System

Abstract

A system is provided.SOLUTION: A system comprising: means for acquiring a behavior history and a purchase history of a user; analysis means using a AI model for analyzing the acquired behavior history and purchase history; means for generating a coupon advertisement customized for each user based on an analysis result; and means for distributing the generated coupon advertisement to user terminals.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional coupon distribution systems have the problem that many coupons are provided at once, making it difficult for users to find the coupons they really need. As a result, many users are more likely to miss useful coupons, resulting in lower coupon usage rates. In addition, the effectiveness of advertisements is limited because the same advertisements are displayed to all users. Furthermore, the cost of creating and publishing many coupon advertisements is high, making efficient coupon distribution difficult. [Means for solving the problem]

[0005] This invention is a system that acquires and analyzes a user's behavioral history and purchase history to generate and distribute coupon advertisements customized for each user. Specifically, it includes a means for acquiring a user's behavioral history and purchase history, an analysis means using an AI model to analyze the acquired behavioral history and purchase history, a means for generating a coupon advertisement customized for each user based on the analysis results, and a means for distributing the generated coupon advertisement to the user's device. This system allows users to efficiently acquire coupons that are best suited to them, thereby improving coupon usage rates and reducing advertising production costs.

[0006] "Behavioral history" is data that records a series of actions a user takes within an app, such as operations, clicks, page views, and time spent on the app.

[0007] "Purchase history" is data that records detailed information such as the products purchased by a user, the purchase date and time, the purchase price, and the store where the purchase was made.

[0008] An "AI model" is an artificial intelligence-based algorithm and system that analyzes a user's behavioral and purchasing history to select the most suitable coupon.

[0009] "Customized coupon ads" are ads that are generated by dynamically incorporating the most suitable coupon information for each user based on the analysis results of an AI model.

[0010] A "user device" is an information processing device such as a user's smartphone or tablet on which an app is installed and which receives and displays advertisements. [Brief explanation of the drawings]

[0011] [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

[0012] 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.

[0013] First, the terms used in the following description will be explained.

[0014] 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).

[0015] 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.

[0016] 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.

[0017] 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.

[0018] 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."

[0019] [First embodiment]

[0020] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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."

[0032] The present invention is a system that acquires and analyzes a user's behavioral history and purchase history to generate and distribute a coupon advertisement customized for each user. This system includes a means for acquiring the user's behavioral history and purchase history, an analysis means using an AI model to analyze the acquired behavioral history and purchase history, a means for generating a coupon advertisement customized for each user based on the analysis results, and a means for distributing the generated coupon advertisement to the user's terminal.

[0033] 1. Collection of user behavioral and purchasing history

[0034] Device: When a user uses the app, operation history and purchase information are recorded. Behavioral history includes the links the user clicked, the product pages viewed, the time spent on the app, and information about campaigns participated in. Purchase history includes the name of the purchased product, the date and time of purchase, the price, and store information.

[0035] Terminal: Sends this data to the server in real time.

[0036] 2. Data storage and preprocessing

[0037] Server: The received behavioral history and purchase history are stored in a database. The stored data is checked for missing values ​​and outliers, and then corrected or supplemented in an appropriate manner.

[0038] Server: Transforms and normalizes the data into a format that can be processed by the AI ​​model.

[0039] 3. Data analysis using AI models

[0040] Server: Inputs each user's behavioral history and purchase history into the AI ​​model to learn the user's purchasing trends.

[0041] Server: Uses cluster analysis and recommendation algorithms to select the best coupon for each user.

[0042] 4. Generate personalized ads

[0043] Server: Generates customized coupon ads for each user based on the results of the AI ​​model analysis. Dynamic templates are used to display specific products based on the user's name and purchasing history.

[0044] Server: Generates advertising images and banners with optimal coupon information embedded and integrates them into the advertising design.

[0045] 5. Delivery of advertisements

[0046] Server: The generated customized advertisement is delivered to the user's device. It is set to be displayed on the user's app homepage at the scheduled time on the first day of each month.

[0047] On your device: When you open the app, a customized ad will appear on the home screen.

[0048] Specific examples

[0049] Example 1: User A who frequently purchases daily ingredients

[0050] Device: User A regularly purchases ingredients. He searches for and purchases vegetables, meats, and seasonings using the app.

[0051] Server: Based on User A's purchase history and behavioral history, the AI ​​model determines that coupons for "vegetables" and "meat" are valid.

[0052] Server: Generates a "vegetable discount coupon ad for user A."

[0053] Device: On the first day of each month, coupon advertisements such as "10% off vegetables" will be displayed on User A's app homepage.

[0054] Example 2: User B prefers a specific brand of product

[0055] Device: User B frequently purchases a particular brand of cosmetics.

[0056] Server: Analyzes User B's purchasing history and determines that a product coupon for a specific brand is valid.

[0057] Server: Generates a "brand product discount coupon ad exclusively for User B."

[0058] Device: On the first day of each month, coupon advertisements such as "20% off brand cosmetics" will be displayed on User B's app homepage.

[0059] summary

[0060] This system allows users to receive personalized coupon ads based on their purchasing behavior, while also helping businesses reduce advertising production and placement costs while increasing user engagement and usage rates.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] Users: Use the app to search for and purchase products, and view promotions and special offers within the app.

[0064] Device: Records user actions in real time and collects behavioral history (clicks, page views, time spent, etc.) as well as purchase history (purchased products, purchase date and time, purchase price, purchase store, etc.).

[0065] Terminal: Sends collected behavioral and purchase history to the server in real time.

[0066] Step 2:

[0067] Server: Stores the received behavioral history and purchase history in a database.

[0068] Server: Performs data cleaning operations, imputing missing values, correcting outliers, and, if necessary, converting and normalizing the data to a format that is easier for the AI ​​model to process.

[0069] Step 3:

[0070] Server: On the scheduled first day of each month, each user's behavioral and purchasing history is input into the AI ​​model.

[0071] Server: The AI ​​model analyzes the input data and learns the purchasing habits of each user. Specifically, it uses cluster analysis and recommendation algorithms to select the most suitable coupon for each user.

[0072] Step 4:

[0073] Server: Select a custom template based on the coupon information selected for each user.

[0074] Server: Generate personalized coupon ads by embedding coupon information for each user in custom templates. Specifically, we use dynamic templates to display specific products based on the user's name and past purchase history.

[0075] Step 5:

[0076] Server: Delivers the generated customized advertisements to the user's device.

[0077] Device: When you open the app on the 1st of each month, a customized ad will be displayed on the home screen.

[0078] Step 6:

[0079] Device: Records information when a user clicks on a coupon ad or actually uses a coupon.

[0080] Terminal: Sends feedback data (such as ad click rates and coupon redemption rates) to the server in real time.

[0081] Server: Based on the received feedback data, the AI ​​model algorithm and coupon selection logic are tuned and reflected in the next analysis.

[0082] Specific examples

[0083] Example 1: User A who frequently purchases daily ingredients

[0084] Device: User A frequently purchases vegetables, meat, and seasonings through the app. Their behavioral and purchase history is collected and sent to the server.

[0085] Server: The AI ​​model analyzes User A's data and determines that coupons for "vegetables" and "meat" are valid.

[0086] Server: Generates customized ads including coupons for "10% off vegetables" and "20% off meat" and delivers them to User A's device.

[0087] Device: The coupon advertisement will be displayed on User A's app homepage on the 1st of each month.

[0088] Example 2: User B prefers a specific brand of product

[0089] Device: User B frequently purchases a particular brand of cosmetics. Their purchase history and behavioral history are collected and sent to the server.

[0090] Server: The AI ​​model analyzes User B's data and determines that a product coupon for a specific brand is valid.

[0091] Server: Generate a customized ad containing a coupon for "20% off a specific brand of cosmetics" and deliver it to User B's device.

[0092] Device: The coupon advertisement will be displayed on User B's app homepage on the 1st of each month.

[0093] Example 1

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

[0095] Conventional ad distribution systems deliver generic coupon ads, making it impossible to provide personalized ads based on each user's purchasing trends and behavioral history. This makes it difficult to effectively deliver coupon ads that match the user's interests and needs, resulting in problems such as the inability to expect improvements in ad click rates and purchasing intent.

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

[0097] In this invention, the server includes means for acquiring user behavioral history and purchase history, means for transmitting the acquired behavioral history and purchase history to the server in real time, means for saving the received behavioral history and purchase history to a database, means for checking the saved data for missing values ​​and outliers and appropriately correcting or completing them, means for converting and normalizing the data into a format that can be processed by an AI model, means for inputting each user's behavioral history and purchase history into an AI model and having it learn the user's purchasing tendencies, means for selecting the most suitable coupon for each user using cluster analysis and a recommendation algorithm, means for generating a coupon advertisement customized for each user based on the analysis results of the AI ​​model, means for delivering the generated coupon advertisement to the user's device, and means for displaying the customized advertisement on the top screen when the user opens the app on the user's device. This enables effective delivery of personalized coupon advertisements based on each user's purchasing tendencies and behavioral history.

[0098] "User behavior history" refers to information related to operations, such as links clicked, product pages viewed, time spent on the app, and information about campaigns participated in, that is recorded when the user operates the app.

[0099] "Purchase history" refers to detailed information about specific purchases, such as the name of the product purchased by the user, the date and time of purchase, the price, and store information.

[0100] A "server" is a device or system for receiving, storing, and analyzing behavioral history and purchase history sent by a user.

[0101] "Database" means a structured data storage system for efficiently storing and managing received behavioral and purchasing histories.

[0102] An "AI model" is an artificial intelligence algorithm and computational model used to analyze a user's behavioral history and purchase history and learn about the user's purchasing trends.

[0103] "Normalization" is the process of converting data into a format that can be processed by an AI model and standardizing the scale and format of the data.

[0104] "Cluster analysis" is an analytical technique for grouping data from multiple users and identifying user groups with similar patterns and trends.

[0105] A "recommendation algorithm" is a method for recommending the most suitable products and coupons to each user based on the user's purchasing history and behavioral history.

[0106] "Customized coupon ads" are ads that include coupons that are customized to meet the interests and needs of a specific user based on the user's individual behavioral history and purchasing history.

[0107] The "top screen" is the main screen that appears first on a user's device when they open the app.

[0108] MODE FOR CARRYING OUT THE INVENTION

[0109] The present invention is a system that acquires and analyzes a user's behavioral history and purchase history to generate and distribute coupon advertisements customized for each user. This system includes the following main means.

[0110] Collection of user behavior and purchase history

[0111] Device: When a user operates the app, their behavioral history, such as the links they clicked, the product pages they viewed, the time they spent there, and the campaign information they participated in, is recorded. Purchase history, such as the name of the product purchased, the date and time of purchase, the price, and store information, is also recorded. This data is sent to the server in real time.

[0112] Data storage and preprocessing

[0113] Server: The received behavioral and purchase history is stored in a database. The stored data is checked for missing values ​​and outliers, and corrected or supplemented in an appropriate manner. The data is then converted into a format that can be processed by the AI ​​model and normalized.

[0114] Data analysis using AI models

[0115] Server: Inputs each user's behavioral and purchase history into the AI ​​model to learn their purchasing trends. Using cluster analysis and recommendation algorithms, the server selects the most suitable coupon for each user.

[0116] Generate personalized ads

[0117] Server: Generates customized coupon ads for each user based on the analysis results of the AI ​​model. Dynamic templates are used to display specific products based on the user's name and purchasing history. Generates ad images and banners with the optimal coupon information embedded and integrated into the ad design.

[0118] Ad serving

[0119] Server: The server delivers the generated customized ads to the user's device. These ads are set to be displayed on the user's app homepage at a pre-scheduled time, for example, on the first day of each month.

[0120] On your device: When you open the app, a customized ad will appear on the home screen.

[0121] Specific examples

[0122] Example 1: User A who frequently purchases daily ingredients

[0123] Device: User A searches for and purchases daily ingredients. For example, they search for "cabbage" or "chicken" in the app and complete the purchase process.

[0124] Server: User A's purchase history and behavioral history are input into the AI ​​model, and it is determined that the coupons for "cabbage" and "chicken" are valid.

[0125] Server: Generate a "vegetable discount coupon ad for user A." For example, create a coupon ad for "10% off cabbage."

[0126] Device: On the first day of each month, a coupon ad for "10% off cabbage" will be displayed on User A's app homepage.

[0127] Example 2: User B prefers a specific brand of product

[0128] Device: User B frequently purchases cosmetics from a specific brand, for example, "Brand X lipstick."

[0129] Server: Analyzes User B's purchase history and determines that "Brand X's cosmetics coupon is valid."

[0130] Server: Generate a "brand product discount coupon ad exclusively for User B." For example, create a coupon ad for "20% off brand X lipstick."

[0131] Device: On the first day of each month, a coupon ad for "20% off Brand X lipstick" will be displayed on User B's app homepage.

[0132] Prompt Sentence Examples

[0133] "Design a system that collects user behavioral and purchasing histories and analyzes them using an AI model."

[0134] "Describe the algorithm that generates customized coupon ads for each user."

[0135] "Please explain the process of collecting data in real time and delivering advertisements based on the analysis results."

[0136] The system of the present invention implemented in this way allows users to receive personalized coupon advertisements based on their purchasing behavior, enabling businesses to reduce advertising production and placement costs while improving user engagement and usage rates.

[0137] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0138] Step 1:

[0139] The device records the user's behavioral history and purchase history when the user operates the app. Specifically, it collects information in real time, such as the links the user clicked, the product pages they viewed, the length of time they stayed, and information about campaigns they participated in. It also records the purchase history, such as the name of the product purchased, the date and time of purchase, the price, and store information. The input data is the user's operations and purchase information, and the output is data sent to the server in real time.

[0140] Step 2:

[0141] The server receives the behavioral history and purchase history sent from the device and stores it in a database. When saving, the data is checked for missing or abnormal values ​​and corrected or supplemented in an appropriate manner. For example, data with missing purchase dates and times is supplemented with estimated dates and times. The input data is the sent behavioral history and purchase history, and the output is the corrected and supplemented saved data.

[0142] Step 3:

[0143] The server converts and normalizes the stored data into a format that the AI ​​model can process. For example, it converts purchase dates and times into a unified year / month / day format and normalizes price data to a certain scale. The input data is the corrected and supplemented stored data, and the output is the normalized data.

[0144] Step 4:

[0145] The server inputs each user's behavioral history and purchase history into the AI ​​model to learn the user's purchasing trends. For example, it learns what other products a user who purchased a "Festival Yukata Set" is interested in. The input data is normalized behavioral history and purchase history, and the output is a learned purchasing trend model.

[0146] Step 5:

[0147] The server uses cluster analysis and recommendation algorithms to select the most suitable coupon for each user. For example, it proposes summer festival-related coupons to a group of users who like similar products. The input data is the trained purchasing tendency model, and the output is the selected optimal coupon information.

[0148] Step 6:

[0149] The server generates a coupon ad customized for each user based on the analysis results of the AI ​​model. For example, for a user who purchases a "Festival Yukata Set," it generates a coupon ad offering 10% off summer festival-related products. The input data is the selected optimal coupon information, and the output is a customized coupon ad.

[0150] Step 7:

[0151] The server delivers the generated customized advertisement to the user's device. For example, a "10% off summer festival related products" coupon is delivered on the first day of every month. The input data is the customized coupon advertisement, and the output is the delivery data to the user's device.

[0152] Step 8:

[0153] When a user opens an app, the device displays a customized advertisement on the home screen. For example, when a user opens an app, a coupon advertisement for "10% off summer festival-related products" is displayed on the home screen. The input data is the delivered customized advertisement, and the output is the displayed advertisement.

[0154] (Application example 1)

[0155] 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."

[0156] In today's information society, providing users with appropriate advertisements and coupons is an important part of a marketing strategy. However, current coupon distribution systems do not fully utilize users' purchasing trends and behavioral history, resulting in a lot of wasteful advertisement distribution and often failing to increase user engagement. Furthermore, there is a lack of technology to personalize coupons based on individual purchasing trends, making efficient advertisement distribution difficult. The present invention aims to solve these problems by providing a system that generates and distributes highly accurate coupon advertisements based on individual users' purchasing trends.

[0157] 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.

[0158] In this invention, the server includes means for acquiring user behavioral history and purchase history, means for processing the acquired behavioral history and purchase history, means for an AI model to analyze the purchasing trends of each user using the processed data, means for generating a coupon advertisement customized for each user based on the analysis results, and means for delivering the generated coupon advertisement to the user terminal. This enables the generation of personalized coupon advertisements based on the user's purchasing trends and efficient advertisement delivery.

[0159] "User behavior history" refers to a record of the actions, clicks, browsing time, search queries, etc. that a user takes on an application or website.

[0160] "Purchase history" refers to a record of information about products a user has purchased in the past, including the date and time of purchase, price, and place of purchase.

[0161] "Means" refers to a specific method or component such as a method, device, or system for achieving a specific purpose.

[0162] An "AI model" is an algorithm or model that uses artificial intelligence techniques to analyze data and generate specific results or predictions.

[0163] "Data processing" refers to the process of converting raw data into a format that can be processed by an AI model, including normalizing the data and filling in missing values.

[0164] "Purchasing trends" are the results of an analysis of what products users prefer to purchase, how often they do so, and when.

[0165] A "coupon ad" is an ad that offers users a discount on a particular product or service, and includes a coupon code or discount information.

[0166] "Generating" is the process of creating new data or content based on the analysis results.

[0167] A "user device" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[0168] A "push notification" is a real-time notification message sent by an application to a user device.

[0169] This invention is a system that acquires and analyzes a user's behavioral history and purchase history to generate a coupon advertisement customized for each user and distributes it to the user's terminal. This system is implemented as follows.

[0170] First, the user's device records the user's behavioral history, such as the operation history, clicks, browsing time, and search queries performed when using the application, as well as the purchase history, such as information on previously purchased products, purchase date and time, price, and purchase location. This data is sent to the server in real time.

[0171] The server then stores the received behavioral and purchase history in a database. This stored data is checked for missing values ​​and outliers, and then corrected and supplemented in an appropriate manner. The data is then converted and normalized into a format that can be processed by the AI ​​model. Libraries such as StandardScaler are used for data preprocessing.

[0172] The normalized data is input into an AI model to analyze each user's purchasing habits. Principal component analysis (PCA) and clustering algorithms (e.g., KMeans) are used for the analysis. This allows users to be appropriately classified into clusters based on their purchasing habits, and the most appropriate coupons are selected for each cluster.

[0173] The AI ​​model then uses the results of its analysis to generate a personalized coupon ad for each user. The ad is generated using dynamic templates to display specific products based on the user's name and purchasing history. The ad image and banner are then generated and integrated with the ad design, incorporating the optimal coupon information.

[0174] Finally, the generated customized advertisement is delivered to the user's device, for example, via push notification. Push notifications allow users to receive interesting advertisements in real time, increasing their motivation to make a purchase.

[0175] For example, if a user tends to purchase many e-books, the system analyzes their purchase history and generates e-book coupon ads. On the first day of each month, the system delivers personalized ads to the user's smartphone, such as "20% off new e-books!"

[0176] As described above, the present invention provides a system that generates personalized advertisements based on a user's behavioral history and purchase history, and realizes efficient advertisement distribution.

[0177] An example of a prompt is as follows:

[0178] Design an AI system that generates personalized ads based on users' behavioral and purchasing history. This system involves the following steps:

[0179] 1. Collection of user behavioral and purchasing history

[0180] 2. Preprocessing of these data (dealing with missing values, outliers, and data normalization)

[0181] 3. Data analysis using cluster analysis and recommendation algorithms

[0182] 4. Generate coupon ads customized for each user

[0183] 5. Delivery of these advertisements to user devices

[0184] Please generate specific program code based on this prompt.

[0185] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0186] Step 1:

[0187] The user's device acquires the user's behavioral history and purchase history. Specifically, it records in real time the operations performed when the user uses the application (clicks, searches, browsing time, etc.) and information about purchased products (product name, purchase date and time, price, etc.). This data is sent to the server. The input data is the user's operations and purchase information, and the output data is the raw behavioral history and purchase history sent to the server.

[0188] Step 2:

[0189] The server stores the received behavioral history and purchase history in a database. The stored data is checked for missing values ​​and outliers, and corrected or supplemented as necessary. Specifically, the database system is used to manage multiple data entries and ensure data consistency. The input data is the received behavioral history and purchase history. The output data is the formatted behavioral history and purchase history data.

[0190] Step 3:

[0191] The server converts the formatted behavioral history and purchase history data into a format that can be processed by the AI ​​model and normalizes the data. Specifically, it scales the data using a tool such as StandardScaler. The input data is the formatted behavioral history and purchase history data, and the output data is the normalized data.

[0192] Step 4:

[0193] The server inputs the normalized data into an AI model to analyze each user's purchasing trends. Principal component analysis (PCA) and clustering algorithms (such as KMeans) are used to classify the data into clusters. The input data is normalized data, and the output data is the clustering results. Specifically, the feature values ​​of each cluster are analyzed to clarify the user's purchasing trends.

[0194] Step 5:

[0195] The server generates coupon ads customized for each user based on the analysis results of the AI ​​model. Coupon information is embedded using dynamic templates to design ads suited to each user. The input data is the clustering results, and the output data is the customized coupon ads. Specifically, the ads are dynamically generated using a template engine.

[0196] Step 6:

[0197] The server delivers the generated customized advertisement to the user's device. Specifically, the advertisement is sent to the user in real time using a method such as push notification. The input data is the customized coupon advertisement, and the output data is the advertisement displayed on the user's device. Specifically, the advertisement data is sent to the user's device using a communication protocol.

[0198] Through the above steps, the present invention provides a system that generates personalized advertisements based on a user's behavioral history and purchase history, and realizes efficient advertisement distribution.

[0199] 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.

[0200] The present invention is a system that generates and distributes coupon advertisements customized for each user by acquiring and analyzing the user's behavioral history, purchase history, and emotional data. This system includes a means for acquiring the user's behavioral history and purchase history, an emotion engine for acquiring and analyzing the emotional data, an analysis means using an AI model for analyzing the acquired behavioral history and purchase history, a means for generating coupon advertisements customized for each user based on the analysis results, and a means for distributing the generated coupon advertisements to the user terminal.

[0201] 1. Collection of user behavioral history, purchase history, and emotional data

[0202] Device: Performs operations when the user uses the app. Collects behavioral history (clicks, page views, time spent) and purchase history (purchased products, purchase date and time, price, store information).

[0203] On the device: Using facial recognition and voice analysis technology to collect emotional data from the user's facial expressions and voice.

[0204] Terminal: Collected behavioral history, purchase history, and emotional data is sent to the server in real time.

[0205] 2. Data storage and preprocessing

[0206] Server: Stores the received behavioral history, purchase history, and emotion data in a database.

[0207] Server: Performs data cleaning processes, imputes and corrects missing values ​​and outliers, and normalizes and converts the data into a format that can be processed by the AI ​​model and emotion engine.

[0208] 3. Data analysis using AI models and emotion engines

[0209] Server: On the first day of each month, each user's behavioral history, purchase history, and emotional data are input into the AI ​​model and emotion engine.

[0210] Server: The AI ​​model learns users' purchasing habits and uses cluster analysis and recommendation algorithms to select the most suitable coupons for each user.

[0211] Server: The emotion engine analyzes the input emotion data and further optimizes coupon selection based on the user's current emotional state.

[0212] 4. Generate personalized ads

[0213] Server: Generates customized coupon ads for each user based on the analysis results of the AI ​​model and emotion engine, using dynamic templates to display specific products based on the user's name, past purchase history, and emotional state.

[0214] Server: Generates advertising images and banners with optimal coupon information embedded and integrates them into the advertising design.

[0215] 5. Delivery of advertisements

[0216] Server: Delivers the generated customized advertisements to the user's device.

[0217] Device: When you open the app on the 1st of each month, a customized ad will be displayed on the home screen.

[0218] Specific examples

[0219] Example 1: User A who frequently purchases daily ingredients

[0220] Device: User A regularly buys ingredients. He searches for and purchases vegetables, meats, and seasonings using the app. The emotion engine detects from User A's facial expressions that shopping is a low-stress activity.

[0221] Server: The AI ​​model and emotion engine analyze User A's data and determine that coupons for "vegetables" and "meat" are valid.

[0222] Server: Generates a "vegetable discount coupon ad for user A."

[0223] Device: On the first day of each month, coupon advertisements such as "10% off vegetables" will be displayed on User A's app homepage.

[0224] Example 2: User B prefers a specific brand of product

[0225] Device: User B frequently purchases a specific brand of cosmetics. Their purchase history and behavioral history are collected and sent to the server. The emotion engine detects a high level of excitement in User B's voice.

[0226] Server: The AI ​​model and emotion engine analyze User B's data and determine that a product coupon for a specific brand is valid.

[0227] Server: Generates a "brand product discount coupon ad exclusively for User B."

[0228] Device: On the first day of each month, coupon advertisements such as "20% off brand cosmetics" will be displayed on User B's app homepage.

[0229] summary

[0230] This system allows users to receive personalized coupon ads based on their purchasing behavior and emotional state, while also helping businesses reduce advertising production and placement costs while increasing user engagement and usage rates.

[0231] The processing flow will be explained below.

[0232] Step 1:

[0233] Users: Use the app to search for and purchase products, and view promotions and special offers within the app.

[0234] Device: Records user actions in real time and collects behavioral history (clicks, page views, time spent). It also records purchase history (items purchased, purchase date and time, purchase price, purchase store, etc.). At the same time, it uses facial recognition and voice analysis technology to collect emotional data from the user's facial expressions and voice.

[0235] Terminal: Collected behavioral history, purchase history, and emotional data is sent to the server in real time.

[0236] Step 2:

[0237] Server: The received behavioral history, purchase history, and emotion data is stored in a database. The stored data is checked for missing values ​​and outliers, and then appropriately supplemented and corrected. The data is converted and normalized into a format that is easy for the AI ​​model and emotion engine to process.

[0238] Step 3:

[0239] Server: On the first day of each month, each user's behavioral history, purchase history, and emotional data are input into the AI ​​model and emotion engine. The AI ​​model learns each user's purchasing habits and selects the most appropriate coupon using cluster analysis and recommendation algorithms. The emotion engine also analyzes the emotional data and further optimizes coupon selection based on the user's current emotional state.

[0240] Step 4:

[0241] Server: Select a custom template based on the coupon information selected for each user. Embed coupon information for each user in the custom template to generate individually tailored coupon ads. Use dynamic templates to display specific products based on the user's name, past purchase history, or emotional state.

[0242] Step 5:

[0243] Server: Delivers the generated customized advertisements to the user's device.

[0244] Device: When the app is opened on the 1st of each month, a customized ad is displayed on the home screen. The fact that the ad was displayed is sent as feedback to the server.

[0245] Step 6:

[0246] Device: When a user clicks on a coupon ad or actually uses a coupon, that information is recorded and feedback data (such as ad click rates and coupon redemption rates) is sent to the server in real time.

[0247] Server: Based on the received feedback data, the AI ​​model, emotion engine algorithms, and coupon selection logic are tuned and reflected in the next analysis.

[0248] Specific examples

[0249] Example 1: User A who frequently purchases daily ingredients

[0250] Device: User A frequently purchases vegetables, meat, and seasonings through the app. Their behavioral and purchasing history is collected and sent to the server. The emotion engine detects from User A's facial expressions that shopping is a low-stress activity.

[0251] Server: The AI ​​model and emotion engine analyze User A's data and determine that coupons for "vegetables" and "meat" are valid.

[0252] Server: Generates a "vegetable discount coupon ad for user A."

[0253] Device: On the first day of each month, coupon advertisements such as "10% off vegetables" will be displayed on User A's app homepage.

[0254] Example 2: User B prefers a specific brand of product

[0255] Device: User B frequently purchases a particular brand of cosmetics. Their purchase history and behavioral history are collected and sent to the server. The emotion engine detects a high level of excitement in User B's voice.

[0256] Server: The AI ​​model and emotion engine analyze User B's data and determine that a product coupon for a specific brand is valid.

[0257] Server: Generates a "brand product discount coupon ad exclusively for User B."

[0258] Device: The coupon advertisement will be displayed on User B's app homepage on the 1st of each month.

[0259] Example 2

[0260] 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."

[0261] Conventional coupon advertising systems generate coupons based solely on a user's behavioral and purchasing history, resulting in insufficient personalization that takes into account the user's current emotional state. This results in insufficient appeal to users' interests and limits the improvement of coupon usage rates and advertising effectiveness. Furthermore, the accuracy of selecting appropriate coupons for each user is low, resulting in a lot of wasted advertising. There was a need to solve these problems and achieve more effective coupon distribution.

[0262] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0263] In this invention, the server includes means for acquiring a user's behavioral history and purchase history, means for acquiring user emotional data using facial recognition and voice analysis technology, and analysis means using an AI model and emotion engine for analyzing the acquired behavioral history, purchase history, and emotional data. This makes it possible to comprehensively analyze a user's purchasing tendencies and emotional state, and generate and distribute coupon advertisements optimized for each user.

[0264] "User behavior history" refers to a record of actions such as clicks, page views, and time spent on an application when a user uses it.

[0265] "User purchase history" refers to a record of the products a user has purchased in the past, the purchase date and time, price, store information, etc.

[0266] "Facial recognition" is a technology that captures a user's facial features and identifies their expressions and emotions.

[0267] "Voice analysis" is a technology that analyzes a user's voice and identifies its tone and emotion.

[0268] "Emotional data" is data that indicates a user's emotional state obtained through facial recognition and voice analysis technology.

[0269] An "AI model" is an artificial intelligence algorithm that learns a user's behavioral and purchasing history and predicts purchasing trends.

[0270] The "emotion engine" is a program that analyzes the acquired emotion data and determines the user's current emotional state.

[0271] "Analysis means" refers to a means for analyzing acquired behavioral history, purchase history, and emotional data using an AI model and an emotion engine.

[0272] A "customized coupon ad" is an individually optimized coupon ad that is generated based on each user's behavioral history, purchase history, and emotional state.

[0273] "User terminal" refers to a device used by a user, such as a smartphone, tablet, or PC.

[0274] This invention is a system that generates individually customized coupon advertisements and delivers them to user devices by acquiring and analyzing user behavioral history, purchase history, and emotion data. This system is implemented using user devices, a server, an AI model, and an emotion engine.

[0275] 1. Collection of user behavioral history, purchase history, and emotional data

[0276] Users operate the application to search for and purchase products.

[0277] The device automatically records the user's behavioral history (clicks, page views, time spent) and purchase history (purchased products, purchase date and time, price, store information). For example, if a user views a product page for 30 seconds, that information will be recorded by the device.

[0278] The device uses facial recognition and voice analysis technologies to collect emotional data from the user's facial expressions and voice. For example, the camera detects when the user is smiling and records the intensity of that smile as a numerical value.

[0279] The device transmits the collected data in real time to a server using an internet connection.

[0280] 2. Data storage and preprocessing

[0281] The server stores the received behavioral history, purchase history, and emotion data in a database using an RDBMS such as MySQL or PostgreSQL.

[0282] The server cleans the data and fills in and corrects missing or outlier values. For example, if there is data that is missing a purchase date and time, it fills in the appropriate value.

[0283] The server converts and normalizes the data into a format that can be processed by the AI ​​model and emotion engine, for example, converting text data into numeric vectors.

[0284] 3. Data analysis using AI models and emotion engines

[0285] On the first day of each month, the server inputs each user's behavioral history, purchase history, and emotional data into the AI ​​model and emotion engine.

[0286] The server uses an AI model to learn users' purchasing habits and then uses cluster analysis and recommendation algorithms to select the most suitable coupons for each user. For example, if a user has purchased a lot of vegetables in the past, vegetable-related coupons will be selected for that user.

[0287] The server uses an emotion engine to analyze the emotion data and further optimize the coupons based on the user's emotional state, for example, if the user is expressing joy, it selects coupons with positive messages.

[0288] 4. Generate personalized ads

[0289] The server then uses the analysis results to generate customized coupon ads for each user, using dynamic templates to display specific products based on the user's name, past purchase history, and emotional state.

[0290] The server generates advertising images and banners with optimal coupon information embedded and integrates them with the advertising design. For example, it generates a banner image that reads, "User A, please use this coupon for 10% off vegetables."

[0291] 5. Delivery of advertisements

[0292] The server then delivers the generated customized advertisements to the user's device in real time.

[0293] The device will display a customized advertisement on the home screen when the app is opened on the first day of each month. For example, when user A starts the app, a coupon advertisement for "10% off vegetables" will be displayed on the home screen.

[0294] Specific examples

[0295] Example 1: User A who frequently purchases daily ingredients

[0296] User A buys groceries on a daily basis.

[0297] The device records user A's actions when searching for and purchasing vegetables, meat, and seasonings using the app.

[0298] The emotion engine detects from User A's facial expression that shopping is a low-stress activity.

[0299] The server uses an AI model and emotion engine to analyze User A's data and determines that coupons for "vegetables" and "meat" are valid.

[0300] The server generates a "vegetable discount coupon advertisement exclusive to User A" and delivers it to User A's app.

[0301] On the first day of each month, the device will display a coupon advertisement for "10% off vegetables" on the top screen of User A's app.

[0302] Example 2: User B prefers a specific brand of product

[0303] User B frequently purchases a particular brand of cosmetics.

[0304] The terminal collects purchase history and behavior history and transmits them to the server.

[0305] The emotion engine detects a high level of excitement in User B's voice.

[0306] The server uses an AI model and emotion engine to analyze User B's data and determine that a product coupon for a specific brand is valid.

[0307] The server generates a "brand product discount coupon advertisement exclusive to User B" and delivers it to User B's app.

[0308] On the first day of each month, the device will display a coupon advertisement for "20% off brand cosmetics" on the top screen of User B's app.

[0309] This allows users to receive optimal coupon advertisements based on their purchasing behavior and emotional state, and businesses to maximize the effectiveness of their advertisements.

[0310] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0311] Step 1: Collect user behavioral, purchasing, and sentiment data

[0312] Users operate the app to search for and purchase products, launch the app, browse pages, and purchase products.

[0313] The device records user behavior (clicks, page views, and time spent on the site). For example, if a user views a product page for 30 seconds, that information is recorded.

[0314] The device also records the user's purchase history (purchased items, purchase date and time, price, store information). For example, if a user purchases a 1,000 yen item on March 1st, the details will be recorded.

[0315] The device uses facial recognition and voice analysis technology to collect emotional data from the user's facial expressions and voice. For example, the camera detects when the user is smiling and records the intensity of that smile.

[0316] The terminal transmits the collected behavioral history, purchase history, and emotional data to the server in real time.

[0317] Input: User operation data, facial expression data, voice data

[0318] Output: Recorded behavioral history, purchase history, emotional data

[0319] Step 2: Storing and Preprocessing Data

[0320] The server stores the received behavioral history, purchase history, and emotion data in a database, using an RDBMS such as MySQL or PostgreSQL.

[0321] The server cleans the stored data and fills in and corrects missing or outlier values. For example, if there is data that is missing a purchase date and time, it fills in the appropriate value.

[0322] The server converts and normalizes the data into a format that can be processed by the AI ​​model and emotion engine, for example, converting text data into numeric vectors.

[0323] Input: Collected behavioral history, purchase history, and raw emotional data

[0324] Output: Cleaned and normalized data

[0325] Step 3: Data analysis with AI models and emotion engines

[0326] On the first day of each month, the server inputs each user's behavioral history, purchase history, and emotional data into the AI ​​model and emotion engine.

[0327] The server uses an AI model to learn users' purchasing habits, and then uses cluster analysis and recommendation algorithms to select the most suitable coupons for each user. For example, if a user has purchased a lot of vegetables in the past, vegetable-related coupons will be selected for that user.

[0328] The server analyzes the emotion data using an emotion engine to further optimize coupon selection based on the user's emotional state, for example, selecting coupons with positive messages when the user is expressing joy.

[0329] Input: Cleaned and normalized behavioral history, purchase history, and sentiment data

[0330] Output: Coupon information optimized for each user

[0331] Step 4: Generate a personalized ad

[0332] The server then uses the results of the AI ​​model and emotion engine to generate customized coupon ads for each user, using dynamic templates to display specific products based on the user's name, past purchase history, and emotional state.

[0333] The server generates advertising images and banners with optimal coupon information embedded and integrates them with the advertising design. For example, it generates a banner image that reads, "User A, please use this coupon for 10% off vegetables."

[0334] Input: Coupon information optimized for each user

[0335] Output: Generated customized coupon ad

[0336] Step 5: Serving Ads

[0337] The server then delivers the generated customized advertisements to the user's device in real time.

[0338] When the app is opened on the first day of each month, the device displays a customized advertisement on the home screen. For example, when user A starts the app, a coupon advertisement for "10% off vegetables" appears on the home screen.

[0339] Input: Generated customized coupon ad

[0340] Output: Coupon ad displayed on user's device

[0341] (Application example 2)

[0342] 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."

[0343] Conventional coupon advertising systems rely solely on users' behavioral and purchasing histories for personalization, making it difficult to deliver appropriate ads that reflect the user's momentary emotional state. Furthermore, the timing and method of ad delivery are limited, making it difficult to provide more useful and desirable ads to users.

[0344] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0345] In this invention, the server includes means for acquiring a user's behavioral history and purchase history, means for analyzing the acquired behavioral history and purchase history using an AI model, means for acquiring and analyzing emotional data, means for generating a coupon advertisement customized for each user based on the analysis results, and means for delivering the generated coupon advertisement to the user terminal and displaying it on the display of the smart device, thereby enabling timely and appropriate advertisement delivery based on the user's emotional state.

[0346] "User behavior history" is a record of actions such as clicks, page views, and time spent on a website or application.

[0347] "Purchase history" is a record of the type of product purchased by the user, the purchase date and time, price, store information, etc.

[0348] An "AI model" is an algorithm or computational model that uses artificial intelligence technology to analyze data and derive specific results.

[0349] "Analysis means" refers to the techniques and methods used to analyze acquired data and convert it into meaningful information.

[0350] "Emotional data" refers to information about a user's emotional state analyzed based on their facial expressions, voice, and other biometric information.

[0351] "Customized coupon ads" are individual coupon ads generated based on each user's behavioral history, purchasing history, and emotional state.

[0352] A "smart device" is a device that has internet connectivity and a user-operable display.

[0353] "Means for displaying on a display" refers to a display function for visually presenting the generated information to the user.

[0354] This invention is a system that acquires a user's behavioral history, purchase history, and emotional data, analyzes them, generates a coupon advertisement customized for each user, and delivers it to the user's terminal. Specific embodiments of the system are described below.

[0355] server:

[0356] 1. The server acquires the user's behavioral history and purchase history and stores it in a database, including the user's clicks, page views, time spent on the website or application, as well as the type of product purchased, purchase date and time, price, store information, etc.

[0357] 2. The server has an emotion engine for acquiring emotion data and analyzes the user's emotional state in real time from their facial expressions and voice. The emotion data generated by the emotion engine is stored in a database along with their behavioral history and purchase history.

[0358] 3. The server inputs the collected data into an AI model to analyze the user's purchasing habits and emotional state. The AI ​​model then uses cluster analysis and recommendation algorithms to select the most suitable coupon for each user.

[0359] 4. Based on the analysis results, the server uses dynamic templates to generate customized coupon ads for each user.

[0360] Device:

[0361] 1. User devices include smart devices such as smartphones, smart glasses, and head-mounted displays. These devices receive coupon advertisements distributed from the server and display them on their displays.

[0362] 2. The device has the ability to collect emotion data in real time when the user uses an application and send it to the server. For example, the device can capture the user's facial expressions using a camera mounted on smart glasses and analyze them with the emotion engine.

[0363] Examples:

[0364] For example, suppose user A is wearing smart glasses. When user A is in a supermarket, the camera in the smart glasses captures user A's facial expression data in real time, which is analyzed by the emotion engine. If the emotion engine detects user A's emotional state as "joy," the server sends this information to the AI ​​model and generates the optimal coupon advertisement for user A. The generated coupon advertisement is displayed on the smart glasses' display.

[0365] Generate AI model prompt:

[0366] "Input the user's facial expression data and purchase history and generate the best ads and coupons. If the user is smiling, select and display positive ads."

[0367] In this way, timely and appropriate advertising can be delivered based on the user's emotional state, and the use of smart devices also allows users to enjoy a more intuitive and personalized advertising experience.

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

[0369] Step 1:

[0370] The device acquires the user's behavioral history and purchase history. Specifically, it records operation data (clicks, page views, time spent, purchased items, purchase date and time, etc.) when the user uses a smart device or application, and sends it to a database. The input is the user's operation data, and the output is the behavioral history and purchase history data stored in the server-side database.

[0371] Step 2:

[0372] The device acquires the user's emotional data. The user's facial expressions are captured in real time using smart glasses or a smartphone camera, and analyzed by the emotion engine. The analysis results (emotion data) are sent to the server. The input is the captured facial expression data, and the output is the analyzed emotional data.

[0373] Step 3:

[0374] The server stores the acquired behavioral history, purchase history, and emotion data in a database. Specifically, it performs data cleaning processes, complements and corrects missing and outlier values, and converts and normalizes the data into a format suitable for the AI ​​model and emotion engine. The input is the user's behavioral history, purchase history, and emotion data, and the output is the normalized data stored in the database.

[0375] Step 4:

[0376] The server analyzes user data using an AI model and emotion engine. At regularly scheduled times (for example, the first day of each month), each user's behavioral history, purchase history, and emotional data are input into the AI ​​model and emotion engine. The AI ​​model learns the user's purchasing trends, and the emotion engine analyzes the emotional data. The inputs are normalized behavioral history, purchase history, and emotional data, and the output is the analysis results (selection of the optimal coupon).

[0377] Step 5:

[0378] The server generates customized coupon ads based on the analysis results. Specifically, it uses the analysis results obtained from the AI ​​model and emotion engine to create dynamic templates to generate individual coupon ads for each user. The input is the analysis results, and the output is the customized coupon ads.

[0379] Step 6:

[0380] The server delivers the generated coupon advertisement to the user terminal. The user terminal receives the delivered coupon advertisement and displays it on the display of the smart device. The input is the customized coupon advertisement, and the output is the advertisement displayed on the display of the user terminal.

[0381] Step 7:

[0382] The device monitors whether the user utilizes the generated coupon advertisement and collects new behavioral history, purchase history, and emotional data again. The input is the user's advertisement usage behavior data, and the output is updated behavioral history, purchase history, and emotional data. This makes it possible to generate even more optimized advertisements in the next cycle.

[0383] At each step, the server, terminal, or user plays a key role, and the processes of data collection, analysis, generation, distribution, and reevaluation are carried out smoothly, enabling the provision of optimal coupon advertisements to users.

[0384] 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.

[0385] 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.

[0386] 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.

[0387] [Second embodiment]

[0388] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0389] 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.

[0390] 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).

[0391] 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.

[0392] 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.

[0393] 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).

[0394] 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.

[0395] 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.

[0396] 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.

[0397] 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.

[0398] 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.

[0399] 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."

[0400] The present invention is a system that acquires and analyzes a user's behavioral history and purchase history to generate and distribute a coupon advertisement customized for each user. This system includes a means for acquiring the user's behavioral history and purchase history, an analysis means using an AI model to analyze the acquired behavioral history and purchase history, a means for generating a coupon advertisement customized for each user based on the analysis results, and a means for distributing the generated coupon advertisement to the user's terminal.

[0401] 1. Collection of user behavioral and purchasing history

[0402] Device: When a user uses the app, operation history and purchase information are recorded. Behavioral history includes the links the user clicked, the product pages viewed, the time spent on the app, and information about campaigns participated in. Purchase history includes the name of the purchased product, the date and time of purchase, the price, and store information.

[0403] Terminal: Sends this data to the server in real time.

[0404] 2. Data storage and preprocessing

[0405] Server: The received behavioral history and purchase history are stored in a database. The stored data is checked for missing values ​​and outliers, and then corrected or supplemented in an appropriate manner.

[0406] Server: Transforms and normalizes the data into a format that can be processed by the AI ​​model.

[0407] 3. Data analysis using AI models

[0408] Server: Inputs each user's behavioral history and purchase history into the AI ​​model to learn the user's purchasing trends.

[0409] Server: Uses cluster analysis and recommendation algorithms to select the best coupon for each user.

[0410] 4. Generate personalized ads

[0411] Server: Generates customized coupon ads for each user based on the results of the AI ​​model analysis. Dynamic templates are used to display specific products based on the user's name and purchasing history.

[0412] Server: Generates advertising images and banners with optimal coupon information embedded and integrates them into the advertising design.

[0413] 5. Delivery of advertisements

[0414] Server: The generated customized advertisement is delivered to the user's device. It is set to be displayed on the user's app homepage at the scheduled time on the first day of each month.

[0415] On your device: When you open the app, a customized ad will appear on the home screen.

[0416] Specific examples

[0417] Example 1: User A who frequently purchases daily ingredients

[0418] Device: User A regularly purchases ingredients. He searches for and purchases vegetables, meats, and seasonings using the app.

[0419] Server: Based on User A's purchase history and behavioral history, the AI ​​model determines that coupons for "vegetables" and "meat" are valid.

[0420] Server: Generates a "vegetable discount coupon ad for user A."

[0421] Device: On the first day of each month, coupon advertisements such as "10% off vegetables" will be displayed on User A's app homepage.

[0422] Example 2: User B prefers a specific brand of product

[0423] Device: User B frequently purchases a particular brand of cosmetics.

[0424] Server: Analyzes User B's purchasing history and determines that a product coupon for a specific brand is valid.

[0425] Server: Generates a "brand product discount coupon ad exclusively for User B."

[0426] Device: On the first day of each month, coupon advertisements such as "20% off brand cosmetics" will be displayed on User B's app homepage.

[0427] summary

[0428] This system allows users to receive personalized coupon ads based on their purchasing behavior, while also helping businesses reduce advertising production and placement costs while increasing user engagement and usage rates.

[0429] The processing flow will be explained below.

[0430] Step 1:

[0431] Users: Use the app to search for and purchase products, and view promotions and special offers within the app.

[0432] Device: Records user actions in real time and collects behavioral history (clicks, page views, time spent, etc.) as well as purchase history (purchased products, purchase date and time, purchase price, purchase store, etc.).

[0433] Terminal: Sends collected behavioral and purchase history to the server in real time.

[0434] Step 2:

[0435] Server: Stores the received behavioral history and purchase history in a database.

[0436] Server: Performs data cleaning operations, imputing missing values, correcting outliers, and, if necessary, converting and normalizing the data to a format that is easier for the AI ​​model to process.

[0437] Step 3:

[0438] Server: On the scheduled first day of each month, each user's behavioral and purchasing history is input into the AI ​​model.

[0439] Server: The AI ​​model analyzes the input data and learns the purchasing habits of each user. Specifically, it uses cluster analysis and recommendation algorithms to select the most suitable coupon for each user.

[0440] Step 4:

[0441] Server: Select a custom template based on the coupon information selected for each user.

[0442] Server: Generate personalized coupon ads by embedding coupon information for each user in custom templates. Specifically, we use dynamic templates to display specific products based on the user's name and past purchase history.

[0443] Step 5:

[0444] Server: Delivers the generated customized advertisements to the user's device.

[0445] Device: When you open the app on the 1st of each month, a customized ad will be displayed on the home screen.

[0446] Step 6:

[0447] Device: Records information when a user clicks on a coupon ad or actually uses a coupon.

[0448] Terminal: Sends feedback data (such as ad click rates and coupon redemption rates) to the server in real time.

[0449] Server: Based on the received feedback data, the AI ​​model algorithm and coupon selection logic are tuned and reflected in the next analysis.

[0450] Specific examples

[0451] Example 1: User A who frequently purchases daily ingredients

[0452] Device: User A frequently purchases vegetables, meat, and seasonings through the app. Their behavioral and purchase history is collected and sent to the server.

[0453] Server: The AI ​​model analyzes User A's data and determines that coupons for "vegetables" and "meat" are valid.

[0454] Server: Generates customized ads including coupons for "10% off vegetables" and "20% off meat" and delivers them to User A's device.

[0455] Device: The coupon advertisement will be displayed on User A's app homepage on the 1st of each month.

[0456] Example 2: User B prefers a specific brand of product

[0457] Device: User B frequently purchases a particular brand of cosmetics. Their purchase history and behavioral history are collected and sent to the server.

[0458] Server: The AI ​​model analyzes User B's data and determines that a product coupon for a specific brand is valid.

[0459] Server: Generate a customized ad containing a coupon for "20% off a specific brand of cosmetics" and deliver it to User B's device.

[0460] Device: The coupon advertisement will be displayed on User B's app homepage on the 1st of each month.

[0461] Example 1

[0462] 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."

[0463] Conventional ad distribution systems deliver generic coupon ads, making it impossible to provide personalized ads based on each user's purchasing trends and behavioral history. This makes it difficult to effectively deliver coupon ads that match the user's interests and needs, resulting in problems such as the inability to expect improvements in ad click rates and purchasing intent.

[0464] 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.

[0465] In this invention, the server includes means for acquiring user behavioral history and purchase history, means for transmitting the acquired behavioral history and purchase history to the server in real time, means for saving the received behavioral history and purchase history to a database, means for checking the saved data for missing values ​​and outliers and appropriately correcting or completing them, means for converting and normalizing the data into a format that can be processed by an AI model, means for inputting each user's behavioral history and purchase history into an AI model and having it learn the user's purchasing tendencies, means for selecting the most suitable coupon for each user using cluster analysis and a recommendation algorithm, means for generating a coupon advertisement customized for each user based on the analysis results of the AI ​​model, means for delivering the generated coupon advertisement to the user's device, and means for displaying the customized advertisement on the top screen when the user opens the app on the user's device. This enables effective delivery of personalized coupon advertisements based on each user's purchasing tendencies and behavioral history.

[0466] "User behavior history" refers to information related to operations, such as links clicked, product pages viewed, time spent on the app, and information about campaigns participated in, that is recorded when the user operates the app.

[0467] "Purchase history" refers to detailed information about specific purchases, such as the name of the product purchased by the user, the date and time of purchase, the price, and store information.

[0468] A "server" is a device or system for receiving, storing, and analyzing behavioral history and purchase history sent by a user.

[0469] "Database" means a structured data storage system for efficiently storing and managing received behavioral and purchasing histories.

[0470] An "AI model" is an artificial intelligence algorithm and computational model used to analyze a user's behavioral history and purchase history and learn about the user's purchasing trends.

[0471] "Normalization" is the process of converting data into a format that can be processed by an AI model and standardizing the scale and format of the data.

[0472] "Cluster analysis" is an analytical technique for grouping data from multiple users and identifying user groups with similar patterns and trends.

[0473] A "recommendation algorithm" is a method for recommending the most suitable products and coupons to each user based on the user's purchasing history and behavioral history.

[0474] "Customized coupon ads" are ads that include coupons that are customized to meet the interests and needs of a specific user based on the user's individual behavioral history and purchasing history.

[0475] The "top screen" is the main screen that appears first on a user's device when they open the app.

[0476] MODE FOR CARRYING OUT THE INVENTION

[0477] The present invention is a system that acquires and analyzes a user's behavioral history and purchase history to generate and distribute coupon advertisements customized for each user. This system includes the following main means.

[0478] Collection of user behavior and purchase history

[0479] Device: When a user operates the app, their behavioral history, such as the links they clicked, the product pages they viewed, the time they spent there, and the campaign information they participated in, is recorded. Purchase history, such as the name of the product purchased, the date and time of purchase, the price, and store information, is also recorded. This data is sent to the server in real time.

[0480] Data storage and preprocessing

[0481] Server: The received behavioral and purchase history is stored in a database. The stored data is checked for missing values ​​and outliers, and corrected or supplemented in an appropriate manner. The data is then converted into a format that can be processed by the AI ​​model and normalized.

[0482] Data analysis using AI models

[0483] Server: Inputs each user's behavioral and purchase history into the AI ​​model to learn their purchasing trends. Using cluster analysis and recommendation algorithms, the server selects the most suitable coupon for each user.

[0484] Generate personalized ads

[0485] Server: Generates customized coupon ads for each user based on the analysis results of the AI ​​model. Dynamic templates are used to display specific products based on the user's name and purchasing history. Generates ad images and banners with the optimal coupon information embedded and integrated into the ad design.

[0486] Ad serving

[0487] Server: The server delivers the generated customized ads to the user's device. These ads are set to be displayed on the user's app homepage at a pre-scheduled time, for example, on the first day of each month.

[0488] On your device: When you open the app, a customized ad will appear on the home screen.

[0489] Specific examples

[0490] Example 1: User A who frequently purchases daily ingredients

[0491] Device: User A searches for and purchases daily ingredients. For example, they search for "cabbage" or "chicken" in the app and complete the purchase process.

[0492] Server: User A's purchase history and behavioral history are input into the AI ​​model, and it is determined that the coupons for "cabbage" and "chicken" are valid.

[0493] Server: Generate a "vegetable discount coupon ad for user A." For example, create a coupon ad for "10% off cabbage."

[0494] Device: On the first day of each month, a coupon ad for "10% off cabbage" will be displayed on User A's app homepage.

[0495] Example 2: User B prefers a specific brand of product

[0496] Device: User B frequently purchases cosmetics from a specific brand, for example, "Brand X lipstick."

[0497] Server: Analyzes User B's purchase history and determines that "Brand X's cosmetics coupon is valid."

[0498] Server: Generate a "brand product discount coupon ad exclusively for User B." For example, create a coupon ad for "20% off brand X lipstick."

[0499] Device: On the first day of each month, a coupon ad for "20% off Brand X lipstick" will be displayed on User B's app homepage.

[0500] Prompt Sentence Examples

[0501] "Design a system that collects user behavioral and purchasing histories and analyzes them using an AI model."

[0502] "Describe the algorithm that generates customized coupon ads for each user."

[0503] "Please explain the process of collecting data in real time and delivering advertisements based on the analysis results."

[0504] The system of the present invention implemented in this way allows users to receive personalized coupon advertisements based on their purchasing behavior, enabling businesses to reduce advertising production and placement costs while improving user engagement and usage rates.

[0505] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0506] Step 1:

[0507] The device records the user's behavioral history and purchase history when the user operates the app. Specifically, it collects information in real time, such as the links the user clicked, the product pages they viewed, the length of time they stayed, and information about campaigns they participated in. It also records the purchase history, such as the name of the product purchased, the date and time of purchase, the price, and store information. The input data is the user's operations and purchase information, and the output is data sent to the server in real time.

[0508] Step 2:

[0509] The server receives the behavioral history and purchase history sent from the device and stores it in a database. When saving, the data is checked for missing or abnormal values ​​and corrected or supplemented in an appropriate manner. For example, data with missing purchase dates and times is supplemented with estimated dates and times. The input data is the sent behavioral history and purchase history, and the output is the corrected and supplemented saved data.

[0510] Step 3:

[0511] The server converts and normalizes the stored data into a format that the AI ​​model can process. For example, it converts purchase dates and times into a unified year / month / day format and normalizes price data to a certain scale. The input data is the corrected and supplemented stored data, and the output is the normalized data.

[0512] Step 4:

[0513] The server inputs each user's behavioral history and purchase history into the AI ​​model to learn the user's purchasing trends. For example, it learns what other products a user who purchased a "Festival Yukata Set" is interested in. The input data is normalized behavioral history and purchase history, and the output is a learned purchasing trend model.

[0514] Step 5:

[0515] The server uses cluster analysis and recommendation algorithms to select the most suitable coupon for each user. For example, it proposes summer festival-related coupons to a group of users who like similar products. The input data is the trained purchasing tendency model, and the output is the selected optimal coupon information.

[0516] Step 6:

[0517] The server generates a coupon ad customized for each user based on the analysis results of the AI ​​model. For example, for a user who purchases a "Festival Yukata Set," it generates a coupon ad offering 10% off summer festival-related products. The input data is the selected optimal coupon information, and the output is a customized coupon ad.

[0518] Step 7:

[0519] The server delivers the generated customized advertisement to the user's device. For example, a "10% off summer festival related products" coupon is delivered on the first day of every month. The input data is the customized coupon advertisement, and the output is the delivery data to the user's device.

[0520] Step 8:

[0521] When a user opens an app, the device displays a customized advertisement on the home screen. For example, when a user opens an app, a coupon advertisement for "10% off summer festival-related products" is displayed on the home screen. The input data is the delivered customized advertisement, and the output is the displayed advertisement.

[0522] (Application example 1)

[0523] 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."

[0524] In today's information society, providing users with appropriate advertisements and coupons is an important part of a marketing strategy. However, current coupon distribution systems do not fully utilize users' purchasing trends and behavioral history, resulting in a lot of wasteful advertisement distribution and often failing to increase user engagement. Furthermore, there is a lack of technology to personalize coupons based on individual purchasing trends, making efficient advertisement distribution difficult. The present invention aims to solve these problems by providing a system that generates and distributes highly accurate coupon advertisements based on individual users' purchasing trends.

[0525] 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.

[0526] In this invention, the server includes means for acquiring user behavioral history and purchase history, means for processing the acquired behavioral history and purchase history, means for an AI model to analyze the purchasing trends of each user using the processed data, means for generating a coupon advertisement customized for each user based on the analysis results, and means for delivering the generated coupon advertisement to the user terminal. This enables the generation of personalized coupon advertisements based on the user's purchasing trends and efficient advertisement delivery.

[0527] "User behavior history" refers to a record of the actions, clicks, browsing time, search queries, etc. that a user takes on an application or website.

[0528] "Purchase history" refers to a record of information about products a user has purchased in the past, including the date and time of purchase, price, and place of purchase.

[0529] "Means" refers to a specific method or component such as a method, device, or system for achieving a specific purpose.

[0530] An "AI model" is an algorithm or model that uses artificial intelligence techniques to analyze data and generate specific results or predictions.

[0531] "Data processing" refers to the process of converting raw data into a format that can be processed by an AI model, including normalizing the data and filling in missing values.

[0532] "Purchasing trends" are the results of an analysis of what products users prefer to purchase, how often they do so, and when.

[0533] A "coupon ad" is an ad that offers users a discount on a particular product or service, and includes a coupon code or discount information.

[0534] "Generating" is the process of creating new data or content based on the analysis results.

[0535] A "user device" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[0536] A "push notification" is a real-time notification message sent by an application to a user device.

[0537] This invention is a system that acquires and analyzes a user's behavioral history and purchase history to generate a coupon advertisement customized for each user and distributes it to the user's terminal. This system is implemented as follows.

[0538] First, the user's device records the user's behavioral history, such as the operation history, clicks, browsing time, and search queries performed when using the application, as well as the purchase history, such as information on previously purchased products, purchase date and time, price, and purchase location. This data is sent to the server in real time.

[0539] The server then stores the received behavioral and purchase history in a database. This stored data is checked for missing values ​​and outliers, and then corrected and supplemented in an appropriate manner. The data is then converted and normalized into a format that can be processed by the AI ​​model. Libraries such as StandardScaler are used for data preprocessing.

[0540] The normalized data is input into an AI model to analyze each user's purchasing habits. Principal component analysis (PCA) and clustering algorithms (e.g., KMeans) are used for the analysis. This allows users to be appropriately classified into clusters based on their purchasing habits, and the most appropriate coupons are selected for each cluster.

[0541] The AI ​​model then uses the results of its analysis to generate a personalized coupon ad for each user. The ad is generated using dynamic templates to display specific products based on the user's name and purchasing history. The ad image and banner are then generated and integrated with the ad design, incorporating the optimal coupon information.

[0542] Finally, the generated customized advertisement is delivered to the user's device, for example, via push notification. Push notifications allow users to receive interesting advertisements in real time, increasing their motivation to make a purchase.

[0543] For example, if a user tends to purchase many e-books, the system analyzes their purchase history and generates e-book coupon ads. On the first day of each month, the system delivers personalized ads to the user's smartphone, such as "20% off new e-books!"

[0544] As described above, the present invention provides a system that generates personalized advertisements based on a user's behavioral history and purchase history, and realizes efficient advertisement distribution.

[0545] An example of a prompt is as follows:

[0546] Design an AI system that generates personalized ads based on users' behavioral and purchasing history. This system involves the following steps:

[0547] 1. Collection of user behavioral and purchasing history

[0548] 2. Preprocessing of these data (dealing with missing values, outliers, and data normalization)

[0549] 3. Data analysis using cluster analysis and recommendation algorithms

[0550] 4. Generate coupon ads customized for each user

[0551] 5. Delivery of these advertisements to user devices

[0552] Please generate specific program code based on this prompt.

[0553] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0554] Step 1:

[0555] The user's device acquires the user's behavioral history and purchase history. Specifically, it records in real time the operations performed when the user uses the application (clicks, searches, browsing time, etc.) and information about purchased products (product name, purchase date and time, price, etc.). This data is sent to the server. The input data is the user's operations and purchase information, and the output data is the raw behavioral history and purchase history sent to the server.

[0556] Step 2:

[0557] The server stores the received behavioral history and purchase history in a database. The stored data is checked for missing values ​​and outliers, and corrected or supplemented as necessary. Specifically, the database system is used to manage multiple data entries and ensure data consistency. The input data is the received behavioral history and purchase history. The output data is the formatted behavioral history and purchase history data.

[0558] Step 3:

[0559] The server converts the formatted behavioral history and purchase history data into a format that can be processed by the AI ​​model and normalizes the data. Specifically, it scales the data using a tool such as StandardScaler. The input data is the formatted behavioral history and purchase history data, and the output data is the normalized data.

[0560] Step 4:

[0561] The server inputs the normalized data into an AI model to analyze each user's purchasing trends. Principal component analysis (PCA) and clustering algorithms (such as KMeans) are used to classify the data into clusters. The input data is normalized data, and the output data is the clustering results. Specifically, the feature values ​​of each cluster are analyzed to clarify the user's purchasing trends.

[0562] Step 5:

[0563] The server generates coupon ads customized for each user based on the analysis results of the AI ​​model. Coupon information is embedded using dynamic templates to design ads suited to each user. The input data is the clustering results, and the output data is the customized coupon ads. Specifically, the ads are dynamically generated using a template engine.

[0564] Step 6:

[0565] The server delivers the generated customized advertisement to the user's device. Specifically, the advertisement is sent to the user in real time using a method such as push notification. The input data is the customized coupon advertisement, and the output data is the advertisement displayed on the user's device. Specifically, the advertisement data is sent to the user's device using a communication protocol.

[0566] Through the above steps, the present invention provides a system that generates personalized advertisements based on a user's behavioral history and purchase history, and realizes efficient advertisement distribution.

[0567] 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.

[0568] The present invention is a system that generates and distributes coupon advertisements customized for each user by acquiring and analyzing the user's behavioral history, purchase history, and emotional data. This system includes a means for acquiring the user's behavioral history and purchase history, an emotion engine for acquiring and analyzing the emotional data, an analysis means using an AI model for analyzing the acquired behavioral history and purchase history, a means for generating coupon advertisements customized for each user based on the analysis results, and a means for distributing the generated coupon advertisements to the user terminal.

[0569] 1. Collection of user behavioral history, purchase history, and emotional data

[0570] Device: Performs operations when the user uses the app. Collects behavioral history (clicks, page views, time spent) and purchase history (purchased products, purchase date and time, price, store information).

[0571] On the device: Using facial recognition and voice analysis technology to collect emotional data from the user's facial expressions and voice.

[0572] Terminal: Collected behavioral history, purchase history, and emotional data is sent to the server in real time.

[0573] 2. Data storage and preprocessing

[0574] Server: Stores the received behavioral history, purchase history, and emotion data in a database.

[0575] Server: Performs data cleaning processes, imputes and corrects missing values ​​and outliers, and normalizes and converts the data into a format that can be processed by the AI ​​model and emotion engine.

[0576] 3. Data analysis using AI models and emotion engines

[0577] Server: On the first day of each month, each user's behavioral history, purchase history, and emotional data are input into the AI ​​model and emotion engine.

[0578] Server: The AI ​​model learns users' purchasing habits and uses cluster analysis and recommendation algorithms to select the most suitable coupons for each user.

[0579] Server: The emotion engine analyzes the input emotion data and further optimizes coupon selection based on the user's current emotional state.

[0580] 4. Generate personalized ads

[0581] Server: Generates customized coupon ads for each user based on the analysis results of the AI ​​model and emotion engine, using dynamic templates to display specific products based on the user's name, past purchase history, and emotional state.

[0582] Server: Generates advertising images and banners with optimal coupon information embedded and integrates them into the advertising design.

[0583] 5. Delivery of advertisements

[0584] Server: Delivers the generated customized advertisements to the user's device.

[0585] Device: When you open the app on the 1st of each month, a customized ad will be displayed on the home screen.

[0586] Specific examples

[0587] Example 1: User A who frequently purchases daily ingredients

[0588] Device: User A regularly buys ingredients. He searches for and purchases vegetables, meats, and seasonings using the app. The emotion engine detects from User A's facial expressions that shopping is a low-stress activity.

[0589] Server: The AI ​​model and emotion engine analyze User A's data and determine that coupons for "vegetables" and "meat" are valid.

[0590] Server: Generates a "vegetable discount coupon ad for user A."

[0591] Device: On the first day of each month, coupon advertisements such as "10% off vegetables" will be displayed on User A's app homepage.

[0592] Example 2: User B prefers a specific brand of product

[0593] Device: User B frequently purchases a specific brand of cosmetics. Their purchase history and behavioral history are collected and sent to the server. The emotion engine detects a high level of excitement in User B's voice.

[0594] Server: The AI ​​model and emotion engine analyze User B's data and determine that a product coupon for a specific brand is valid.

[0595] Server: Generates a "brand product discount coupon ad exclusively for User B."

[0596] Device: On the first day of each month, coupon advertisements such as "20% off brand cosmetics" will be displayed on User B's app homepage.

[0597] summary

[0598] This system allows users to receive personalized coupon ads based on their purchasing behavior and emotional state, while also helping businesses reduce advertising production and placement costs while increasing user engagement and usage rates.

[0599] The processing flow will be explained below.

[0600] Step 1:

[0601] Users: Use the app to search for and purchase products, and view promotions and special offers within the app.

[0602] Device: Records user actions in real time and collects behavioral history (clicks, page views, time spent). It also records purchase history (items purchased, purchase date and time, purchase price, purchase store, etc.). At the same time, it uses facial recognition and voice analysis technology to collect emotional data from the user's facial expressions and voice.

[0603] Terminal: Collected behavioral history, purchase history, and emotional data is sent to the server in real time.

[0604] Step 2:

[0605] Server: The received behavioral history, purchase history, and emotion data is stored in a database. The stored data is checked for missing values ​​and outliers, and then appropriately supplemented and corrected. The data is converted and normalized into a format that is easy for the AI ​​model and emotion engine to process.

[0606] Step 3:

[0607] Server: On the first day of each month, each user's behavioral history, purchase history, and emotional data are input into the AI ​​model and emotion engine. The AI ​​model learns each user's purchasing habits and selects the most appropriate coupon using cluster analysis and recommendation algorithms. The emotion engine also analyzes the emotional data and further optimizes coupon selection based on the user's current emotional state.

[0608] Step 4:

[0609] Server: Select a custom template based on the coupon information selected for each user. Embed coupon information for each user in the custom template to generate individually tailored coupon ads. Use dynamic templates to display specific products based on the user's name, past purchase history, or emotional state.

[0610] Step 5:

[0611] Server: Delivers the generated customized advertisements to the user's device.

[0612] Device: When the app is opened on the 1st of each month, a customized ad is displayed on the home screen. The fact that the ad was displayed is sent as feedback to the server.

[0613] Step 6:

[0614] Device: When a user clicks on a coupon ad or actually uses a coupon, that information is recorded and feedback data (such as ad click rates and coupon redemption rates) is sent to the server in real time.

[0615] Server: Based on the received feedback data, the AI ​​model, emotion engine algorithms, and coupon selection logic are tuned and reflected in the next analysis.

[0616] Specific examples

[0617] Example 1: User A who frequently purchases daily ingredients

[0618] Device: User A frequently purchases vegetables, meat, and seasonings through the app. Their behavioral and purchasing history is collected and sent to the server. The emotion engine detects from User A's facial expressions that shopping is a low-stress activity.

[0619] Server: The AI ​​model and emotion engine analyze User A's data and determine that coupons for "vegetables" and "meat" are valid.

[0620] Server: Generates a "vegetable discount coupon ad for user A."

[0621] Device: On the first day of each month, coupon advertisements such as "10% off vegetables" will be displayed on User A's app homepage.

[0622] Example 2: User B prefers a specific brand of product

[0623] Device: User B frequently purchases a particular brand of cosmetics. Their purchase history and behavioral history are collected and sent to the server. The emotion engine detects a high level of excitement in User B's voice.

[0624] Server: The AI ​​model and emotion engine analyze User B's data and determine that a product coupon for a specific brand is valid.

[0625] Server: Generates a "brand product discount coupon ad exclusively for User B."

[0626] Device: The coupon advertisement will be displayed on User B's app homepage on the 1st of each month.

[0627] Example 2

[0628] 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."

[0629] Conventional coupon advertising systems generate coupons based solely on a user's behavioral and purchasing history, resulting in insufficient personalization that takes into account the user's current emotional state. This results in insufficient appeal to users' interests and limits the improvement of coupon usage rates and advertising effectiveness. Furthermore, the accuracy of selecting appropriate coupons for each user is low, resulting in a lot of wasted advertising. There was a need to solve these problems and achieve more effective coupon distribution.

[0630] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0631] In this invention, the server includes means for acquiring a user's behavioral history and purchase history, means for acquiring user emotional data using facial recognition and voice analysis technology, and analysis means using an AI model and emotion engine for analyzing the acquired behavioral history, purchase history, and emotional data. This makes it possible to comprehensively analyze a user's purchasing tendencies and emotional state, and generate and distribute coupon advertisements optimized for each user.

[0632] "User behavior history" refers to a record of actions such as clicks, page views, and time spent on an application when a user uses it.

[0633] "User purchase history" refers to a record of the products a user has purchased in the past, the purchase date and time, price, store information, etc.

[0634] "Facial recognition" is a technology that captures a user's facial features and identifies their expressions and emotions.

[0635] "Voice analysis" is a technology that analyzes a user's voice and identifies its tone and emotion.

[0636] "Emotional data" is data that indicates a user's emotional state obtained through facial recognition and voice analysis technology.

[0637] An "AI model" is an artificial intelligence algorithm that learns a user's behavioral and purchasing history and predicts purchasing trends.

[0638] The "emotion engine" is a program that analyzes the acquired emotion data and determines the user's current emotional state.

[0639] "Analysis means" refers to a means for analyzing acquired behavioral history, purchase history, and emotional data using an AI model and an emotion engine.

[0640] A "customized coupon ad" is an individually optimized coupon ad that is generated based on each user's behavioral history, purchase history, and emotional state.

[0641] "User terminal" refers to a device used by a user, such as a smartphone, tablet, or PC.

[0642] This invention is a system that generates individually customized coupon advertisements and delivers them to user devices by acquiring and analyzing user behavioral history, purchase history, and emotion data. This system is implemented using user devices, a server, an AI model, and an emotion engine.

[0643] 1. Collection of user behavioral history, purchase history, and emotional data

[0644] Users operate the application to search for and purchase products.

[0645] The device automatically records the user's behavioral history (clicks, page views, time spent) and purchase history (purchased products, purchase date and time, price, store information). For example, if a user views a product page for 30 seconds, that information will be recorded by the device.

[0646] The device uses facial recognition and voice analysis technologies to collect emotional data from the user's facial expressions and voice. For example, the camera detects when the user is smiling and records the intensity of that smile as a numerical value.

[0647] The device transmits the collected data in real time to a server using an internet connection.

[0648] 2. Data storage and preprocessing

[0649] The server stores the received behavioral history, purchase history, and emotion data in a database using an RDBMS such as MySQL or PostgreSQL.

[0650] The server cleans the data and fills in and corrects missing or outlier values. For example, if there is data that is missing a purchase date and time, it fills in the appropriate value.

[0651] The server converts and normalizes the data into a format that can be processed by the AI ​​model and emotion engine, for example, converting text data into numeric vectors.

[0652] 3. Data analysis using AI models and emotion engines

[0653] On the first day of each month, the server inputs each user's behavioral history, purchase history, and emotional data into the AI ​​model and emotion engine.

[0654] The server uses an AI model to learn users' purchasing habits and then uses cluster analysis and recommendation algorithms to select the most suitable coupons for each user. For example, if a user has purchased a lot of vegetables in the past, vegetable-related coupons will be selected for that user.

[0655] The server uses an emotion engine to analyze the emotion data and further optimize the coupons based on the user's emotional state, for example, if the user is expressing joy, it selects coupons with positive messages.

[0656] 4. Generate personalized ads

[0657] The server then uses the analysis results to generate customized coupon ads for each user, using dynamic templates to display specific products based on the user's name, past purchase history, and emotional state.

[0658] The server generates advertising images and banners with optimal coupon information embedded and integrates them with the advertising design. For example, it generates a banner image that reads, "User A, please use this coupon for 10% off vegetables."

[0659] 5. Delivery of advertisements

[0660] The server then delivers the generated customized advertisements to the user's device in real time.

[0661] The device will display a customized advertisement on the home screen when the app is opened on the first day of each month. For example, when user A starts the app, a coupon advertisement for "10% off vegetables" will be displayed on the home screen.

[0662] Specific examples

[0663] Example 1: User A who frequently purchases daily ingredients

[0664] User A buys groceries on a daily basis.

[0665] The device records user A's actions when searching for and purchasing vegetables, meat, and seasonings using the app.

[0666] The emotion engine detects from User A's facial expression that shopping is a low-stress activity.

[0667] The server uses an AI model and emotion engine to analyze User A's data and determines that coupons for "vegetables" and "meat" are valid.

[0668] The server generates a "vegetable discount coupon advertisement exclusive to User A" and delivers it to User A's app.

[0669] On the first day of each month, the device will display a coupon advertisement for "10% off vegetables" on the top screen of User A's app.

[0670] Example 2: User B prefers a specific brand of product

[0671] User B frequently purchases a particular brand of cosmetics.

[0672] The terminal collects purchase history and behavior history and transmits them to the server.

[0673] The emotion engine detects a high level of excitement in User B's voice.

[0674] The server uses an AI model and emotion engine to analyze User B's data and determine that a product coupon for a specific brand is valid.

[0675] The server generates a "brand product discount coupon advertisement exclusive to User B" and delivers it to User B's app.

[0676] On the first day of each month, the device will display a coupon advertisement for "20% off brand cosmetics" on the top screen of User B's app.

[0677] This allows users to receive optimal coupon advertisements based on their purchasing behavior and emotional state, and businesses to maximize the effectiveness of their advertisements.

[0678] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0679] Step 1: Collect user behavioral, purchasing, and sentiment data

[0680] Users operate the app to search for and purchase products, launch the app, browse pages, and purchase products.

[0681] The device records user behavior (clicks, page views, and time spent on the site). For example, if a user views a product page for 30 seconds, that information is recorded.

[0682] The device also records the user's purchase history (purchased items, purchase date and time, price, store information). For example, if a user purchases a 1,000 yen item on March 1st, the details will be recorded.

[0683] The device uses facial recognition and voice analysis technology to collect emotional data from the user's facial expressions and voice. For example, the camera detects when the user is smiling and records the intensity of that smile.

[0684] The terminal transmits the collected behavioral history, purchase history, and emotional data to the server in real time.

[0685] Input: User operation data, facial expression data, voice data

[0686] Output: Recorded behavioral history, purchase history, emotional data

[0687] Step 2: Storing and Preprocessing Data

[0688] The server stores the received behavioral history, purchase history, and emotion data in a database, using an RDBMS such as MySQL or PostgreSQL.

[0689] The server cleans the stored data and fills in and corrects missing or outlier values. For example, if there is data that is missing a purchase date and time, it fills in the appropriate value.

[0690] The server converts and normalizes the data into a format that can be processed by the AI ​​model and emotion engine, for example, converting text data into numeric vectors.

[0691] Input: Collected behavioral history, purchase history, and raw emotional data

[0692] Output: Cleaned and normalized data

[0693] Step 3: Data analysis with AI models and emotion engines

[0694] On the first day of each month, the server inputs each user's behavioral history, purchase history, and emotional data into the AI ​​model and emotion engine.

[0695] The server uses an AI model to learn users' purchasing habits, and then uses cluster analysis and recommendation algorithms to select the most suitable coupons for each user. For example, if a user has purchased a lot of vegetables in the past, vegetable-related coupons will be selected for that user.

[0696] The server analyzes the emotion data using an emotion engine to further optimize coupon selection based on the user's emotional state, for example, selecting coupons with positive messages when the user is expressing joy.

[0697] Input: Cleaned and normalized behavioral history, purchase history, and sentiment data

[0698] Output: Coupon information optimized for each user

[0699] Step 4: Generate a personalized ad

[0700] The server then uses the results of the AI ​​model and emotion engine to generate customized coupon ads for each user, using dynamic templates to display specific products based on the user's name, past purchase history, and emotional state.

[0701] The server generates advertising images and banners with optimal coupon information embedded and integrates them with the advertising design. For example, it generates a banner image that reads, "User A, please use this coupon for 10% off vegetables."

[0702] Input: Coupon information optimized for each user

[0703] Output: Generated customized coupon ad

[0704] Step 5: Serving Ads

[0705] The server then delivers the generated customized advertisements to the user's device in real time.

[0706] When the app is opened on the first day of each month, the device displays a customized advertisement on the home screen. For example, when user A starts the app, a coupon advertisement for "10% off vegetables" appears on the home screen.

[0707] Input: Generated customized coupon ad

[0708] Output: Coupon ad displayed on user's device

[0709] (Application example 2)

[0710] 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."

[0711] Conventional coupon advertising systems rely solely on users' behavioral and purchasing histories for personalization, making it difficult to deliver appropriate ads that reflect the user's momentary emotional state. Furthermore, the timing and method of ad delivery are limited, making it difficult to provide more useful and desirable ads to users.

[0712] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0713] In this invention, the server includes means for acquiring a user's behavioral history and purchase history, means for analyzing the acquired behavioral history and purchase history using an AI model, means for acquiring and analyzing emotional data, means for generating a coupon advertisement customized for each user based on the analysis results, and means for delivering the generated coupon advertisement to the user terminal and displaying it on the display of the smart device, thereby enabling timely and appropriate advertisement delivery based on the user's emotional state.

[0714] "User behavior history" is a record of actions such as clicks, page views, and time spent on a website or application.

[0715] "Purchase history" is a record of the type of product purchased by the user, the purchase date and time, price, store information, etc.

[0716] An "AI model" is an algorithm or computational model that uses artificial intelligence technology to analyze data and derive specific results.

[0717] "Analysis means" refers to the techniques and methods used to analyze acquired data and convert it into meaningful information.

[0718] "Emotional data" refers to information about a user's emotional state analyzed based on their facial expressions, voice, and other biometric information.

[0719] "Customized coupon ads" are individual coupon ads generated based on each user's behavioral history, purchasing history, and emotional state.

[0720] A "smart device" is a device that has internet connectivity and a user-operable display.

[0721] "Means for displaying on a display" refers to a display function for visually presenting the generated information to the user.

[0722] This invention is a system that acquires a user's behavioral history, purchase history, and emotional data, analyzes them, generates a coupon advertisement customized for each user, and delivers it to the user's terminal. Specific embodiments of the system are described below.

[0723] server:

[0724] 1. The server acquires the user's behavioral history and purchase history and stores it in a database, including the user's clicks, page views, time spent on the website or application, as well as the type of product purchased, purchase date and time, price, store information, etc.

[0725] 2. The server has an emotion engine for acquiring emotion data and analyzes the user's emotional state in real time from their facial expressions and voice. The emotion data generated by the emotion engine is stored in a database along with their behavioral history and purchase history.

[0726] 3. The server inputs the collected data into an AI model to analyze the user's purchasing habits and emotional state. The AI ​​model then uses cluster analysis and recommendation algorithms to select the most suitable coupon for each user.

[0727] 4. Based on the analysis results, the server uses dynamic templates to generate customized coupon ads for each user.

[0728] Device:

[0729] 1. User devices include smart devices such as smartphones, smart glasses, and head-mounted displays. These devices receive coupon advertisements distributed from the server and display them on their displays.

[0730] 2. The device has the ability to collect emotion data in real time when the user uses an application and send it to the server. For example, the device can capture the user's facial expressions using a camera mounted on smart glasses and analyze them with the emotion engine.

[0731] Examples:

[0732] For example, suppose user A is wearing smart glasses. When user A is in a supermarket, the camera in the smart glasses captures user A's facial expression data in real time, which is analyzed by the emotion engine. If the emotion engine detects user A's emotional state as "joy," the server sends this information to the AI ​​model and generates the optimal coupon advertisement for user A. The generated coupon advertisement is displayed on the smart glasses' display.

[0733] Generate AI model prompt:

[0734] "Input the user's facial expression data and purchase history and generate the best ads and coupons. If the user is smiling, select and display positive ads."

[0735] In this way, timely and appropriate advertising can be delivered based on the user's emotional state, and the use of smart devices also allows users to enjoy a more intuitive and personalized advertising experience.

[0736] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0737] Step 1:

[0738] The device acquires the user's behavioral history and purchase history. Specifically, it records operation data (clicks, page views, time spent, purchased items, purchase date and time, etc.) when the user uses a smart device or application, and sends it to a database. The input is the user's operation data, and the output is the behavioral history and purchase history data stored in the server-side database.

[0739] Step 2:

[0740] The device acquires the user's emotional data. The user's facial expressions are captured in real time using smart glasses or a smartphone camera, and analyzed by the emotion engine. The analysis results (emotion data) are sent to the server. The input is the captured facial expression data, and the output is the analyzed emotional data.

[0741] Step 3:

[0742] The server stores the acquired behavioral history, purchase history, and emotion data in a database. Specifically, it performs data cleaning processes, complements and corrects missing and outlier values, and converts and normalizes the data into a format suitable for the AI ​​model and emotion engine. The input is the user's behavioral history, purchase history, and emotion data, and the output is the normalized data stored in the database.

[0743] Step 4:

[0744] The server analyzes user data using an AI model and emotion engine. At regularly scheduled times (for example, the first day of each month), each user's behavioral history, purchase history, and emotional data are input into the AI ​​model and emotion engine. The AI ​​model learns the user's purchasing trends, and the emotion engine analyzes the emotional data. The inputs are normalized behavioral history, purchase history, and emotional data, and the output is the analysis results (selection of the optimal coupon).

[0745] Step 5:

[0746] The server generates customized coupon ads based on the analysis results. Specifically, it uses the analysis results obtained from the AI ​​model and emotion engine to create dynamic templates to generate individual coupon ads for each user. The input is the analysis results, and the output is the customized coupon ads.

[0747] Step 6:

[0748] The server delivers the generated coupon advertisement to the user terminal. The user terminal receives the delivered coupon advertisement and displays it on the display of the smart device. The input is the customized coupon advertisement, and the output is the advertisement displayed on the display of the user terminal.

[0749] Step 7:

[0750] The device monitors whether the user utilizes the generated coupon advertisement and collects new behavioral history, purchase history, and emotional data again. The input is the user's advertisement usage behavior data, and the output is updated behavioral history, purchase history, and emotional data. This makes it possible to generate even more optimized advertisements in the next cycle.

[0751] At each step, the server, terminal, or user plays a key role, and the processes of data collection, analysis, generation, distribution, and reevaluation are carried out smoothly, enabling the provision of optimal coupon advertisements to users.

[0752] 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.

[0753] 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.

[0754] 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.

[0755] [Third embodiment]

[0756] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0757] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0758] 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).

[0759] 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.

[0760] 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.

[0761] 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).

[0762] 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.

[0763] 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.

[0764] 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.

[0765] 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.

[0766] 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.

[0767] 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."

[0768] The present invention is a system that acquires and analyzes a user's behavioral history and purchase history to generate and distribute a coupon advertisement customized for each user. This system includes a means for acquiring the user's behavioral history and purchase history, an analysis means using an AI model to analyze the acquired behavioral history and purchase history, a means for generating a coupon advertisement customized for each user based on the analysis results, and a means for distributing the generated coupon advertisement to the user's terminal.

[0769] 1. Collection of user behavioral and purchasing history

[0770] Device: When a user uses the app, operation history and purchase information are recorded. Behavioral history includes the links the user clicked, the product pages viewed, the time spent on the app, and information about campaigns participated in. Purchase history includes the name of the purchased product, the date and time of purchase, the price, and store information.

[0771] Terminal: Sends this data to the server in real time.

[0772] 2. Data storage and preprocessing

[0773] Server: The received behavioral history and purchase history are stored in a database. The stored data is checked for missing values ​​and outliers, and then corrected or supplemented in an appropriate manner.

[0774] Server: Transforms and normalizes the data into a format that can be processed by the AI ​​model.

[0775] 3. Data analysis using AI models

[0776] Server: Inputs each user's behavioral history and purchase history into the AI ​​model to learn the user's purchasing trends.

[0777] Server: Uses cluster analysis and recommendation algorithms to select the best coupon for each user.

[0778] 4. Generate personalized ads

[0779] Server: Generates customized coupon ads for each user based on the results of the AI ​​model analysis. Dynamic templates are used to display specific products based on the user's name and purchasing history.

[0780] Server: Generates advertising images and banners with optimal coupon information embedded and integrates them into the advertising design.

[0781] 5. Delivery of advertisements

[0782] Server: The generated customized advertisement is delivered to the user's device. It is set to be displayed on the user's app homepage at the scheduled time on the first day of each month.

[0783] On your device: When you open the app, a customized ad will appear on the home screen.

[0784] Specific examples

[0785] Example 1: User A who frequently purchases daily ingredients

[0786] Device: User A regularly purchases ingredients. He searches for and purchases vegetables, meats, and seasonings using the app.

[0787] Server: Based on User A's purchase history and behavioral history, the AI ​​model determines that coupons for "vegetables" and "meat" are valid.

[0788] Server: Generates a "vegetable discount coupon ad for user A."

[0789] Device: On the first day of each month, coupon advertisements such as "10% off vegetables" will be displayed on User A's app homepage.

[0790] Example 2: User B prefers a specific brand of product

[0791] Device: User B frequently purchases a particular brand of cosmetics.

[0792] Server: Analyzes User B's purchasing history and determines that a product coupon for a specific brand is valid.

[0793] Server: Generates a "brand product discount coupon ad exclusively for User B."

[0794] Device: On the first day of each month, coupon advertisements such as "20% off brand cosmetics" will be displayed on User B's app homepage.

[0795] summary

[0796] This system allows users to receive personalized coupon ads based on their purchasing behavior, while also helping businesses reduce advertising production and placement costs while increasing user engagement and usage rates.

[0797] The processing flow will be explained below.

[0798] Step 1:

[0799] Users: Use the app to search for and purchase products, and view promotions and special offers within the app.

[0800] Device: Records user actions in real time and collects behavioral history (clicks, page views, time spent, etc.) as well as purchase history (purchased products, purchase date and time, purchase price, purchase store, etc.).

[0801] Terminal: Sends collected behavioral and purchase history to the server in real time.

[0802] Step 2:

[0803] Server: Stores the received behavioral history and purchase history in a database.

[0804] Server: Performs data cleaning operations, imputing missing values, correcting outliers, and, if necessary, converting and normalizing the data to a format that is easier for the AI ​​model to process.

[0805] Step 3:

[0806] Server: On the scheduled first day of each month, each user's behavioral and purchasing history is input into the AI ​​model.

[0807] Server: The AI ​​model analyzes the input data and learns the purchasing habits of each user. Specifically, it uses cluster analysis and recommendation algorithms to select the most suitable coupon for each user.

[0808] Step 4:

[0809] Server: Select a custom template based on the coupon information selected for each user.

[0810] Server: Generate personalized coupon ads by embedding coupon information for each user in custom templates. Specifically, we use dynamic templates to display specific products based on the user's name and past purchase history.

[0811] Step 5:

[0812] Server: Delivers the generated customized advertisements to the user's device.

[0813] Device: When you open the app on the 1st of each month, a customized ad will be displayed on the home screen.

[0814] Step 6:

[0815] Device: Records information when a user clicks on a coupon ad or actually uses a coupon.

[0816] Terminal: Sends feedback data (such as ad click rates and coupon redemption rates) to the server in real time.

[0817] Server: Based on the received feedback data, the AI ​​model algorithm and coupon selection logic are tuned and reflected in the next analysis.

[0818] Specific examples

[0819] Example 1: User A who frequently purchases daily ingredients

[0820] Device: User A frequently purchases vegetables, meat, and seasonings through the app. Their behavioral and purchase history is collected and sent to the server.

[0821] Server: The AI ​​model analyzes User A's data and determines that coupons for "vegetables" and "meat" are valid.

[0822] Server: Generates customized ads including coupons for "10% off vegetables" and "20% off meat" and delivers them to User A's device.

[0823] Device: The coupon advertisement will be displayed on User A's app homepage on the 1st of each month.

[0824] Example 2: User B prefers a specific brand of product

[0825] Device: User B frequently purchases a particular brand of cosmetics. Their purchase history and behavioral history are collected and sent to the server.

[0826] Server: The AI ​​model analyzes User B's data and determines that a product coupon for a specific brand is valid.

[0827] Server: Generate a customized ad containing a coupon for "20% off a specific brand of cosmetics" and deliver it to User B's device.

[0828] Device: The coupon advertisement will be displayed on User B's app homepage on the 1st of each month.

[0829] Example 1

[0830] 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."

[0831] Conventional ad distribution systems deliver generic coupon ads, making it impossible to provide personalized ads based on each user's purchasing trends and behavioral history. This makes it difficult to effectively deliver coupon ads that match the user's interests and needs, resulting in problems such as the inability to expect improvements in ad click rates and purchasing intent.

[0832] 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.

[0833] In this invention, the server includes means for acquiring user behavioral history and purchase history, means for transmitting the acquired behavioral history and purchase history to the server in real time, means for saving the received behavioral history and purchase history to a database, means for checking the saved data for missing values ​​and outliers and appropriately correcting or completing them, means for converting and normalizing the data into a format that can be processed by an AI model, means for inputting each user's behavioral history and purchase history into an AI model and having it learn the user's purchasing tendencies, means for selecting the most suitable coupon for each user using cluster analysis and a recommendation algorithm, means for generating a coupon advertisement customized for each user based on the analysis results of the AI ​​model, means for delivering the generated coupon advertisement to the user's device, and means for displaying the customized advertisement on the top screen when the user opens the app on the user's device. This enables effective delivery of personalized coupon advertisements based on each user's purchasing tendencies and behavioral history.

[0834] "User behavior history" refers to information related to operations, such as links clicked, product pages viewed, time spent on the app, and information about campaigns participated in, that is recorded when the user operates the app.

[0835] "Purchase history" refers to detailed information about specific purchases, such as the name of the product purchased by the user, the date and time of purchase, the price, and store information.

[0836] A "server" is a device or system for receiving, storing, and analyzing behavioral history and purchase history sent by a user.

[0837] "Database" means a structured data storage system for efficiently storing and managing received behavioral and purchasing histories.

[0838] An "AI model" is an artificial intelligence algorithm and computational model used to analyze a user's behavioral history and purchase history and learn about the user's purchasing trends.

[0839] "Normalization" is the process of converting data into a format that can be processed by an AI model and standardizing the scale and format of the data.

[0840] "Cluster analysis" is an analytical technique for grouping data from multiple users and identifying user groups with similar patterns and trends.

[0841] A "recommendation algorithm" is a method for recommending the most suitable products and coupons to each user based on the user's purchasing history and behavioral history.

[0842] "Customized coupon ads" are ads that include coupons that are customized to meet the interests and needs of a specific user based on the user's individual behavioral history and purchasing history.

[0843] The "top screen" is the main screen that appears first on a user's device when they open the app.

[0844] MODE FOR CARRYING OUT THE INVENTION

[0845] The present invention is a system that acquires and analyzes a user's behavioral history and purchase history to generate and distribute coupon advertisements customized for each user. This system includes the following main means.

[0846] Collection of user behavior and purchase history

[0847] Device: When a user operates the app, their behavioral history, such as the links they clicked, the product pages they viewed, the time they spent there, and the campaign information they participated in, is recorded. Purchase history, such as the name of the product purchased, the date and time of purchase, the price, and store information, is also recorded. This data is sent to the server in real time.

[0848] Data storage and preprocessing

[0849] Server: The received behavioral and purchase history is stored in a database. The stored data is checked for missing values ​​and outliers, and corrected or supplemented in an appropriate manner. The data is then converted into a format that can be processed by the AI ​​model and normalized.

[0850] Data analysis using AI models

[0851] Server: Inputs each user's behavioral and purchase history into the AI ​​model to learn their purchasing trends. Using cluster analysis and recommendation algorithms, the server selects the most suitable coupon for each user.

[0852] Generate personalized ads

[0853] Server: Generates customized coupon ads for each user based on the analysis results of the AI ​​model. Dynamic templates are used to display specific products based on the user's name and purchasing history. Generates ad images and banners with the optimal coupon information embedded and integrated into the ad design.

[0854] Ad serving

[0855] Server: The server delivers the generated customized ads to the user's device. These ads are set to be displayed on the user's app homepage at a pre-scheduled time, for example, on the first day of each month.

[0856] On your device: When you open the app, a customized ad will appear on the home screen.

[0857] Specific examples

[0858] Example 1: User A who frequently purchases daily ingredients

[0859] Device: User A searches for and purchases daily ingredients. For example, they search for "cabbage" or "chicken" in the app and complete the purchase process.

[0860] Server: User A's purchase history and behavioral history are input into the AI ​​model, and it is determined that the coupons for "cabbage" and "chicken" are valid.

[0861] Server: Generate a "vegetable discount coupon ad for user A." For example, create a coupon ad for "10% off cabbage."

[0862] Device: On the first day of each month, a coupon ad for "10% off cabbage" will be displayed on User A's app homepage.

[0863] Example 2: User B prefers a specific brand of product

[0864] Device: User B frequently purchases cosmetics from a specific brand, for example, "Brand X lipstick."

[0865] Server: Analyzes User B's purchase history and determines that "Brand X's cosmetics coupon is valid."

[0866] Server: Generate a "brand product discount coupon ad exclusively for User B." For example, create a coupon ad for "20% off brand X lipstick."

[0867] Device: On the first day of each month, a coupon ad for "20% off Brand X lipstick" will be displayed on User B's app homepage.

[0868] Prompt Sentence Examples

[0869] "Design a system that collects user behavioral and purchasing histories and analyzes them using an AI model."

[0870] "Describe the algorithm that generates customized coupon ads for each user."

[0871] "Please explain the process of collecting data in real time and delivering advertisements based on the analysis results."

[0872] The system of the present invention implemented in this way allows users to receive personalized coupon advertisements based on their purchasing behavior, enabling businesses to reduce advertising production and placement costs while improving user engagement and usage rates.

[0873] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0874] Step 1:

[0875] The device records the user's behavioral history and purchase history when the user operates the app. Specifically, it collects information in real time, such as the links the user clicked, the product pages they viewed, the length of time they stayed, and information about campaigns they participated in. It also records the purchase history, such as the name of the product purchased, the date and time of purchase, the price, and store information. The input data is the user's operations and purchase information, and the output is data sent to the server in real time.

[0876] Step 2:

[0877] The server receives the behavioral history and purchase history sent from the device and stores it in a database. When saving, the data is checked for missing or abnormal values ​​and corrected or supplemented in an appropriate manner. For example, data with missing purchase dates and times is supplemented with estimated dates and times. The input data is the sent behavioral history and purchase history, and the output is the corrected and supplemented saved data.

[0878] Step 3:

[0879] The server converts and normalizes the stored data into a format that the AI ​​model can process. For example, it converts purchase dates and times into a unified year / month / day format and normalizes price data to a certain scale. The input data is the corrected and supplemented stored data, and the output is the normalized data.

[0880] Step 4:

[0881] The server inputs each user's behavioral history and purchase history into the AI ​​model to learn the user's purchasing trends. For example, it learns what other products a user who purchased a "Festival Yukata Set" is interested in. The input data is normalized behavioral history and purchase history, and the output is a learned purchasing trend model.

[0882] Step 5:

[0883] The server uses cluster analysis and recommendation algorithms to select the most suitable coupon for each user. For example, it proposes summer festival-related coupons to a group of users who like similar products. The input data is the trained purchasing tendency model, and the output is the selected optimal coupon information.

[0884] Step 6:

[0885] The server generates a coupon ad customized for each user based on the analysis results of the AI ​​model. For example, for a user who purchases a "Festival Yukata Set," it generates a coupon ad offering 10% off summer festival-related products. The input data is the selected optimal coupon information, and the output is a customized coupon ad.

[0886] Step 7:

[0887] The server delivers the generated customized advertisement to the user's device. For example, a "10% off summer festival related products" coupon is delivered on the first day of every month. The input data is the customized coupon advertisement, and the output is the delivery data to the user's device.

[0888] Step 8:

[0889] When a user opens an app, the device displays a customized advertisement on the home screen. For example, when a user opens an app, a coupon advertisement for "10% off summer festival-related products" is displayed on the home screen. The input data is the delivered customized advertisement, and the output is the displayed advertisement.

[0890] (Application example 1)

[0891] 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."

[0892] In today's information society, providing users with appropriate advertisements and coupons is an important part of a marketing strategy. However, current coupon distribution systems do not fully utilize users' purchasing trends and behavioral history, resulting in a lot of wasteful advertisement distribution and often failing to increase user engagement. Furthermore, there is a lack of technology to personalize coupons based on individual purchasing trends, making efficient advertisement distribution difficult. The present invention aims to solve these problems by providing a system that generates and distributes highly accurate coupon advertisements based on individual users' purchasing trends.

[0893] 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.

[0894] In this invention, the server includes means for acquiring user behavioral history and purchase history, means for processing the acquired behavioral history and purchase history, means for an AI model to analyze the purchasing trends of each user using the processed data, means for generating a coupon advertisement customized for each user based on the analysis results, and means for delivering the generated coupon advertisement to the user terminal. This enables the generation of personalized coupon advertisements based on the user's purchasing trends and efficient advertisement delivery.

[0895] "User behavior history" refers to a record of the actions, clicks, browsing time, search queries, etc. that a user takes on an application or website.

[0896] "Purchase history" refers to a record of information about products a user has purchased in the past, including the date and time of purchase, price, and place of purchase.

[0897] "Means" refers to a specific method or component such as a method, device, or system for achieving a specific purpose.

[0898] An "AI model" is an algorithm or model that uses artificial intelligence techniques to analyze data and generate specific results or predictions.

[0899] "Data processing" refers to the process of converting raw data into a format that can be processed by an AI model, including normalizing the data and filling in missing values.

[0900] "Purchasing trends" are the results of an analysis of what products users prefer to purchase, how often they do so, and when.

[0901] A "coupon ad" is an ad that offers users a discount on a particular product or service, and includes a coupon code or discount information.

[0902] "Generating" is the process of creating new data or content based on the analysis results.

[0903] A "user device" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[0904] A "push notification" is a real-time notification message sent by an application to a user device.

[0905] This invention is a system that acquires and analyzes a user's behavioral history and purchase history to generate a coupon advertisement customized for each user and distributes it to the user's terminal. This system is implemented as follows.

[0906] First, the user's device records the user's behavioral history, such as the operation history, clicks, browsing time, and search queries performed when using the application, as well as the purchase history, such as information on previously purchased products, purchase date and time, price, and purchase location. This data is sent to the server in real time.

[0907] The server then stores the received behavioral and purchase history in a database. This stored data is checked for missing values ​​and outliers, and then corrected and supplemented in an appropriate manner. The data is then converted and normalized into a format that can be processed by the AI ​​model. Libraries such as StandardScaler are used for data preprocessing.

[0908] The normalized data is input into an AI model to analyze each user's purchasing habits. Principal component analysis (PCA) and clustering algorithms (e.g., KMeans) are used for the analysis. This allows users to be appropriately classified into clusters based on their purchasing habits, and the most appropriate coupons are selected for each cluster.

[0909] The AI ​​model then uses the results of its analysis to generate a personalized coupon ad for each user. The ad is generated using dynamic templates to display specific products based on the user's name and purchasing history. The ad image and banner are then generated and integrated with the ad design, incorporating the optimal coupon information.

[0910] Finally, the generated customized advertisement is delivered to the user's device, for example, via push notification. Push notifications allow users to receive interesting advertisements in real time, increasing their motivation to make a purchase.

[0911] For example, if a user tends to purchase many e-books, the system analyzes their purchase history and generates e-book coupon ads. On the first day of each month, the system delivers personalized ads to the user's smartphone, such as "20% off new e-books!"

[0912] As described above, the present invention provides a system that generates personalized advertisements based on a user's behavioral history and purchase history, and realizes efficient advertisement distribution.

[0913] An example of a prompt is as follows:

[0914] Design an AI system that generates personalized ads based on users' behavioral and purchasing history. This system involves the following steps:

[0915] 1. Collection of user behavioral and purchasing history

[0916] 2. Preprocessing of these data (dealing with missing values, outliers, and data normalization)

[0917] 3. Data analysis using cluster analysis and recommendation algorithms

[0918] 4. Generate coupon ads customized for each user

[0919] 5. Delivery of these advertisements to user devices

[0920] Please generate specific program code based on this prompt.

[0921] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0922] Step 1:

[0923] The user's device acquires the user's behavioral history and purchase history. Specifically, it records in real time the operations performed when the user uses the application (clicks, searches, browsing time, etc.) and information about purchased products (product name, purchase date and time, price, etc.). This data is sent to the server. The input data is the user's operations and purchase information, and the output data is the raw behavioral history and purchase history sent to the server.

[0924] Step 2:

[0925] The server stores the received behavioral history and purchase history in a database. The stored data is checked for missing values ​​and outliers, and corrected or supplemented as necessary. Specifically, the database system is used to manage multiple data entries and ensure data consistency. The input data is the received behavioral history and purchase history. The output data is the formatted behavioral history and purchase history data.

[0926] Step 3:

[0927] The server converts the formatted behavioral history and purchase history data into a format that can be processed by the AI ​​model and normalizes the data. Specifically, it scales the data using a tool such as StandardScaler. The input data is the formatted behavioral history and purchase history data, and the output data is the normalized data.

[0928] Step 4:

[0929] The server inputs the normalized data into an AI model to analyze each user's purchasing trends. Principal component analysis (PCA) and clustering algorithms (such as KMeans) are used to classify the data into clusters. The input data is normalized data, and the output data is the clustering results. Specifically, the feature values ​​of each cluster are analyzed to clarify the user's purchasing trends.

[0930] Step 5:

[0931] The server generates coupon ads customized for each user based on the analysis results of the AI ​​model. Coupon information is embedded using dynamic templates to design ads suited to each user. The input data is the clustering results, and the output data is the customized coupon ads. Specifically, the ads are dynamically generated using a template engine.

[0932] Step 6:

[0933] The server delivers the generated customized advertisement to the user's device. Specifically, the advertisement is sent to the user in real time using a method such as push notification. The input data is the customized coupon advertisement, and the output data is the advertisement displayed on the user's device. Specifically, the advertisement data is sent to the user's device using a communication protocol.

[0934] Through the above steps, the present invention provides a system that generates personalized advertisements based on a user's behavioral history and purchase history, and realizes efficient advertisement distribution.

[0935] 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.

[0936] The present invention is a system that generates and distributes coupon advertisements customized for each user by acquiring and analyzing the user's behavioral history, purchase history, and emotional data. This system includes a means for acquiring the user's behavioral history and purchase history, an emotion engine for acquiring and analyzing the emotional data, an analysis means using an AI model for analyzing the acquired behavioral history and purchase history, a means for generating coupon advertisements customized for each user based on the analysis results, and a means for distributing the generated coupon advertisements to the user terminal.

[0937] 1. Collection of user behavioral history, purchase history, and emotional data

[0938] Device: Performs operations when the user uses the app. Collects behavioral history (clicks, page views, time spent) and purchase history (purchased products, purchase date and time, price, store information).

[0939] On the device: Using facial recognition and voice analysis technology to collect emotional data from the user's facial expressions and voice.

[0940] Terminal: Collected behavioral history, purchase history, and emotional data is sent to the server in real time.

[0941] 2. Data storage and preprocessing

[0942] Server: Stores the received behavioral history, purchase history, and emotion data in a database.

[0943] Server: Performs data cleaning processes, imputes and corrects missing values ​​and outliers, and normalizes and converts the data into a format that can be processed by the AI ​​model and emotion engine.

[0944] 3. Data analysis using AI models and emotion engines

[0945] Server: On the first day of each month, each user's behavioral history, purchase history, and emotional data are input into the AI ​​model and emotion engine.

[0946] Server: The AI ​​model learns users' purchasing habits and uses cluster analysis and recommendation algorithms to select the most suitable coupons for each user.

[0947] Server: The emotion engine analyzes the input emotion data and further optimizes coupon selection based on the user's current emotional state.

[0948] 4. Generate personalized ads

[0949] Server: Generates customized coupon ads for each user based on the analysis results of the AI ​​model and emotion engine, using dynamic templates to display specific products based on the user's name, past purchase history, and emotional state.

[0950] Server: Generates advertising images and banners with optimal coupon information embedded and integrates them into the advertising design.

[0951] 5. Delivery of advertisements

[0952] Server: Delivers the generated customized advertisements to the user's device.

[0953] Device: When you open the app on the 1st of each month, a customized ad will be displayed on the home screen.

[0954] Specific examples

[0955] Example 1: User A who frequently purchases daily ingredients

[0956] Device: User A regularly buys ingredients. He searches for and purchases vegetables, meats, and seasonings using the app. The emotion engine detects from User A's facial expressions that shopping is a low-stress activity.

[0957] Server: The AI ​​model and emotion engine analyze User A's data and determine that coupons for "vegetables" and "meat" are valid.

[0958] Server: Generates a "vegetable discount coupon ad for user A."

[0959] Device: On the first day of each month, coupon advertisements such as "10% off vegetables" will be displayed on User A's app homepage.

[0960] Example 2: User B prefers a specific brand of product

[0961] Device: User B frequently purchases a specific brand of cosmetics. Their purchase history and behavioral history are collected and sent to the server. The emotion engine detects a high level of excitement in User B's voice.

[0962] Server: The AI ​​model and emotion engine analyze User B's data and determine that a product coupon for a specific brand is valid.

[0963] Server: Generates a "brand product discount coupon ad exclusively for User B."

[0964] Device: On the first day of each month, coupon advertisements such as "20% off brand cosmetics" will be displayed on User B's app homepage.

[0965] summary

[0966] This system allows users to receive personalized coupon ads based on their purchasing behavior and emotional state, while also helping businesses reduce advertising production and placement costs while increasing user engagement and usage rates.

[0967] The processing flow will be explained below.

[0968] Step 1:

[0969] Users: Use the app to search for and purchase products, and view promotions and special offers within the app.

[0970] Device: Records user actions in real time and collects behavioral history (clicks, page views, time spent). It also records purchase history (items purchased, purchase date and time, purchase price, purchase store, etc.). At the same time, it uses facial recognition and voice analysis technology to collect emotional data from the user's facial expressions and voice.

[0971] Terminal: Collected behavioral history, purchase history, and emotional data is sent to the server in real time.

[0972] Step 2:

[0973] Server: The received behavioral history, purchase history, and emotion data is stored in a database. The stored data is checked for missing values ​​and outliers, and then appropriately supplemented and corrected. The data is converted and normalized into a format that is easy for the AI ​​model and emotion engine to process.

[0974] Step 3:

[0975] Server: On the first day of each month, each user's behavioral history, purchase history, and emotional data are input into the AI ​​model and emotion engine. The AI ​​model learns each user's purchasing habits and selects the most appropriate coupon using cluster analysis and recommendation algorithms. The emotion engine also analyzes the emotional data and further optimizes coupon selection based on the user's current emotional state.

[0976] Step 4:

[0977] Server: Select a custom template based on the coupon information selected for each user. Embed coupon information for each user in the custom template to generate individually tailored coupon ads. Use dynamic templates to display specific products based on the user's name, past purchase history, or emotional state.

[0978] Step 5:

[0979] Server: Delivers the generated customized advertisements to the user's device.

[0980] Device: When the app is opened on the 1st of each month, a customized ad is displayed on the home screen. The fact that the ad was displayed is sent as feedback to the server.

[0981] Step 6:

[0982] Device: When a user clicks on a coupon ad or actually uses a coupon, that information is recorded and feedback data (such as ad click rates and coupon redemption rates) is sent to the server in real time.

[0983] Server: Based on the received feedback data, the AI ​​model, emotion engine algorithms, and coupon selection logic are tuned and reflected in the next analysis.

[0984] Specific examples

[0985] Example 1: User A who frequently purchases daily ingredients

[0986] Device: User A frequently purchases vegetables, meat, and seasonings through the app. Their behavioral and purchasing history is collected and sent to the server. The emotion engine detects from User A's facial expressions that shopping is a low-stress activity.

[0987] Server: The AI ​​model and emotion engine analyze User A's data and determine that coupons for "vegetables" and "meat" are valid.

[0988] Server: Generates a "vegetable discount coupon ad for user A."

[0989] Device: On the first day of each month, coupon advertisements such as "10% off vegetables" will be displayed on User A's app homepage.

[0990] Example 2: User B prefers a specific brand of product

[0991] Device: User B frequently purchases a particular brand of cosmetics. Their purchase history and behavioral history are collected and sent to the server. The emotion engine detects a high level of excitement in User B's voice.

[0992] Server: The AI ​​model and emotion engine analyze User B's data and determine that a product coupon for a specific brand is valid.

[0993] Server: Generates a "brand product discount coupon ad exclusively for User B."

[0994] Device: The coupon advertisement will be displayed on User B's app homepage on the 1st of each month.

[0995] Example 2

[0996] 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."

[0997] Conventional coupon advertising systems generate coupons based solely on a user's behavioral and purchasing history, resulting in insufficient personalization that takes into account the user's current emotional state. This results in insufficient appeal to users' interests and limits the improvement of coupon usage rates and advertising effectiveness. Furthermore, the accuracy of selecting appropriate coupons for each user is low, resulting in a lot of wasted advertising. There was a need to solve these problems and achieve more effective coupon distribution.

[0998] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0999] In this invention, the server includes means for acquiring a user's behavioral history and purchase history, means for acquiring user emotional data using facial recognition and voice analysis technology, and analysis means using an AI model and emotion engine for analyzing the acquired behavioral history, purchase history, and emotional data. This makes it possible to comprehensively analyze a user's purchasing tendencies and emotional state, and generate and distribute coupon advertisements optimized for each user.

[1000] "User behavior history" refers to a record of actions such as clicks, page views, and time spent on an application when a user uses it.

[1001] "User purchase history" refers to a record of the products a user has purchased in the past, the purchase date and time, price, store information, etc.

[1002] "Facial recognition" is a technology that captures a user's facial features and identifies their expressions and emotions.

[1003] "Voice analysis" is a technology that analyzes a user's voice and identifies its tone and emotion.

[1004] "Emotional data" is data that indicates a user's emotional state obtained through facial recognition and voice analysis technology.

[1005] An "AI model" is an artificial intelligence algorithm that learns a user's behavioral and purchasing history and predicts purchasing trends.

[1006] The "emotion engine" is a program that analyzes the acquired emotion data and determines the user's current emotional state.

[1007] "Analysis means" refers to a means for analyzing acquired behavioral history, purchase history, and emotional data using an AI model and an emotion engine.

[1008] A "customized coupon ad" is an individually optimized coupon ad that is generated based on each user's behavioral history, purchase history, and emotional state.

[1009] "User terminal" refers to a device used by a user, such as a smartphone, tablet, or PC.

[1010] This invention is a system that generates individually customized coupon advertisements and delivers them to user devices by acquiring and analyzing user behavioral history, purchase history, and emotion data. This system is implemented using user devices, a server, an AI model, and an emotion engine.

[1011] 1. Collection of user behavioral history, purchase history, and emotional data

[1012] Users operate the application to search for and purchase products.

[1013] The device automatically records the user's behavioral history (clicks, page views, time spent) and purchase history (purchased products, purchase date and time, price, store information). For example, if a user views a product page for 30 seconds, that information will be recorded by the device.

[1014] The device uses facial recognition and voice analysis technologies to collect emotional data from the user's facial expressions and voice. For example, the camera detects when the user is smiling and records the intensity of that smile as a numerical value.

[1015] The device transmits the collected data in real time to a server using an internet connection.

[1016] 2. Data storage and preprocessing

[1017] The server stores the received behavioral history, purchase history, and emotion data in a database using an RDBMS such as MySQL or PostgreSQL.

[1018] The server cleans the data and fills in and corrects missing or outlier values. For example, if there is data that is missing a purchase date and time, it fills in the appropriate value.

[1019] The server converts and normalizes the data into a format that can be processed by the AI ​​model and emotion engine, for example, converting text data into numeric vectors.

[1020] 3. Data analysis using AI models and emotion engines

[1021] On the first day of each month, the server inputs each user's behavioral history, purchase history, and emotional data into the AI ​​model and emotion engine.

[1022] The server uses an AI model to learn users' purchasing habits and then uses cluster analysis and recommendation algorithms to select the most suitable coupons for each user. For example, if a user has purchased a lot of vegetables in the past, vegetable-related coupons will be selected for that user.

[1023] The server uses an emotion engine to analyze the emotion data and further optimize the coupons based on the user's emotional state, for example, if the user is expressing joy, it selects coupons with positive messages.

[1024] 4. Generate personalized ads

[1025] The server then uses the analysis results to generate customized coupon ads for each user, using dynamic templates to display specific products based on the user's name, past purchase history, and emotional state.

[1026] The server generates advertising images and banners with optimal coupon information embedded and integrates them with the advertising design. For example, it generates a banner image that reads, "User A, please use this coupon for 10% off vegetables."

[1027] 5. Delivery of advertisements

[1028] The server then delivers the generated customized advertisements to the user's device in real time.

[1029] The device will display a customized advertisement on the home screen when the app is opened on the first day of each month. For example, when user A starts the app, a coupon advertisement for "10% off vegetables" will be displayed on the home screen.

[1030] Specific examples

[1031] Example 1: User A who frequently purchases daily ingredients

[1032] User A buys groceries on a daily basis.

[1033] The device records user A's actions when searching for and purchasing vegetables, meat, and seasonings using the app.

[1034] The emotion engine detects from User A's facial expression that shopping is a low-stress activity.

[1035] The server uses an AI model and emotion engine to analyze User A's data and determines that coupons for "vegetables" and "meat" are valid.

[1036] The server generates a "vegetable discount coupon advertisement exclusive to User A" and delivers it to User A's app.

[1037] On the first day of each month, the device will display a coupon advertisement for "10% off vegetables" on the top screen of User A's app.

[1038] Example 2: User B prefers a specific brand of product

[1039] User B frequently purchases a particular brand of cosmetics.

[1040] The terminal collects purchase history and behavior history and transmits them to the server.

[1041] The emotion engine detects a high level of excitement in User B's voice.

[1042] The server uses an AI model and emotion engine to analyze User B's data and determine that a product coupon for a specific brand is valid.

[1043] The server generates a "brand product discount coupon advertisement exclusive to User B" and delivers it to User B's app.

[1044] On the first day of each month, the device will display a coupon advertisement for "20% off brand cosmetics" on the top screen of User B's app.

[1045] This allows users to receive optimal coupon advertisements based on their purchasing behavior and emotional state, and businesses to maximize the effectiveness of their advertisements.

[1046] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1047] Step 1: Collect user behavioral, purchasing, and sentiment data

[1048] Users operate the app to search for and purchase products, launch the app, browse pages, and purchase products.

[1049] The device records user behavior (clicks, page views, and time spent on the site). For example, if a user views a product page for 30 seconds, that information is recorded.

[1050] The device also records the user's purchase history (purchased items, purchase date and time, price, store information). For example, if a user purchases a 1,000 yen item on March 1st, the details will be recorded.

[1051] The device uses facial recognition and voice analysis technology to collect emotional data from the user's facial expressions and voice. For example, the camera detects when the user is smiling and records the intensity of that smile.

[1052] The terminal transmits the collected behavioral history, purchase history, and emotional data to the server in real time.

[1053] Input: User operation data, facial expression data, voice data

[1054] Output: Recorded behavioral history, purchase history, emotional data

[1055] Step 2: Storing and Preprocessing Data

[1056] The server stores the received behavioral history, purchase history, and emotion data in a database, using an RDBMS such as MySQL or PostgreSQL.

[1057] The server cleans the stored data and fills in and corrects missing or outlier values. For example, if there is data that is missing a purchase date and time, it fills in the appropriate value.

[1058] The server converts and normalizes the data into a format that can be processed by the AI ​​model and emotion engine, for example, converting text data into numeric vectors.

[1059] Input: Collected behavioral history, purchase history, and raw emotional data

[1060] Output: Cleaned and normalized data

[1061] Step 3: Data analysis with AI models and emotion engines

[1062] On the first day of each month, the server inputs each user's behavioral history, purchase history, and emotional data into the AI ​​model and emotion engine.

[1063] The server uses an AI model to learn users' purchasing habits, and then uses cluster analysis and recommendation algorithms to select the most suitable coupons for each user. For example, if a user has purchased a lot of vegetables in the past, vegetable-related coupons will be selected for that user.

[1064] The server analyzes the emotion data using an emotion engine to further optimize coupon selection based on the user's emotional state, for example, selecting coupons with positive messages when the user is expressing joy.

[1065] Input: Cleaned and normalized behavioral history, purchase history, and sentiment data

[1066] Output: Coupon information optimized for each user

[1067] Step 4: Generate a personalized ad

[1068] The server then uses the results of the AI ​​model and emotion engine to generate customized coupon ads for each user, using dynamic templates to display specific products based on the user's name, past purchase history, and emotional state.

[1069] The server generates advertising images and banners with optimal coupon information embedded and integrates them with the advertising design. For example, it generates a banner image that reads, "User A, please use this coupon for 10% off vegetables."

[1070] Input: Coupon information optimized for each user

[1071] Output: Generated customized coupon ad

[1072] Step 5: Serving Ads

[1073] The server then delivers the generated customized advertisements to the user's device in real time.

[1074] When the app is opened on the first day of each month, the device displays a customized advertisement on the home screen. For example, when user A starts the app, a coupon advertisement for "10% off vegetables" appears on the home screen.

[1075] Input: Generated customized coupon ad

[1076] Output: Coupon ad displayed on user's device

[1077] (Application example 2)

[1078] 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."

[1079] Conventional coupon advertising systems rely solely on users' behavioral and purchasing histories for personalization, making it difficult to deliver appropriate ads that reflect the user's momentary emotional state. Furthermore, the timing and method of ad delivery are limited, making it difficult to provide more useful and desirable ads to users.

[1080] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1081] In this invention, the server includes means for acquiring a user's behavioral history and purchase history, means for analyzing the acquired behavioral history and purchase history using an AI model, means for acquiring and analyzing emotional data, means for generating a coupon advertisement customized for each user based on the analysis results, and means for delivering the generated coupon advertisement to the user terminal and displaying it on the display of the smart device, thereby enabling timely and appropriate advertisement delivery based on the user's emotional state.

[1082] "User behavior history" is a record of actions such as clicks, page views, and time spent on a website or application.

[1083] "Purchase history" is a record of the type of product purchased by the user, the purchase date and time, price, store information, etc.

[1084] An "AI model" is an algorithm or computational model that uses artificial intelligence technology to analyze data and derive specific results.

[1085] "Analysis means" refers to the techniques and methods used to analyze acquired data and convert it into meaningful information.

[1086] "Emotional data" refers to information about a user's emotional state analyzed based on their facial expressions, voice, and other biometric information.

[1087] "Customized coupon ads" are individual coupon ads generated based on each user's behavioral history, purchasing history, and emotional state.

[1088] A "smart device" is a device that has internet connectivity and a user-operable display.

[1089] "Means for displaying on a display" refers to a display function for visually presenting the generated information to the user.

[1090] This invention is a system that acquires a user's behavioral history, purchase history, and emotional data, analyzes them, generates a coupon advertisement customized for each user, and delivers it to the user's terminal. Specific embodiments of the system are described below.

[1091] server:

[1092] 1. The server acquires the user's behavioral history and purchase history and stores it in a database, including the user's clicks, page views, time spent on the website or application, as well as the type of product purchased, purchase date and time, price, store information, etc.

[1093] 2. The server has an emotion engine for acquiring emotion data and analyzes the user's emotional state in real time from their facial expressions and voice. The emotion data generated by the emotion engine is stored in a database along with their behavioral history and purchase history.

[1094] 3. The server inputs the collected data into an AI model to analyze the user's purchasing habits and emotional state. The AI ​​model then uses cluster analysis and recommendation algorithms to select the most suitable coupon for each user.

[1095] 4. Based on the analysis results, the server uses dynamic templates to generate customized coupon ads for each user.

[1096] Device:

[1097] 1. User devices include smart devices such as smartphones, smart glasses, and head-mounted displays. These devices receive coupon advertisements distributed from the server and display them on their displays.

[1098] 2. The device has the ability to collect emotion data in real time when the user uses an application and send it to the server. For example, the device can capture the user's facial expressions using a camera mounted on smart glasses and analyze them with the emotion engine.

[1099] Examples:

[1100] For example, suppose user A is wearing smart glasses. When user A is in a supermarket, the camera in the smart glasses captures user A's facial expression data in real time, which is analyzed by the emotion engine. If the emotion engine detects user A's emotional state as "joy," the server sends this information to the AI ​​model and generates the optimal coupon advertisement for user A. The generated coupon advertisement is displayed on the smart glasses' display.

[1101] Generate AI model prompt:

[1102] "Input the user's facial expression data and purchase history and generate the best ads and coupons. If the user is smiling, select and display positive ads."

[1103] In this way, timely and appropriate advertising can be delivered based on the user's emotional state, and the use of smart devices also allows users to enjoy a more intuitive and personalized advertising experience.

[1104] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1105] Step 1:

[1106] The device acquires the user's behavioral history and purchase history. Specifically, it records operation data (clicks, page views, time spent, purchased items, purchase date and time, etc.) when the user uses a smart device or application, and sends it to a database. The input is the user's operation data, and the output is the behavioral history and purchase history data stored in the server-side database.

[1107] Step 2:

[1108] The device acquires the user's emotional data. The user's facial expressions are captured in real time using smart glasses or a smartphone camera, and analyzed by the emotion engine. The analysis results (emotion data) are sent to the server. The input is the captured facial expression data, and the output is the analyzed emotional data.

[1109] Step 3:

[1110] The server stores the acquired behavioral history, purchase history, and emotion data in a database. Specifically, it performs data cleaning processes, complements and corrects missing and outlier values, and converts and normalizes the data into a format suitable for the AI ​​model and emotion engine. The input is the user's behavioral history, purchase history, and emotion data, and the output is the normalized data stored in the database.

[1111] Step 4:

[1112] The server analyzes user data using an AI model and emotion engine. At regularly scheduled times (for example, the first day of each month), each user's behavioral history, purchase history, and emotional data are input into the AI ​​model and emotion engine. The AI ​​model learns the user's purchasing trends, and the emotion engine analyzes the emotional data. The inputs are normalized behavioral history, purchase history, and emotional data, and the output is the analysis results (selection of the optimal coupon).

[1113] Step 5:

[1114] The server generates customized coupon ads based on the analysis results. Specifically, it uses the analysis results obtained from the AI ​​model and emotion engine to create dynamic templates to generate individual coupon ads for each user. The input is the analysis results, and the output is the customized coupon ads.

[1115] Step 6:

[1116] The server delivers the generated coupon advertisement to the user terminal. The user terminal receives the delivered coupon advertisement and displays it on the display of the smart device. The input is the customized coupon advertisement, and the output is the advertisement displayed on the display of the user terminal.

[1117] Step 7:

[1118] The device monitors whether the user utilizes the generated coupon advertisement and collects new behavioral history, purchase history, and emotional data again. The input is the user's advertisement usage behavior data, and the output is updated behavioral history, purchase history, and emotional data. This makes it possible to generate even more optimized advertisements in the next cycle.

[1119] At each step, the server, terminal, or user plays a key role, and the processes of data collection, analysis, generation, distribution, and reevaluation are carried out smoothly, enabling the provision of optimal coupon advertisements to users.

[1120] 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.

[1121] 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.

[1122] 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.

[1123] [Fourth embodiment]

[1124] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1125] 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.

[1126] 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).

[1127] 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.

[1128] 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.

[1129] 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).

[1130] 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.

[1131] 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.

[1132] 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.

[1133] 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.

[1134] 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.

[1135] 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.

[1136] 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."

[1137] The present invention is a system that acquires and analyzes a user's behavioral history and purchase history to generate and distribute a coupon advertisement customized for each user. This system includes a means for acquiring the user's behavioral history and purchase history, an analysis means using an AI model to analyze the acquired behavioral history and purchase history, a means for generating a coupon advertisement customized for each user based on the analysis results, and a means for distributing the generated coupon advertisement to the user's terminal.

[1138] 1. Collection of user behavioral and purchasing history

[1139] Device: When a user uses the app, operation history and purchase information are recorded. Behavioral history includes the links the user clicked, the product pages viewed, the time spent on the app, and information about campaigns participated in. Purchase history includes the name of the purchased product, the date and time of purchase, the price, and store information.

[1140] Terminal: Sends this data to the server in real time.

[1141] 2. Data storage and preprocessing

[1142] Server: The received behavioral history and purchase history are stored in a database. The stored data is checked for missing values ​​and outliers, and then corrected or supplemented in an appropriate manner.

[1143] Server: Transforms and normalizes the data into a format that can be processed by the AI ​​model.

[1144] 3. Data analysis using AI models

[1145] Server: Inputs each user's behavioral history and purchase history into the AI ​​model to learn the user's purchasing trends.

[1146] Server: Uses cluster analysis and recommendation algorithms to select the best coupon for each user.

[1147] 4. Generate personalized ads

[1148] Server: Generates customized coupon ads for each user based on the results of the AI ​​model analysis. Dynamic templates are used to display specific products based on the user's name and purchasing history.

[1149] Server: Generates advertising images and banners with optimal coupon information embedded and integrates them into the advertising design.

[1150] 5. Delivery of advertisements

[1151] Server: The generated customized advertisement is delivered to the user's device. It is set to be displayed on the user's app homepage at the scheduled time on the first day of each month.

[1152] On your device: When you open the app, a customized ad will appear on the home screen.

[1153] Specific examples

[1154] Example 1: User A who frequently purchases daily ingredients

[1155] Device: User A regularly purchases ingredients. He searches for and purchases vegetables, meats, and seasonings using the app.

[1156] Server: Based on User A's purchase history and behavioral history, the AI ​​model determines that coupons for "vegetables" and "meat" are valid.

[1157] Server: Generates a "vegetable discount coupon ad for user A."

[1158] Device: On the first day of each month, coupon advertisements such as "10% off vegetables" will be displayed on User A's app homepage.

[1159] Example 2: User B prefers a specific brand of product

[1160] Device: User B frequently purchases a particular brand of cosmetics.

[1161] Server: Analyzes User B's purchasing history and determines that a product coupon for a specific brand is valid.

[1162] Server: Generates a "brand product discount coupon ad exclusively for User B."

[1163] Device: On the first day of each month, coupon advertisements such as "20% off brand cosmetics" will be displayed on User B's app homepage.

[1164] summary

[1165] This system allows users to receive personalized coupon ads based on their purchasing behavior, while also helping businesses reduce advertising production and placement costs while increasing user engagement and usage rates.

[1166] The processing flow will be explained below.

[1167] Step 1:

[1168] Users: Use the app to search for and purchase products, and view promotions and special offers within the app.

[1169] Device: Records user actions in real time and collects behavioral history (clicks, page views, time spent, etc.) as well as purchase history (purchased products, purchase date and time, purchase price, purchase store, etc.).

[1170] Terminal: Sends collected behavioral and purchase history to the server in real time.

[1171] Step 2:

[1172] Server: Stores the received behavioral history and purchase history in a database.

[1173] Server: Performs data cleaning operations, imputing missing values, correcting outliers, and, if necessary, converting and normalizing the data to a format that is easier for the AI ​​model to process.

[1174] Step 3:

[1175] Server: On the scheduled first day of each month, each user's behavioral and purchasing history is input into the AI ​​model.

[1176] Server: The AI ​​model analyzes the input data and learns the purchasing habits of each user. Specifically, it uses cluster analysis and recommendation algorithms to select the most suitable coupon for each user.

[1177] Step 4:

[1178] Server: Select a custom template based on the coupon information selected for each user.

[1179] Server: Generate personalized coupon ads by embedding coupon information for each user in custom templates. Specifically, we use dynamic templates to display specific products based on the user's name and past purchase history.

[1180] Step 5:

[1181] Server: Delivers the generated customized advertisements to the user's device.

[1182] Device: When you open the app on the 1st of each month, a customized ad will be displayed on the home screen.

[1183] Step 6:

[1184] Device: Records information when a user clicks on a coupon ad or actually uses a coupon.

[1185] Terminal: Sends feedback data (such as ad click rates and coupon redemption rates) to the server in real time.

[1186] Server: Based on the received feedback data, the AI ​​model algorithm and coupon selection logic are tuned and reflected in the next analysis.

[1187] Specific examples

[1188] Example 1: User A who frequently purchases daily ingredients

[1189] Device: User A frequently purchases vegetables, meat, and seasonings through the app. Their behavioral and purchase history is collected and sent to the server.

[1190] Server: The AI ​​model analyzes User A's data and determines that coupons for "vegetables" and "meat" are valid.

[1191] Server: Generates customized ads including coupons for "10% off vegetables" and "20% off meat" and delivers them to User A's device.

[1192] Device: The coupon advertisement will be displayed on User A's app homepage on the 1st of each month.

[1193] Example 2: User B prefers a specific brand of product

[1194] Device: User B frequently purchases a particular brand of cosmetics. Their purchase history and behavioral history are collected and sent to the server.

[1195] Server: The AI ​​model analyzes User B's data and determines that a product coupon for a specific brand is valid.

[1196] Server: Generate a customized ad containing a coupon for "20% off a specific brand of cosmetics" and deliver it to User B's device.

[1197] Device: The coupon advertisement will be displayed on User B's app homepage on the 1st of each month.

[1198] Example 1

[1199] 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."

[1200] Conventional ad distribution systems deliver generic coupon ads, making it impossible to provide personalized ads based on each user's purchasing trends and behavioral history. This makes it difficult to effectively deliver coupon ads that match the user's interests and needs, resulting in problems such as the inability to expect improvements in ad click rates and purchasing intent.

[1201] 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.

[1202] In this invention, the server includes means for acquiring user behavioral history and purchase history, means for transmitting the acquired behavioral history and purchase history to the server in real time, means for saving the received behavioral history and purchase history to a database, means for checking the saved data for missing values ​​and outliers and appropriately correcting or completing them, means for converting and normalizing the data into a format that can be processed by an AI model, means for inputting each user's behavioral history and purchase history into an AI model and having it learn the user's purchasing tendencies, means for selecting the most suitable coupon for each user using cluster analysis and a recommendation algorithm, means for generating a coupon advertisement customized for each user based on the analysis results of the AI ​​model, means for delivering the generated coupon advertisement to the user's device, and means for displaying the customized advertisement on the top screen when the user opens the app on the user's device. This enables effective delivery of personalized coupon advertisements based on each user's purchasing tendencies and behavioral history.

[1203] "User behavior history" refers to information related to operations, such as links clicked, product pages viewed, time spent on the app, and information about campaigns participated in, that is recorded when the user operates the app.

[1204] "Purchase history" refers to detailed information about specific purchases, such as the name of the product purchased by the user, the date and time of purchase, the price, and store information.

[1205] A "server" is a device or system for receiving, storing, and analyzing behavioral history and purchase history sent by a user.

[1206] "Database" means a structured data storage system for efficiently storing and managing received behavioral and purchasing histories.

[1207] An "AI model" is an artificial intelligence algorithm and computational model used to analyze a user's behavioral history and purchase history and learn about the user's purchasing trends.

[1208] "Normalization" is the process of converting data into a format that can be processed by an AI model and standardizing the scale and format of the data.

[1209] "Cluster analysis" is an analytical technique for grouping data from multiple users and identifying user groups with similar patterns and trends.

[1210] A "recommendation algorithm" is a method for recommending the most suitable products and coupons to each user based on the user's purchasing history and behavioral history.

[1211] "Customized coupon ads" are ads that include coupons that are customized to meet the interests and needs of a specific user based on the user's individual behavioral history and purchasing history.

[1212] The "top screen" is the main screen that appears first on a user's device when they open the app.

[1213] MODE FOR CARRYING OUT THE INVENTION

[1214] The present invention is a system that acquires and analyzes a user's behavioral history and purchase history to generate and distribute coupon advertisements customized for each user. This system includes the following main means.

[1215] Collection of user behavior and purchase history

[1216] Device: When a user operates the app, their behavioral history, such as the links they clicked, the product pages they viewed, the time they spent there, and the campaign information they participated in, is recorded. Purchase history, such as the name of the product purchased, the date and time of purchase, the price, and store information, is also recorded. This data is sent to the server in real time.

[1217] Data storage and preprocessing

[1218] Server: The received behavioral and purchase history is stored in a database. The stored data is checked for missing values ​​and outliers, and corrected or supplemented in an appropriate manner. The data is then converted into a format that can be processed by the AI ​​model and normalized.

[1219] Data analysis using AI models

[1220] Server: Inputs each user's behavioral and purchase history into the AI ​​model to learn their purchasing trends. Using cluster analysis and recommendation algorithms, the server selects the most suitable coupon for each user.

[1221] Generate personalized ads

[1222] Server: Generates customized coupon ads for each user based on the analysis results of the AI ​​model. Dynamic templates are used to display specific products based on the user's name and purchasing history. Generates ad images and banners with the optimal coupon information embedded and integrated into the ad design.

[1223] Ad serving

[1224] Server: The server delivers the generated customized ads to the user's device. These ads are set to be displayed on the user's app homepage at a pre-scheduled time, for example, on the first day of each month.

[1225] On your device: When you open the app, a customized ad will appear on the home screen.

[1226] Specific examples

[1227] Example 1: User A who frequently purchases daily ingredients

[1228] Device: User A searches for and purchases daily ingredients. For example, they search for "cabbage" or "chicken" in the app and complete the purchase process.

[1229] Server: User A's purchase history and behavioral history are input into the AI ​​model, and it is determined that the coupons for "cabbage" and "chicken" are valid.

[1230] Server: Generate a "vegetable discount coupon ad for user A." For example, create a coupon ad for "10% off cabbage."

[1231] Device: On the first day of each month, a coupon ad for "10% off cabbage" will be displayed on User A's app homepage.

[1232] Example 2: User B prefers a specific brand of product

[1233] Device: User B frequently purchases cosmetics from a specific brand, for example, "Brand X lipstick."

[1234] Server: Analyzes User B's purchase history and determines that "Brand X's cosmetics coupon is valid."

[1235] Server: Generate a "brand product discount coupon ad exclusively for User B." For example, create a coupon ad for "20% off brand X lipstick."

[1236] Device: On the first day of each month, a coupon ad for "20% off Brand X lipstick" will be displayed on User B's app homepage.

[1237] Prompt Sentence Examples

[1238] "Design a system that collects user behavioral and purchasing histories and analyzes them using an AI model."

[1239] "Describe the algorithm that generates customized coupon ads for each user."

[1240] "Please explain the process of collecting data in real time and delivering advertisements based on the analysis results."

[1241] The system of the present invention implemented in this way allows users to receive personalized coupon advertisements based on their purchasing behavior, enabling businesses to reduce advertising production and placement costs while improving user engagement and usage rates.

[1242] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1243] Step 1:

[1244] The device records the user's behavioral history and purchase history when the user operates the app. Specifically, it collects information in real time, such as the links the user clicked, the product pages they viewed, the length of time they stayed, and information about campaigns they participated in. It also records the purchase history, such as the name of the product purchased, the date and time of purchase, the price, and store information. The input data is the user's operations and purchase information, and the output is data sent to the server in real time.

[1245] Step 2:

[1246] The server receives the behavioral history and purchase history sent from the device and stores it in a database. When saving, the data is checked for missing or abnormal values ​​and corrected or supplemented in an appropriate manner. For example, data with missing purchase dates and times is supplemented with estimated dates and times. The input data is the sent behavioral history and purchase history, and the output is the corrected and supplemented saved data.

[1247] Step 3:

[1248] The server converts and normalizes the stored data into a format that the AI ​​model can process. For example, it converts purchase dates and times into a unified year / month / day format and normalizes price data to a certain scale. The input data is the corrected and supplemented stored data, and the output is the normalized data.

[1249] Step 4:

[1250] The server inputs each user's behavioral history and purchase history into the AI ​​model to learn the user's purchasing trends. For example, it learns what other products a user who purchased a "Festival Yukata Set" is interested in. The input data is normalized behavioral history and purchase history, and the output is a learned purchasing trend model.

[1251] Step 5:

[1252] The server uses cluster analysis and recommendation algorithms to select the most suitable coupon for each user. For example, it proposes summer festival-related coupons to a group of users who like similar products. The input data is the trained purchasing tendency model, and the output is the selected optimal coupon information.

[1253] Step 6:

[1254] The server generates a coupon ad customized for each user based on the analysis results of the AI ​​model. For example, for a user who purchases a "Festival Yukata Set," it generates a coupon ad offering 10% off summer festival-related products. The input data is the selected optimal coupon information, and the output is a customized coupon ad.

[1255] Step 7:

[1256] The server delivers the generated customized advertisement to the user's device. For example, a "10% off summer festival related products" coupon is delivered on the first day of every month. The input data is the customized coupon advertisement, and the output is the delivery data to the user's device.

[1257] Step 8:

[1258] When a user opens an app, the device displays a customized advertisement on the home screen. For example, when a user opens an app, a coupon advertisement for "10% off summer festival-related products" is displayed on the home screen. The input data is the delivered customized advertisement, and the output is the displayed advertisement.

[1259] (Application example 1)

[1260] 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."

[1261] In today's information society, providing users with appropriate advertisements and coupons is an important part of a marketing strategy. However, current coupon distribution systems do not fully utilize users' purchasing trends and behavioral history, resulting in a lot of wasteful advertisement distribution and often failing to increase user engagement. Furthermore, there is a lack of technology to personalize coupons based on individual purchasing trends, making efficient advertisement distribution difficult. The present invention aims to solve these problems by providing a system that generates and distributes highly accurate coupon advertisements based on individual users' purchasing trends.

[1262] 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.

[1263] In this invention, the server includes means for acquiring user behavioral history and purchase history, means for processing the acquired behavioral history and purchase history, means for an AI model to analyze the purchasing trends of each user using the processed data, means for generating a coupon advertisement customized for each user based on the analysis results, and means for delivering the generated coupon advertisement to the user terminal. This enables the generation of personalized coupon advertisements based on the user's purchasing trends and efficient advertisement delivery.

[1264] "User behavior history" refers to a record of the actions, clicks, browsing time, search queries, etc. that a user takes on an application or website.

[1265] "Purchase history" refers to a record of information about products a user has purchased in the past, including the date and time of purchase, price, and place of purchase.

[1266] "Means" refers to a specific method or component such as a method, device, or system for achieving a specific purpose.

[1267] An "AI model" is an algorithm or model that uses artificial intelligence techniques to analyze data and generate specific results or predictions.

[1268] "Data processing" refers to the process of converting raw data into a format that can be processed by an AI model, including normalizing the data and filling in missing values.

[1269] "Purchasing trends" are the results of an analysis of what products users prefer to purchase, how often they do so, and when.

[1270] A "coupon ad" is an ad that offers users a discount on a particular product or service, and includes a coupon code or discount information.

[1271] "Generating" is the process of creating new data or content based on the analysis results.

[1272] A "user device" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[1273] A "push notification" is a real-time notification message sent by an application to a user device.

[1274] This invention is a system that acquires and analyzes a user's behavioral history and purchase history to generate a coupon advertisement customized for each user and distributes it to the user's terminal. This system is implemented as follows.

[1275] First, the user's device records the user's behavioral history, such as the operation history, clicks, browsing time, and search queries performed when using the application, as well as the purchase history, such as information on previously purchased products, purchase date and time, price, and purchase location. This data is sent to the server in real time.

[1276] The server then stores the received behavioral and purchase history in a database. This stored data is checked for missing values ​​and outliers, and then corrected and supplemented in an appropriate manner. The data is then converted and normalized into a format that can be processed by the AI ​​model. Libraries such as StandardScaler are used for data preprocessing.

[1277] The normalized data is input into an AI model to analyze each user's purchasing habits. Principal component analysis (PCA) and clustering algorithms (e.g., KMeans) are used for the analysis. This allows users to be appropriately classified into clusters based on their purchasing habits, and the most appropriate coupons are selected for each cluster.

[1278] The AI ​​model then uses the results of its analysis to generate a personalized coupon ad for each user. The ad is generated using dynamic templates to display specific products based on the user's name and purchasing history. The ad image and banner are then generated and integrated with the ad design, incorporating the optimal coupon information.

[1279] Finally, the generated customized advertisement is delivered to the user's device, for example, via push notification. Push notifications allow users to receive interesting advertisements in real time, increasing their motivation to make a purchase.

[1280] For example, if a user tends to purchase many e-books, the system analyzes their purchase history and generates e-book coupon ads. On the first day of each month, the system delivers personalized ads to the user's smartphone, such as "20% off new e-books!"

[1281] As described above, the present invention provides a system that generates personalized advertisements based on a user's behavioral history and purchase history, and realizes efficient advertisement distribution.

[1282] An example of a prompt is as follows:

[1283] Design an AI system that generates personalized ads based on users' behavioral and purchasing history. This system involves the following steps:

[1284] 1. Collection of user behavioral and purchasing history

[1285] 2. Preprocessing of these data (dealing with missing values, outliers, and data normalization)

[1286] 3. Data analysis using cluster analysis and recommendation algorithms

[1287] 4. Generate coupon ads customized for each user

[1288] 5. Delivery of these advertisements to user devices

[1289] Please generate specific program code based on this prompt.

[1290] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1291] Step 1:

[1292] The user's device acquires the user's behavioral history and purchase history. Specifically, it records in real time the operations performed when the user uses the application (clicks, searches, browsing time, etc.) and information about purchased products (product name, purchase date and time, price, etc.). This data is sent to the server. The input data is the user's operations and purchase information, and the output data is the raw behavioral history and purchase history sent to the server.

[1293] Step 2:

[1294] The server stores the received behavioral history and purchase history in a database. The stored data is checked for missing values ​​and outliers, and corrected or supplemented as necessary. Specifically, the database system is used to manage multiple data entries and ensure data consistency. The input data is the received behavioral history and purchase history. The output data is the formatted behavioral history and purchase history data.

[1295] Step 3:

[1296] The server converts the formatted behavioral history and purchase history data into a format that can be processed by the AI ​​model and normalizes the data. Specifically, it scales the data using a tool such as StandardScaler. The input data is the formatted behavioral history and purchase history data, and the output data is the normalized data.

[1297] Step 4:

[1298] The server inputs the normalized data into an AI model to analyze each user's purchasing trends. Principal component analysis (PCA) and clustering algorithms (such as KMeans) are used to classify the data into clusters. The input data is normalized data, and the output data is the clustering results. Specifically, the feature values ​​of each cluster are analyzed to clarify the user's purchasing trends.

[1299] Step 5:

[1300] The server generates coupon ads customized for each user based on the analysis results of the AI ​​model. Coupon information is embedded using dynamic templates to design ads suited to each user. The input data is the clustering results, and the output data is the customized coupon ads. Specifically, the ads are dynamically generated using a template engine.

[1301] Step 6:

[1302] The server delivers the generated customized advertisement to the user's device. Specifically, the advertisement is sent to the user in real time using a method such as push notification. The input data is the customized coupon advertisement, and the output data is the advertisement displayed on the user's device. Specifically, the advertisement data is sent to the user's device using a communication protocol.

[1303] Through the above steps, the present invention provides a system that generates personalized advertisements based on a user's behavioral history and purchase history, and realizes efficient advertisement distribution.

[1304] 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.

[1305] The present invention is a system that generates and distributes coupon advertisements customized for each user by acquiring and analyzing the user's behavioral history, purchase history, and emotional data. This system includes a means for acquiring the user's behavioral history and purchase history, an emotion engine for acquiring and analyzing the emotional data, an analysis means using an AI model for analyzing the acquired behavioral history and purchase history, a means for generating coupon advertisements customized for each user based on the analysis results, and a means for distributing the generated coupon advertisements to the user terminal.

[1306] 1. Collection of user behavioral history, purchase history, and emotional data

[1307] Device: Performs operations when the user uses the app. Collects behavioral history (clicks, page views, time spent) and purchase history (purchased products, purchase date and time, price, store information).

[1308] On the device: Using facial recognition and voice analysis technology to collect emotional data from the user's facial expressions and voice.

[1309] Terminal: Collected behavioral history, purchase history, and emotional data is sent to the server in real time.

[1310] 2. Data storage and preprocessing

[1311] Server: Stores the received behavioral history, purchase history, and emotion data in a database.

[1312] Server: Performs data cleaning processes, imputes and corrects missing values ​​and outliers, and normalizes and converts the data into a format that can be processed by the AI ​​model and emotion engine.

[1313] 3. Data analysis using AI models and emotion engines

[1314] Server: On the first day of each month, each user's behavioral history, purchase history, and emotional data are input into the AI ​​model and emotion engine.

[1315] Server: The AI ​​model learns users' purchasing habits and uses cluster analysis and recommendation algorithms to select the most suitable coupons for each user.

[1316] Server: The emotion engine analyzes the input emotion data and further optimizes coupon selection based on the user's current emotional state.

[1317] 4. Generate personalized ads

[1318] Server: Generates customized coupon ads for each user based on the analysis results of the AI ​​model and emotion engine, using dynamic templates to display specific products based on the user's name, past purchase history, and emotional state.

[1319] Server: Generates advertising images and banners with optimal coupon information embedded and integrates them into the advertising design.

[1320] 5. Delivery of advertisements

[1321] Server: Delivers the generated customized advertisements to the user's device.

[1322] Device: When you open the app on the 1st of each month, a customized ad will be displayed on the home screen.

[1323] Specific examples

[1324] Example 1: User A who frequently purchases daily ingredients

[1325] Device: User A regularly buys ingredients. He searches for and purchases vegetables, meats, and seasonings using the app. The emotion engine detects from User A's facial expressions that shopping is a low-stress activity.

[1326] Server: The AI ​​model and emotion engine analyze User A's data and determine that coupons for "vegetables" and "meat" are valid.

[1327] Server: Generates a "vegetable discount coupon ad for user A."

[1328] Device: On the first day of each month, coupon advertisements such as "10% off vegetables" will be displayed on User A's app homepage.

[1329] Example 2: User B prefers a specific brand of product

[1330] Device: User B frequently purchases a specific brand of cosmetics. Their purchase history and behavioral history are collected and sent to the server. The emotion engine detects a high level of excitement in User B's voice.

[1331] Server: The AI ​​model and emotion engine analyze User B's data and determine that a product coupon for a specific brand is valid.

[1332] Server: Generates a "brand product discount coupon ad exclusively for User B."

[1333] Device: On the first day of each month, coupon advertisements such as "20% off brand cosmetics" will be displayed on User B's app homepage.

[1334] summary

[1335] This system allows users to receive personalized coupon ads based on their purchasing behavior and emotional state, while also helping businesses reduce advertising production and placement costs while increasing user engagement and usage rates.

[1336] The processing flow will be explained below.

[1337] Step 1:

[1338] Users: Use the app to search for and purchase products, and view promotions and special offers within the app.

[1339] Device: Records user actions in real time and collects behavioral history (clicks, page views, time spent). It also records purchase history (items purchased, purchase date and time, purchase price, purchase store, etc.). At the same time, it uses facial recognition and voice analysis technology to collect emotional data from the user's facial expressions and voice.

[1340] Terminal: Collected behavioral history, purchase history, and emotional data is sent to the server in real time.

[1341] Step 2:

[1342] Server: The received behavioral history, purchase history, and emotion data is stored in a database. The stored data is checked for missing values ​​and outliers, and then appropriately supplemented and corrected. The data is converted and normalized into a format that is easy for the AI ​​model and emotion engine to process.

[1343] Step 3:

[1344] Server: On the first day of each month, each user's behavioral history, purchase history, and emotional data are input into the AI ​​model and emotion engine. The AI ​​model learns each user's purchasing habits and selects the most appropriate coupon using cluster analysis and recommendation algorithms. The emotion engine also analyzes the emotional data and further optimizes coupon selection based on the user's current emotional state.

[1345] Step 4:

[1346] Server: Select a custom template based on the coupon information selected for each user. Embed coupon information for each user in the custom template to generate individually tailored coupon ads. Use dynamic templates to display specific products based on the user's name, past purchase history, or emotional state.

[1347] Step 5:

[1348] Server: Delivers the generated customized advertisements to the user's device.

[1349] Device: When the app is opened on the 1st of each month, a customized ad is displayed on the home screen. The fact that the ad was displayed is sent as feedback to the server.

[1350] Step 6:

[1351] Device: When a user clicks on a coupon ad or actually uses a coupon, that information is recorded and feedback data (such as ad click rates and coupon redemption rates) is sent to the server in real time.

[1352] Server: Based on the received feedback data, the AI ​​model, emotion engine algorithms, and coupon selection logic are tuned and reflected in the next analysis.

[1353] Specific examples

[1354] Example 1: User A who frequently purchases daily ingredients

[1355] Device: User A frequently purchases vegetables, meat, and seasonings through the app. Their behavioral and purchasing history is collected and sent to the server. The emotion engine detects from User A's facial expressions that shopping is a low-stress activity.

[1356] Server: The AI ​​model and emotion engine analyze User A's data and determine that coupons for "vegetables" and "meat" are valid.

[1357] Server: Generates a "vegetable discount coupon ad for user A."

[1358] Device: On the first day of each month, coupon advertisements such as "10% off vegetables" will be displayed on User A's app homepage.

[1359] Example 2: User B prefers a specific brand of product

[1360] Device: User B frequently purchases a particular brand of cosmetics. Their purchase history and behavioral history are collected and sent to the server. The emotion engine detects a high level of excitement in User B's voice.

[1361] Server: The AI ​​model and emotion engine analyze User B's data and determine that a product coupon for a specific brand is valid.

[1362] Server: Generates a "brand product discount coupon ad exclusively for User B."

[1363] Device: The coupon advertisement will be displayed on User B's app homepage on the 1st of each month.

[1364] Example 2

[1365] 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."

[1366] Conventional coupon advertising systems generate coupons based solely on a user's behavioral and purchasing history, resulting in insufficient personalization that takes into account the user's current emotional state. This results in insufficient appeal to users' interests and limits the improvement of coupon usage rates and advertising effectiveness. Furthermore, the accuracy of selecting appropriate coupons for each user is low, resulting in a lot of wasted advertising. There was a need to solve these problems and achieve more effective coupon distribution.

[1367] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1368] In this invention, the server includes means for acquiring a user's behavioral history and purchase history, means for acquiring user emotional data using facial recognition and voice analysis technology, and analysis means using an AI model and emotion engine for analyzing the acquired behavioral history, purchase history, and emotional data. This makes it possible to comprehensively analyze a user's purchasing tendencies and emotional state, and generate and distribute coupon advertisements optimized for each user.

[1369] "User behavior history" refers to a record of actions such as clicks, page views, and time spent on an application when a user uses it.

[1370] "User purchase history" refers to a record of the products a user has purchased in the past, the purchase date and time, price, store information, etc.

[1371] "Facial recognition" is a technology that captures a user's facial features and identifies their expressions and emotions.

[1372] "Voice analysis" is a technology that analyzes a user's voice and identifies its tone and emotion.

[1373] "Emotional data" is data that indicates a user's emotional state obtained through facial recognition and voice analysis technology.

[1374] An "AI model" is an artificial intelligence algorithm that learns a user's behavioral and purchasing history and predicts purchasing trends.

[1375] The "emotion engine" is a program that analyzes the acquired emotion data and determines the user's current emotional state.

[1376] "Analysis means" refers to a means for analyzing acquired behavioral history, purchase history, and emotional data using an AI model and an emotion engine.

[1377] A "customized coupon ad" is an individually optimized coupon ad that is generated based on each user's behavioral history, purchase history, and emotional state.

[1378] "User terminal" refers to a device used by a user, such as a smartphone, tablet, or PC.

[1379] This invention is a system that generates individually customized coupon advertisements and delivers them to user devices by acquiring and analyzing user behavioral history, purchase history, and emotion data. This system is implemented using user devices, a server, an AI model, and an emotion engine.

[1380] 1. Collection of user behavioral history, purchase history, and emotional data

[1381] Users operate the application to search for and purchase products.

[1382] The device automatically records the user's behavioral history (clicks, page views, time spent) and purchase history (purchased products, purchase date and time, price, store information). For example, if a user views a product page for 30 seconds, that information will be recorded by the device.

[1383] The device uses facial recognition and voice analysis technologies to collect emotional data from the user's facial expressions and voice. For example, the camera detects when the user is smiling and records the intensity of that smile as a numerical value.

[1384] The device transmits the collected data in real time to a server using an internet connection.

[1385] 2. Data storage and preprocessing

[1386] The server stores the received behavioral history, purchase history, and emotion data in a database using an RDBMS such as MySQL or PostgreSQL.

[1387] The server cleans the data and fills in and corrects missing or outlier values. For example, if there is data that is missing a purchase date and time, it fills in the appropriate value.

[1388] The server converts and normalizes the data into a format that can be processed by the AI ​​model and emotion engine, for example, converting text data into numeric vectors.

[1389] 3. Data analysis using AI models and emotion engines

[1390] On the first day of each month, the server inputs each user's behavioral history, purchase history, and emotional data into the AI ​​model and emotion engine.

[1391] The server uses an AI model to learn users' purchasing habits and then uses cluster analysis and recommendation algorithms to select the most suitable coupons for each user. For example, if a user has purchased a lot of vegetables in the past, vegetable-related coupons will be selected for that user.

[1392] The server uses an emotion engine to analyze the emotion data and further optimize the coupons based on the user's emotional state, for example, if the user is expressing joy, it selects coupons with positive messages.

[1393] 4. Generate personalized ads

[1394] The server then uses the analysis results to generate customized coupon ads for each user, using dynamic templates to display specific products based on the user's name, past purchase history, and emotional state.

[1395] The server generates advertising images and banners with optimal coupon information embedded and integrates them with the advertising design. For example, it generates a banner image that reads, "User A, please use this coupon for 10% off vegetables."

[1396] 5. Delivery of advertisements

[1397] The server then delivers the generated customized advertisements to the user's device in real time.

[1398] The device will display a customized advertisement on the home screen when the app is opened on the first day of each month. For example, when user A starts the app, a coupon advertisement for "10% off vegetables" will be displayed on the home screen.

[1399] Specific examples

[1400] Example 1: User A who frequently purchases daily ingredients

[1401] User A buys groceries on a daily basis.

[1402] The device records user A's actions when searching for and purchasing vegetables, meat, and seasonings using the app.

[1403] The emotion engine detects from User A's facial expression that shopping is a low-stress activity.

[1404] The server uses an AI model and emotion engine to analyze User A's data and determines that coupons for "vegetables" and "meat" are valid.

[1405] The server generates a "vegetable discount coupon advertisement exclusive to User A" and delivers it to User A's app.

[1406] On the first day of each month, the device will display a coupon advertisement for "10% off vegetables" on the top screen of User A's app.

[1407] Example 2: User B prefers a specific brand of product

[1408] User B frequently purchases a particular brand of cosmetics.

[1409] The terminal collects purchase history and behavior history and transmits them to the server.

[1410] The emotion engine detects a high level of excitement in User B's voice.

[1411] The server uses an AI model and emotion engine to analyze User B's data and determine that a product coupon for a specific brand is valid.

[1412] The server generates a "brand product discount coupon advertisement exclusive to User B" and delivers it to User B's app.

[1413] On the first day of each month, the device will display a coupon advertisement for "20% off brand cosmetics" on the top screen of User B's app.

[1414] This allows users to receive optimal coupon advertisements based on their purchasing behavior and emotional state, and businesses to maximize the effectiveness of their advertisements.

[1415] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1416] Step 1: Collect user behavioral, purchasing, and sentiment data

[1417] Users operate the app to search for and purchase products, launch the app, browse pages, and purchase products.

[1418] The device records user behavior (clicks, page views, and time spent on the site). For example, if a user views a product page for 30 seconds, that information is recorded.

[1419] The device also records the user's purchase history (purchased items, purchase date and time, price, store information). For example, if a user purchases a 1,000 yen item on March 1st, the details will be recorded.

[1420] The device uses facial recognition and voice analysis technology to collect emotional data from the user's facial expressions and voice. For example, the camera detects when the user is smiling and records the intensity of that smile.

[1421] The terminal transmits the collected behavioral history, purchase history, and emotional data to the server in real time.

[1422] Input: User operation data, facial expression data, voice data

[1423] Output: Recorded behavioral history, purchase history, emotional data

[1424] Step 2: Storing and Preprocessing Data

[1425] The server stores the received behavioral history, purchase history, and emotion data in a database, using an RDBMS such as MySQL or PostgreSQL.

[1426] The server cleans the stored data and fills in and corrects missing or outlier values. For example, if there is data that is missing a purchase date and time, it fills in the appropriate value.

[1427] The server converts and normalizes the data into a format that can be processed by the AI ​​model and emotion engine, for example, converting text data into numeric vectors.

[1428] Input: Collected behavioral history, purchase history, and raw emotional data

[1429] Output: Cleaned and normalized data

[1430] Step 3: Data analysis with AI models and emotion engines

[1431] On the first day of each month, the server inputs each user's behavioral history, purchase history, and emotional data into the AI ​​model and emotion engine.

[1432] The server uses an AI model to learn users' purchasing habits, and then uses cluster analysis and recommendation algorithms to select the most suitable coupons for each user. For example, if a user has purchased a lot of vegetables in the past, vegetable-related coupons will be selected for that user.

[1433] The server analyzes the emotion data using an emotion engine to further optimize coupon selection based on the user's emotional state, for example, selecting coupons with positive messages when the user is expressing joy.

[1434] Input: Cleaned and normalized behavioral history, purchase history, and sentiment data

[1435] Output: Coupon information optimized for each user

[1436] Step 4: Generate a personalized ad

[1437] The server then uses the results of the AI ​​model and emotion engine to generate customized coupon ads for each user, using dynamic templates to display specific products based on the user's name, past purchase history, and emotional state.

[1438] The server generates advertising images and banners with optimal coupon information embedded and integrates them with the advertising design. For example, it generates a banner image that reads, "User A, please use this coupon for 10% off vegetables."

[1439] Input: Coupon information optimized for each user

[1440] Output: Generated customized coupon ad

[1441] Step 5: Serving Ads

[1442] The server then delivers the generated customized advertisements to the user's device in real time.

[1443] When the app is opened on the first day of each month, the device displays a customized advertisement on the home screen. For example, when user A starts the app, a coupon advertisement for "10% off vegetables" appears on the home screen.

[1444] Input: Generated customized coupon ad

[1445] Output: Coupon ad displayed on user's device

[1446] (Application example 2)

[1447] 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."

[1448] Conventional coupon advertising systems rely solely on users' behavioral and purchasing histories for personalization, making it difficult to deliver appropriate ads that reflect the user's momentary emotional state. Furthermore, the timing and method of ad delivery are limited, making it difficult to provide more useful and desirable ads to users.

[1449] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1450] In this invention, the server includes means for acquiring a user's behavioral history and purchase history, means for analyzing the acquired behavioral history and purchase history using an AI model, means for acquiring and analyzing emotional data, means for generating a coupon advertisement customized for each user based on the analysis results, and means for delivering the generated coupon advertisement to the user terminal and displaying it on the display of the smart device, thereby enabling timely and appropriate advertisement delivery based on the user's emotional state.

[1451] "User behavior history" is a record of actions such as clicks, page views, and time spent on a website or application.

[1452] "Purchase history" is a record of the type of product purchased by the user, the purchase date and time, price, store information, etc.

[1453] An "AI model" is an algorithm or computational model that uses artificial intelligence technology to analyze data and derive specific results.

[1454] "Analysis means" refers to the techniques and methods used to analyze acquired data and convert it into meaningful information.

[1455] "Emotional data" refers to information about a user's emotional state analyzed based on their facial expressions, voice, and other biometric information.

[1456] "Customized coupon ads" are individual coupon ads generated based on each user's behavioral history, purchasing history, and emotional state.

[1457] A "smart device" is a device that has internet connectivity and a user-operable display.

[1458] "Means for displaying on a display" refers to a display function for visually presenting the generated information to the user.

[1459] This invention is a system that acquires a user's behavioral history, purchase history, and emotional data, analyzes them, generates a coupon advertisement customized for each user, and delivers it to the user's terminal. Specific embodiments of the system are described below.

[1460] server:

[1461] 1. The server acquires the user's behavioral history and purchase history and stores it in a database, including the user's clicks, page views, time spent on the website or application, as well as the type of product purchased, purchase date and time, price, store information, etc.

[1462] 2. The server has an emotion engine for acquiring emotion data and analyzes the user's emotional state in real time from their facial expressions and voice. The emotion data generated by the emotion engine is stored in a database along with their behavioral history and purchase history.

[1463] 3. The server inputs the collected data into an AI model to analyze the user's purchasing habits and emotional state. The AI ​​model then uses cluster analysis and recommendation algorithms to select the most suitable coupon for each user.

[1464] 4. Based on the analysis results, the server uses dynamic templates to generate customized coupon ads for each user.

[1465] Device:

[1466] 1. User devices include smart devices such as smartphones, smart glasses, and head-mounted displays. These devices receive coupon advertisements distributed from the server and display them on their displays.

[1467] 2. The device has the ability to collect emotion data in real time when the user uses an application and send it to the server. For example, the device can capture the user's facial expressions using a camera mounted on smart glasses and analyze them with the emotion engine.

[1468] Examples:

[1469] For example, suppose user A is wearing smart glasses. When user A is in a supermarket, the camera in the smart glasses captures user A's facial expression data in real time, which is analyzed by the emotion engine. If the emotion engine detects user A's emotional state as "joy," the server sends this information to the AI ​​model and generates the optimal coupon advertisement for user A. The generated coupon advertisement is displayed on the smart glasses' display.

[1470] Generate AI model prompt:

[1471] "Input the user's facial expression data and purchase history and generate the best ads and coupons. If the user is smiling, select and display positive ads."

[1472] In this way, timely and appropriate advertising can be delivered based on the user's emotional state, and the use of smart devices also allows users to enjoy a more intuitive and personalized advertising experience.

[1473] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1474] Step 1:

[1475] The device acquires the user's behavioral history and purchase history. Specifically, it records operation data (clicks, page views, time spent, purchased items, purchase date and time, etc.) when the user uses a smart device or application, and sends it to a database. The input is the user's operation data, and the output is the behavioral history and purchase history data stored in the server-side database.

[1476] Step 2:

[1477] The device acquires the user's emotional data. The user's facial expressions are captured in real time using smart glasses or a smartphone camera, and analyzed by the emotion engine. The analysis results (emotion data) are sent to the server. The input is the captured facial expression data, and the output is the analyzed emotional data.

[1478] Step 3:

[1479] The server stores the acquired behavioral history, purchase history, and emotion data in a database. Specifically, it performs data cleaning processes, complements and corrects missing and outlier values, and converts and normalizes the data into a format suitable for the AI ​​model and emotion engine. The input is the user's behavioral history, purchase history, and emotion data, and the output is the normalized data stored in the database.

[1480] Step 4:

[1481] The server analyzes user data using an AI model and emotion engine. At regularly scheduled times (for example, the first day of each month), each user's behavioral history, purchase history, and emotional data are input into the AI ​​model and emotion engine. The AI ​​model learns the user's purchasing trends, and the emotion engine analyzes the emotional data. The inputs are normalized behavioral history, purchase history, and emotional data, and the output is the analysis results (selection of the optimal coupon).

[1482] Step 5:

[1483] The server generates customized coupon ads based on the analysis results. Specifically, it uses the analysis results obtained from the AI ​​model and emotion engine to create dynamic templates to generate individual coupon ads for each user. The input is the analysis results, and the output is the customized coupon ads.

[1484] Step 6:

[1485] The server delivers the generated coupon advertisement to the user terminal. The user terminal receives the delivered coupon advertisement and displays it on the display of the smart device. The input is the customized coupon advertisement, and the output is the advertisement displayed on the display of the user terminal.

[1486] Step 7:

[1487] The device monitors whether the user utilizes the generated coupon advertisement and collects new behavioral history, purchase history, and emotional data again. The input is the user's advertisement usage behavior data, and the output is updated behavioral history, purchase history, and emotional data. This makes it possible to generate even more optimized advertisements in the next cycle.

[1488] At each step, the server, terminal, or user plays a key role, and the processes of data collection, analysis, generation, distribution, and reevaluation are carried out smoothly, enabling the provision of optimal coupon advertisements to users.

[1489] 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.

[1490] 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.

[1491] 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.

[1492] 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.

[1493] 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.

[1494] 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.

[1495] 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).

[1496] 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.

[1497] 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."

[1498] 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.

[1499] 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).

[1500] 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.

[1501] 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.

[1502] 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.

[1503] 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.

[1504] 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.

[1505] 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.

[1506] 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.

[1507] 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.

[1508] 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.

[1509] 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.

[1510] The following is further disclosed regarding the above embodiment.

[1511] (Claim 1)

[1512] A means for acquiring user behavioral history and purchase history;

[1513] An analysis method using an AI model to analyze the acquired behavioral history and purchase history;

[1514] A means for generating a coupon advertisement customized for each user based on the analysis result;

[1515] A means for delivering the generated coupon advertisement to a user terminal;

[1516] A system including:

[1517] (Claim 2)

[1518] 2. The system according to claim 1, wherein the analysis means analyzes the purchasing trends of each user and selects the optimal coupon using cluster analysis and a recommendation algorithm.

[1519] (Claim 3)

[1520] 2. The system of claim 1, wherein the generated coupon advertisement is displayed on a top screen of the user terminal.

[1521] "Example 1"

[1522] (Claim 1)

[1523] A means for acquiring user behavioral history and purchase history;

[1524] means for transmitting the acquired behavioral history and purchase history to a server in real time;

[1525] A means for storing the received behavioral history and purchase history in a database;

[1526] A means to check the stored data for missing values ​​and outliers, and to correct and supplement them appropriately.

[1527] A means to convert and normalize the data into a format that can be processed by AI models;

[1528] A method for inputting each user's behavioral history and purchase history into an AI model to learn the user's purchasing trends,

[1529] A method for selecting the most suitable coupon for each user using cluster analysis and recommendation algorithms,

[1530] A method to generate coupon advertisements customized for each user based on the analysis results of the AI ​​model, and

[1531] A means for delivering the generated coupon advertisement to a user terminal;

[1532] A means to display customized advertisements on the home screen when the app is opened on the user's device,

[1533] A system including:

[1534] (Claim 2)

[1535] 2. The system according to claim 1, wherein the analysis means analyzes the purchasing trends of each user and selects the optimal coupon using cluster analysis and a recommendation algorithm.

[1536] (Claim 3)

[1537] 2. The system of claim 1, wherein the generated coupon advertisement is displayed on a top screen of the user terminal.

[1538] "Application Example 1"

[1539] (Claim 1)

[1540] A means for acquiring user behavioral history and purchase history;

[1541] A means for processing the acquired behavioral history and purchase history;

[1542] The AI ​​model uses the processed data to analyze each user's purchasing trends,

[1543] A means for generating a coupon advertisement customized for each user based on the analysis result;

[1544] A means for delivering the generated coupon advertisement to a user terminal;

[1545] A system including:

[1546] (Claim 2)

[1547] 2. The system according to claim 1, wherein the analysis means analyzes the purchasing trends of each user and selects the optimal coupon using principal component analysis and a clustering algorithm.

[1548] (Claim 3)

[1549] 10. The system of claim 1, wherein the generated coupon advertisement is delivered to the user terminal as a push notification.

[1550] "Example 2: Combining Emotion Engines"

[1551] (Claim 1)

[1552] A means for acquiring user behavioral history and purchase history;

[1553] A means of obtaining user emotional data using facial recognition and voice analysis technology;

[1554] An analysis means using an AI model and emotion engine to analyze the acquired behavioral history, purchase history, and emotion data;

[1555] A means for generating a coupon advertisement customized for each user based on the analysis result;

[1556] A means for delivering the generated coupon advertisement to a user terminal;

[1557] A system including:

[1558] (Claim 2)

[1559] 2. The system of claim 1, wherein the analysis means analyzes the purchasing trends and emotional states of each user and selects the most suitable coupons using cluster analysis and recommendation algorithms.

[1560] (Claim 3)

[1561] 2. The system of claim 1, wherein the generated coupon advertisement is displayed on a top screen of the user terminal.

[1562] "Application example 2 when combining emotion engines"

[1563] (Claim 1)

[1564] A means for acquiring user behavioral history and purchase history;

[1565] An analysis method using an AI model to analyze the acquired behavioral history and purchase history;

[1566] a means for acquiring and analyzing emotion data;

[1567] A means for generating a coupon advertisement customized for each user based on the analysis result;

[1568] a means for delivering the generated coupon advertisement to a user terminal and displaying it on a display of the smart device;

[1569] A system including:

[1570] (Claim 2)

[1571] 2. The system of claim 1, wherein the analysis means analyzes purchasing trends and sentiment data for each user and selects optimal coupons using cluster analysis and recommendation algorithms.

[1572] (Claim 3)

[1573] The system of claim 1, wherein the generated coupon advertisement is displayed on the top screen of the user terminal or on the display of the smart device. [Explanation of symbols]

[1574] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for acquiring user behavioral history and purchase history; An analysis method using an AI model to analyze the acquired behavioral history and purchase history; A means for generating a coupon advertisement customized for each user based on the analysis result; A means for delivering the generated coupon advertisement to a user terminal; A system including:

2. The system according to claim 1, wherein the analysis means analyzes the purchasing trends of each user and selects the most suitable coupon using cluster analysis and a recommendation algorithm.

3. 2. The system according to claim 1, wherein the generated coupon advertisement is displayed on a top screen of a user terminal.

Images