coupon.

[1732] MODE FOR CARRYING OUT THE INVENTION

[1733] The present invention relates to a system that collects user purchasing information and emotional data, and generates and distributes optimized coupons based on that information. This system operates in cooperation with a server, terminals, and users, with the aim of improving the user experience. Specific embodiments are described below.

[1734] Data collection

[1735] The server works in conjunction with the electronic payment system to collect information on products purchased by users in real time (product name, price, purchase date and time, purchase location, etc.). This is done using an API linked to the POS system. The server also uses the device's camera and microphone to obtain user emotional data (facial expression analysis and voice analysis) and stores this in a database. Possible tools used include Python's OpenCV library and voice analysis library.

[1736] Users provide the necessary emotional data by using the device's camera and microphone in a natural way when making digital payments, so data is collected without any special action required.

[1737] Data analysis

[1738] The server integrates the collected purchasing information and sentiment data and performs analysis using machine learning models and data analysis algorithms. Specifically, it uses Python's Scikit-learn library to form user groups using clustering algorithms (K-means and DBSCAN). This makes it possible to identify users with similar purchasing patterns and sentiment data.

[1739] Coupon Generation

[1740] The server generates the most suitable coupon for the user based on the data analysis results. For example, if the user has a happy expression when purchasing chocolate, the server generates a coupon for 10% off the next chocolate purchase. This process is performed using software with a coupon generation algorithm.

[1741] Example prompt for coupon generation: "If the user purchases chocolate and has a happy expression when purchasing, generate a coupon for 10% off."

[1742] Coupon distribution

[1743] The server then delivers the generated coupon to the user's mobile device via push notification, SMS, or email. APIs used include Firebase Cloud Messaging (FCM) and Amazon SNS (Simple Notification Service).

[1744] The device will then display the details of the coupon to the user, using a mobile app to receive and display notifications.

[1745] Viewing and Using Coupons

[1746] Users can use the coupons they receive to purchase products, such as milk at a supermarket, by using the coupon displayed on their smartphone screen.

[1747] The terminal displays the coupon's QR code or barcode, which can then be scanned at the store using the mobile device's camera.

[1748] Coupon usage data collection

[1749] The server collects information when a user uses a coupon (such as the date and time of use, the store where it was used, and the discount amount) and stores it in a database. By linking with the POS system, usage information is collected in real time.

[1750] Reanalysis of usage data and feedback

[1751] The server re-analyzes the collected coupon usage data and sentiment data and reflects it in the next coupon generation algorithm. This allows for more effective and personalized coupons to be provided. Specific analysis is performed using the aforementioned Python library and analysis tools.

[1752] Through this series of processes, the system can generate and distribute personalized coupons in a timely manner that takes into account the user's purchasing behavior and emotional state, which is expected to improve the user experience and promote the use of digital payments.

[1753] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1754] Step 1: Data collection

[1755] The server collects data from the POS system and the terminal's camera and microphone. The POS system receives the user's purchase information (product name, price, purchase date and time, purchase location, etc.), and the camera and microphone collect the user's emotional data (facial expression data and voice data). This data is stored in a secure database.

[1756] Input: Purchase information from the POS system, emotion data from the device's camera and microphone.

[1757] Output: A database containing purchasing information and sentiment data.

[1758] Specific operation: The server communicates with the POS system via API to obtain real-time purchase data. Emotion data from the device is captured using the camera and microphone and sent to the server.

[1759] Step 2: Data analysis

[1760] The server integrates the collected purchasing information and emotional data and analyzes them using data analysis algorithms and machine learning models (for example, clustering algorithms using Python's Scikit-learn library). This allows the server to cluster users' purchasing patterns and emotional states and form specific user groups.

[1761] Input: Purchase information and sentiment data stored in a database.

[1762] Output: Clustered user population data.

[1763] How it works: The server extracts purchasing information and emotional data from the database and inputs them into a clustering algorithm, which then forms groups of users with similar purchasing patterns and emotional states.

[1764] Step 3: Generate coupon

[1765] The server generates the most suitable coupon for the user based on the analysis results. For example, if a user has a happy expression when purchasing chocolate, the server generates a 10% off coupon for the user's next chocolate purchase.

[1766] Input: Clustered user group data and analysis results of each user's purchasing and sentiment data.

[1767] Output: The generated coupon data.

[1768] How it works: The server determines which coupon is best suited to which user based on purchasing patterns and sentiment data, then runs a coupon generation algorithm to generate coupons, which are then stored in a coupon database.

[1769] Step 4: Coupon Delivery

[1770] The server then delivers the generated coupon to the user's mobile device via push notification, SMS, or email.

[1771] Input: Generated coupon data and user contact information.

[1772] Output: The coupon notification delivered.

[1773] Specific operation: The server uses the user's contact information to select the appropriate delivery method (push notification, SMS, email) and send the coupon. The notification is delivered to the user's device using Firebase Cloud Messaging (FCM) or Amazon SNS.

[1774] Step 5: View and redeem coupons

[1775] Users can use the coupons they receive to purchase products, such as milk at a supermarket, by using the coupon displayed on their smartphone screen.

[1776] Input: The coupon notification the user received.

[1777] Output: Purchase data using coupons.

[1778] What it does: The user shows the coupon displayed on the device to the store clerk and has them scan the QR code or barcode, which applies the discount.

[1779] Step 6: Collect coupon usage data

[1780] The server collects information when a user uses a coupon and stores it in a database, including the date and time of use, the store where the coupon was used, and the discount amount.

[1781] Input: Transaction information when the coupon was redeemed.

[1782] Output: A database containing coupon redemption data.

[1783] Specific operation: The server obtains coupon usage data from the POS system and stores it in a database. Since usage data is collected in real time, it is updated immediately.

[1784] Step 7: Reanalyze usage data and provide feedback

[1785] The server reanalyzes the collected coupon usage data and emotional data and incorporates it into the next coupon generation algorithm, particularly evaluating how emotional states affect coupon usage.

[1786] Input: Coupon redemption data and sentiment data stored in a database.

[1787] Output: An improved coupon generation algorithm.

[1788] How it works: The server retrains the machine learning model based on newly collected coupon usage data to improve the accuracy of the next coupon generation, enabling it to provide more effective personalized coupons.

[1789] Through each of these processing steps, the system can improve the user experience and promote the use of digital payments.

[1790] (Application example 2)

[1791] 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."

[1792] Conventional coupon distribution systems generate coupons based only on a user's purchase history, making it difficult to provide coupons that reflect the user's current emotional state and purchasing patterns. This has led to challenges in delivering coupons at the optimal time for users and generating more effective coupons.

[1793] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user purchasing information, means for analyzing the collected purchasing information and emotional data, means for clustering purchasing patterns and emotional data using a machine learning model, means for generating coupons based on the analysis results, means for delivering the generated coupons to the user's terminal, means for displaying the delivered coupons, means for collecting user coupon usage data, and means for performing further data analysis based on the collected coupon usage data. This makes it possible to provide more personalized and effective coupons based on the user's current emotional state and purchasing patterns.

[1794] "Purchase information" refers to information obtained when a user purchases a product or service, and specifically includes data such as the product name, price, purchase date and time, and purchase location.

[1795] "Emotional data" refers to data that represents the emotional state of the user, and specifically includes information on the emotional state obtained from facial expression recognition and voice analysis.

[1796] A "machine learning model" refers to an algorithm or method that learns patterns and rules based on collected data and makes future predictions and classifications.

[1797] "Clustering" is a method of grouping data with similar characteristics, and is used to analyze user purchasing patterns and emotional data to form similar user groups.

[1798] "Coupon" refers to a ticket or code that allows a user to receive a discount or benefit on their next purchase.

[1799] The term "terminal" refers to an electronic device used by a user, including a smartphone, which in the present invention is used to receive and display coupons.

[1800] The "database" is a system for efficiently storing and managing collected purchasing information, emotional data, and coupon usage data.

[1801] "Analysis results" refers to conclusions and insights derived from collected purchasing information and sentiment data using machine learning models and data analysis algorithms.

[1802] "Coupon usage data" refers to data when a user actually uses a coupon, and includes information such as the date and time of use, the store where the coupon was used, and the discount amount.

[1803] "Push notification" is a function in which a server sends information to a user's device in real time, and is used to distribute generated coupons.

[1804] "Reanalysis" is the process of conducting further analysis based on data that has already been collected to find new insights and areas for improvement.

[1805] The present invention provides a system for collecting user purchasing information and emotional data, analyzing the data, and generating personalized coupons. This system has the following configuration.

[1806] Hardware and Software Configuration

[1807] The server includes means for collecting user purchasing information, means for analyzing the collected purchasing information and emotional data, means for clustering purchasing patterns and emotional data using a machine learning model (such as TensorFlow or PyTorch), means for generating coupons based on the analysis results, means for delivering the generated coupons to the user's device, means for displaying the delivered coupons, means for collecting coupon usage data from users, and means for performing data analysis again based on the collected coupon usage data.

[1808] Processing the data

[1809] When a user purchases an item on an online shopping site, the server collects information about the purchased item (item name, price, purchase date and time, purchase location, etc.) and the item being viewed. It also obtains the user's emotional data (emotional state obtained from facial expression recognition and voice analysis) via the camera and microphone and stores it in a database (MySQL, MongoDB, etc.).

[1810] The server then analyzes the collected purchasing information and sentiment data using machine learning models and data analysis algorithms (e.g., clustering techniques). This process forms groups of users with similar purchasing patterns and sentiment data.

[1811] Based on the analysis, the server generates coupons that best fit the user's purchasing history and emotional state. For example, if a user is excited about buying a new gadget, the server generates a discount coupon for the user's next gadget purchase.

[1812] The generated coupon is sent from the server to the user's device via push notification (e.g., Firebase Cloud Messaging). Detailed coupon information is displayed on the user's device, allowing the user to check and use the coupon. When the user uses the coupon during their next purchase, usage information is generated in real time and stored in a database.

[1813] The collected coupon usage data will be analyzed again and reflected in the next coupon generation algorithm, allowing for more personalized coupons based on the user's emotional state and purchasing patterns.

[1814] Specific examples

[1815] For example, when User A purchases a gadget on an online shopping site, the camera captures his or her excited facial expression. The server then generates a 10% off coupon that can be applied to User A's future gadget purchases and sends it to User A's smartphone via push notification. When User A uses the coupon on their next purchase, information such as the date and time of use, the store where it was used, and the discount amount is collected and stored in a database. This data is used for the next analysis to help regenerate the most appropriate coupon for User A.

[1816] Prompt Sentence Examples

[1817] "Please propose an algorithm that analyzes user purchasing patterns based on emotional data and generates optimal coupons."

[1818] "Generate the best coupon using the following user data: User A: Purchase history [gadgets, books], Emotion data [excitement, joy]"

[1819] In this way, the present invention can provide more personalized coupons based on a user's emotional state and purchasing patterns.

[1820] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1821] Step 1:

[1822] The server collects the user's purchasing information and emotional data. The purchasing information includes the product name, price, purchase date and time, and purchase location. The emotional data is facial recognition and voice analysis data obtained through the device's camera and microphone. This data is sent to the server and stored in a database. The input is the information obtained when the user purchases a product on an online shopping site, and the output is the purchasing information and emotional data stored in the database.

[1823] Step 2:

[1824] The server analyzes the purchasing information and emotional data stored in the database using machine learning models (such as TensorFlow or PyTorch) and data analysis algorithms. It uses clustering techniques to form user groups with similar purchasing patterns and emotional data. The input is the purchasing information and emotional data stored in the database, and the output is the clustering results. Specifically, the machine learning algorithm analyzes the data and forms user groups.

[1825] Step 3:

[1826] The server generates a coupon that best suits the user's purchase history and emotional state based on the clustering results. For example, if a user is excited while purchasing a gadget, it generates a coupon that can be used for the user's next gadget purchase. The input is the clustering results and the user's emotional data, and the output is the generated coupon. Specifically, the server runs a coupon generation algorithm to create the optimal coupon.

[1827] Step 4:

[1828] The server delivers the generated coupon to the user's device via push notification (e.g., Firebase Cloud Messaging). The input is the generated coupon, and the output is the coupon notification delivered to the user's device. Specifically, the server sends detailed coupon information using a push notification service.

[1829] Step 5:

[1830] The terminal displays detailed coupon information to the user, who can then check and use the coupon. The input is the delivered coupon notification, and the output is the displayed coupon information. Specifically, the terminal activates a function to display coupon details on the screen.

[1831] Step 6:

[1832] When a user uses a coupon to purchase a product, the terminal displays the coupon code and automatically applies it at the time of purchase. The input is the coupon information the user wants to use, and the output is the applied coupon information. Specifically, the terminal's coupon code display function is activated and the code is entered.

[1833] Step 7:

[1834] When a coupon is used, the server collects usage information (date and time of use, store used, discount amount, etc.) in real time and stores it in a database. The input is the information at the time of coupon use, and the output is the coupon usage information stored in the database. Specifically, the server's data collection function is activated and the information is added to the database.

[1835] Step 8:

[1836] The server reanalyzes the collected coupon usage data and sentiment data and reflects it in the next coupon generation algorithm. The input is the coupon usage data and sentiment data stored in the database, and the output is the reanalysis results. Specifically, the server runs the data analysis algorithm again and uses the insights gained to help generate the next coupon.

[1837] 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.

[1838] 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.

[1839] 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.

[1840] 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.

[1841] 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.

[1842] 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.

[1843] 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).

[1844] 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.

[1845] 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."

[1846] 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.

[1847] 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).

[1848] 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.

[1849] 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.

[1850] 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.

[1851] 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.

[1852] 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.

[1853] 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.

[1854] 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.

[1855] 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.

[1856] 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.

[1857] 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.

[1858] The following is further disclosed regarding the above embodiment.

[1859] (Claim 1)

[1860] A means of collecting user purchasing information,

[1861] A means for analyzing the collected purchasing information;

[1862] means for generating coupons based on the analysis results;

[1863] A means for delivering the generated coupon to a user's terminal;

[1864] A means for collecting coupon usage data of users;

[1865] A means to conduct further data analysis based on the collected coupon usage data, and

[1866] A system including:

[1867] (Claim 2)

[1868] 10. The system of claim 1, wherein the system clusters user purchasing patterns.

[1869] (Claim 3)

[1870] 10. The system of claim 1, wherein the effectiveness of the generated coupons is optimized through A / B testing.

[1871] "Example 1"

[1872] (Claim 1)

[1873] A means of collecting user purchasing information using digital payment methods;

[1874] A means for storing the collected purchasing information in a database;

[1875] A means for analyzing the stored purchasing information using a machine learning algorithm;

[1876] a means for generating coupons using rule-based or generative AI models based on the analytical results;

[1877] A means for notifying or delivering the generated coupon to the user's terminal;

[1878] A means of collecting usage data when users use coupons;

[1879] Based on the collected coupon usage data, we will analyze the data again and optimize the algorithm.

[1880] A system including:

[1881] (Claim 2)

[1882] 10. The system of claim 1, wherein the purchasing patterns of users are grouped using a clustering algorithm.

[1883] (Claim 3)

[1884] 10. The system of claim 1, wherein the effectiveness of the generated coupons is optimized using A / B testing.

[1885] "Application Example 1"

[1886] (Claim 1)

[1887] A means of collecting user purchasing information,

[1888] A means for analyzing the collected purchasing information;

[1889] means for generating coupons based on the analysis results;

[1890] A means for delivering the generated coupon to a user's terminal;

[1891] A means for collecting coupon usage data of users;

[1892] A means to conduct further data analysis based on the collected coupon usage data, and

[1893] A means for generating individually optimized advertisements based on the collected and analyzed purchasing information;

[1894] means for delivering the generated advertisement to a user's device;

[1895] A system including:

[1896] (Claim 2)

[1897] 10. The system of claim 1, wherein the system clusters user purchasing patterns.

[1898] (Claim 3)

[1899] 10. The system of claim 1, wherein the effectiveness of the generated coupons and advertisements is optimized through A / B testing.

[1900] "Example 2: Combining Emotion Engines"

[1901] (Claim 1)

[1902] A means of collecting user purchasing information,

[1903] a means for collecting user emotional data;

[1904] a means for analyzing the collected purchasing information and sentiment data;

[1905] means for generating coupons based on the analysis results;

[1906] A means for delivering the generated coupon to a user's terminal;

[1907] A means for collecting coupon usage data of users;

[1908] A means to conduct further data analysis based on the collected coupon usage data, and

[1909] A system including:

[1910] (Claim 2)

[1911] 10. The system of claim 1, wherein the system clusters user purchasing patterns and sentiment data.

[1912] (Claim 3)

[1913] 10. The system of claim 1, wherein the effectiveness of the generated coupons is optimized through A / B testing.

[1914] "Application example 2 when combining emotion engines"

[1915] (Claim 1)

[1916] A means of collecting user purchasing information,

[1917] A means of analyzing the collected purchasing information and sentiment data;

[1918] a means for clustering purchasing patterns and sentiment data using machine learning models;

[1919] means for generating coupons based on the analysis results;

[1920] A means for delivering the generated coupon to a user's terminal;

[1921] A means for displaying the distributed coupon;

[1922] A means for collecting coupon usage data of use...

Claims

1. A means of collecting user purchasing information, A means for analyzing the collected purchasing information; means for generating coupons based on the analysis results; A means for delivering the generated coupon to a user's terminal; A means for collecting coupon usage data of users; A means to conduct further data analysis based on the collected coupon usage data, and A system including:

2. The system of claim 1 , further comprising clustering user purchasing patterns.

3. The system according to claim 1, wherein the effectiveness of the generated coupons is optimized through A / B testing.

Images