System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting activity data of a user; means for analyzing the collected activity data and learning a usage trend for each user; means for generating an appropriate coupon or advertisement information based on the usage trend of the user; means for transmitting the generated information to a terminal of the user; means for displaying the information on the terminal of the user; and means for providing additional store information or congestion status based on information selected by the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's world, many people use smartphones and electronic payment systems, but it is still difficult for them to efficiently find the coupons and promotional information that best suit them. Furthermore, it is difficult for merchants to advertise effectively, and the means to deliver accurate information to target customers are limited. To solve this problem, a system is needed that can accurately grasp each user's lifestyle and usage trends and provide them with the most appropriate information based on that information. [Means for solving the problem]

[0005] The present invention solves this problem by providing a means for collecting user activity data and analyzing and learning from that data. It also provides a means for generating coupons and promotional information that are optimal for each user's usage trends based on the learning results, and sending and displaying that information on the user's terminal. Specifically, it provides the following means:

[0006] 1. How we collect user activity data.

[0007] 2. A means of analyzing collected activity data and learning usage trends for each user.

[0008] 3. A means of generating appropriate coupons and promotional information based on user usage trends.

[0009] 4. A means for transmitting the generated information to the user's device.

[0010] 5. A means of displaying information on the user's device.

[0011] 6. A means to provide additional store information and traffic conditions based on user selections.

[0012] The system may further include means for acquiring the user's current location and using the location information to calculate the time required to reach the store. This provides a system that allows users to easily obtain coupons and promotional information that are best suited to them, and allows affiliated stores to carry out efficient promotions.

[0013] "User" is the end consumer who uses the application or system to make payments, collect information, etc.

[0014] "Activity data" refers to information about transactions and actions performed by users using the system, including, specifically, payment date and time, store information, payment amount, etc.

[0015] "Collection means" refers to software and hardware mechanisms for collecting user activity data in real time or batch processing.

[0016] "Means of analysis" refers to algorithms and methods for analyzing collected activity data and extracting user behavior patterns and usage trends.

[0017] "Means of learning" refers to technology that uses machine learning algorithms based on user behavior patterns and usage trends to model a user's unique preferences and interests.

[0018] The "means for generation" refers to a system or algorithm that automatically creates coupons and promotional information appropriate for each user based on the learning results.

[0019] "Transmission means" refers to the communication protocol or technology used to send the generated coupon or promotional information to the user's terminal.

[0020] "Display means" refers to an interface and method for visually displaying coupons and promotional information on a user's terminal, such as in a pop-up format.

[0021] "Additional store information and crowding status" refers to the store's location information and current customer status that are displayed in relation to the coupon or promotional information selected by the user.

[0022] "Means using location information" refers to a method of obtaining the user's current location using technology such as GPS and calculating the time required to reach the store. [Brief explanation of the drawings]

[0023] [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

[0024] 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.

[0025] First, the terms used in the following description will be explained.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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."

[0031] [First embodiment]

[0032] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0033] 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.

[0034] 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).

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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."

[0044] The present invention relates to a system that collects user activity data, analyzes and learns from that data, and provides optimal coupons and promotional information to individual users. Specific embodiments of this system are described below.

[0045] Server-side processing

[0046] The server first collects user activity data. Every time a user uses the payment system, transaction data is acquired in real time and stored in a database. For example, payment date and time, payment store, payment amount, etc. are collected.

[0047] The server then analyzes the collected data and learns the usage trends of each user. Here, machine learning algorithms are used to model user preferences and behavioral patterns based on past behavioral data. For example, if a user tends to frequently visit Chinese restaurants in a particular area (Minato Ward), this pattern can be learned.

[0048] The server then generates optimal coupons and promotional information for each user based on the learning results. The generated information is sent to the user's device as a push notification or message. For example, a user who likes Chinese food will receive a coupon for a nearby Chinese restaurant.

[0049] Terminal side processing

[0050] The device receives coupons and promotional information sent from the server and displays them in the form of a pop-up on the home screen. For example, a notification might appear saying, "20% off coupon for a nearby Chinese restaurant."

[0051] When a user clicks on the popup, the device displays additional information, such as the walking time to the store and the current traffic situation. The device can also use GPS to determine the user's current location and calculate the time it will take to get to the store.

[0052] User processing

[0053] Users can check the information displayed on their device and select the coupons or promotions they are interested in. For example, they can click on "Coupons for a new Chinese restaurant in Minato Ward" to view more information.

[0054] When a user wants to use a coupon, they can show their smartphone at the store and apply the coupon, allowing them to receive a discount.

[0055] Specific examples

[0056] For example, suppose a user visits a Chinese restaurant in Minato Ward four times a week. This user's activity data is collected by the server and automatically analyzed and learned from. The server generates a "20% off coupon for Chinese restaurants in Minato Ward" for this user and sends it to the user's device. The user can check this coupon on their smartphone and, if they decide to use it, present the coupon at the store to receive the discount.

[0057] In this way, the present invention realizes a system that can provide information tailored to the needs and preferences of each individual user, and provides a convenient and valuable service to users. The roles of the server, terminal, and user are clearly defined, and the entire system works seamlessly together to provide a highly personalized experience.

[0058] The processing flow will be explained below.

[0059] Step 1:

[0060] The server collects transaction data in real time when a user uses the payment system, specifically data such as the date and time of payment, store information, and payment amount, and stores the data in a database.

[0061] Step 2:

[0062] The server periodically analyzes the collected transaction data in batches, where it uses data analysis algorithms to analyze each user's activity data and extract usage trends.

[0063] Step 3:

[0064] The server uses machine learning algorithms to learn from the analyzed usage trends, for example, if a particular user frequently visits a particular type of store in a certain area, it will model that pattern.

[0065] Step 4:

[0066] The server then generates optimal coupons and promotional information for each user based on the learning results. The generated information is based on the user's past behavioral data and current interests.

[0067] Step 5:

[0068] The server then sends the generated coupons and promotional information to the user's device in the form of push notifications or messages, using a communication protocol to send the information quickly and securely.

[0069] Step 6:

[0070] The device receives coupons and promotional information sent from the server in the background, stores it in a local database, and then displays it in a pop-up format on the home screen at the appropriate time.

[0071] Step 7:

[0072] When users click on the pop-up, the device opens a screen with additional details, such as walking time to the store and real-time traffic conditions.

[0073] Step 8:

[0074] The device uses GPS to obtain the user's current location, and only with the user's permission, uses this location information to calculate and display the route and travel time to the store.

[0075] Step 9:

[0076] Users check the information displayed on their device and select the coupons and promotional information they are interested in. They check the details of the coupon they want to use and understand the applicable conditions.

[0077] Step 10:

[0078] The user presents the coupon at the store to receive the discount. The store will verify the coupon and apply the corresponding discount. The verification process is complete when the user receives the discount.

[0079] Example 1

[0080] 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."

[0081] Conventional systems have struggled to provide personalized services based on individual user preferences and behavioral patterns. They also lacked the means to provide users with information that would actually be useful to them at the right time. As a result, it was difficult to provide effective advertising and coupons that met user demand.

[0082] 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.

[0083] In this invention, the server includes means for collecting user activity data, means for saving the collected activity data in a database, means for analyzing the saved data and learning usage trends for each user, means for generating appropriate coupons and promotional information based on the user's usage trends, means for sending the generated information to the user's terminal, means for displaying the information on the user's terminal, and means for providing additional store information and congestion status based on information selected by the user. This makes it possible to provide optimal information at the appropriate time according to the user's preferences and behavioral patterns.

[0084] "User" refers to an individual user of the system.

[0085] "Activity data" refers to data related to the user's behavior, and specifically includes payment information, location information, and the like.

[0086] "Means of collection" refers to the hardware and software used to obtain activity data.

[0087] "Database" refers to the system or function for storing and managing collected data.

[0088] "Means for storage" refers to the function for storing collected activity data in a database.

[0089] "Means for analysis" refers to the function for analyzing user usage trends using collected data.

[0090] "Means of learning" refers to algorithms and functions for modeling user preferences and behavioral patterns based on the analysis results.

[0091] "Means for generating" refers to the function for creating coupons and promotional information suitable for users based on the learning results.

[0092] "Means for sending" refers to the function for sending the generated coupons and promotional information to the user's terminal.

[0093] "Terminal" refers to an electronic device used by a user to receive and display information.

[0094] "Display means" refers to the function for visually displaying coupons and promotional information on the terminal.

[0095] "Selected information" refers to coupons and promotional information selected by the user on the device.

[0096] "Additional store information" refers to detailed store information related to the selected information.

[0097] "Crowd status" refers to data showing the current level of congestion at the store.

[0098] "Location Information" refers to geographic data that indicates a user's current location.

[0099] "Means for calculating travel time" refers to a function for calculating travel time from the user's current location to the store.

[0100] This invention relates to a system that collects user activity data, analyzes and learns from that data, and provides optimal coupons and promotional information to each individual user. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0101] Server-side processing

[0102] The server first uses the payment system's API to collect user activity data. Specifically, it obtains transaction data (payment date and time, payment store, payment amount, etc.) in real time when the user makes a payment and stores it in a database. The database is typically MySQL or MongoDB.

[0103] The server then analyzes the collected data, using machine learning algorithms such as Scikit-learn and TensorFlow to model user preferences and behavioral patterns based on past behavioral data. For example, if a user tends to frequently visit Chinese restaurants in a particular area (Minato Ward), the system will learn that pattern.

[0104] Based on the learning results, the server generates optimal coupons and promotional information for each user. The generated information is sent to the user's device as a push notification or message using FIREBASE Cloud Messaging (FCM). For example, a user who likes Chinese food will receive a coupon for a nearby Chinese restaurant.

[0105] Terminal side processing

[0106] The device receives coupons and promotional information sent from the server and displays them in the form of a pop-up on the home screen. For example, a notification might appear saying, "20% off coupon for a nearby Chinese restaurant."

[0107] When the user clicks on the popup, the device displays additional information, such as the walking time to the store and current traffic conditions using the Google Maps API. The device can also use GPS to determine the user's current location and calculate the time it will take to get to the store.

[0108] User processing

[0109] The user checks the information displayed on the device and selects the coupon or promotional information they are interested in. For example, they click on "Coupon for a new Chinese restaurant in Minato Ward" to check the details.

[0110] When a user wants to use a coupon, they can present their smartphone at the store and apply the coupon, allowing them to receive a discount.

[0111] Specific examples

[0112] For example, suppose a user visits a Chinese restaurant in Minato Ward four times a week. The user's activity data is collected by the server and automatically analyzed and learned from. The server generates a "20% off coupon for the Chinese restaurant in Minato Ward" for the user and sends it to the user's device. The user can check this coupon on their smartphone and, if they decide to use it, present the coupon at the store to receive the discount.

[0113] Example prompts for generative AI models

[0114] If a user visits a Chinese restaurant in Minato Ward four times a week, I want to create an algorithm that generates the most suitable coupons and promotional information for that user. What kind of machine learning method should I use based on past user data?

[0115] As described above, it is possible to provide information tailored to individual needs based on user activity data. This system clarifies the roles played by the server, device, and user, and achieves seamless cooperation, thereby providing a highly personalized experience.

[0116] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0117] Step 1:

[0118] The server collects user activity data. Specifically, when a user uses the payment system, payment information (payment date and time, payment store, payment amount, etc.) is obtained in real time via API. The input is the transaction data of the payment system, and the output is the collected activity data.

[0119] Step 2:

[0120] The server stores the collected data in a database. Specifically, it stores the acquired transaction data in a database such as MySQL or MongoDB. The input is the collected activity data, and the output is the data stored in the database.

[0121] Step 3:

[0122] The server analyzes the data and learns the trends of each user. Specifically, it uses a Python program to analyze the data with machine learning algorithms such as Scikit-learn and TensorFlow to model user preferences and behavioral patterns. The input is the activity data in the database, and the output is a model of the user's behavioral patterns as a result of learning.

[0123] Step 4:

[0124] The server generates optimal coupons and promotional information based on the learning results. Specifically, it uses the output of the machine learning model to apply a predictive algorithm to create optimal coupons and promotional information for each user. The input is a model of the user's behavioral patterns, and the output is the generated coupons and promotional information.

[0125] Step 5:

[0126] The server sends the generated information to the user's device. Specifically, it uses FIREBASE Cloud Messaging (FCM) to send the generated coupons and promotional information to the user's mobile device as push notifications. The input is the generated coupons and promotional information, and the output is the notification sent to the user's device.

[0127] Step 6:

[0128] The device notifies the user of the received information. Specifically, it uses the device's notification system to display a notification in pop-up format on the home screen. For example, it displays a message such as "20% off coupon for a nearby Chinese restaurant." The input is the received coupon or promotional information, and the output is the notification displayed on the home screen.

[0129] Step 7:

[0130] The user checks the notification and selects a coupon or promotional information. Specifically, the user clicks on the displayed notification and takes the action of checking detailed information. The input is the notification displayed on the home screen, and the output is the coupon or promotional information selected by the user.

[0131] Step 8:

[0132] The device displays detailed coupon information, the distance to the store, and the store's congestion status. Specifically, it uses the Google Maps API to calculate the walking time from the user's current location to the store, and also retrieves and displays store congestion status information from a database. The input is the coupon selected by the user and the device's location information, and the output is the store information displayed on the detailed information screen.

[0133] Step 9:

[0134] Users can receive a discount by using a coupon and presenting it at a store. Specifically, they present the coupon displayed on their smartphone at the store to receive the discount. The store confirms that the coupon has been applied by scanning a QR code or barcode. The input is the coupon presented by the user, and the output is the transaction in which the discount was received.

[0135] (Application example 1)

[0136] 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."

[0137] Today's consumers have a wide range of choices and require personalized information tailored to their preferences and behavioral patterns. However, existing systems face challenges in effectively analyzing user activity data and providing optimal coupons and promotional information to individual users. Furthermore, there are still insufficient means to provide this information at the right time and quickly display information that is valuable to users.

[0138] 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.

[0139] In this invention, the server includes means for collecting user activity data, means for analyzing the collected activity data and using a machine learning algorithm to learn usage trends for each user, means for generating appropriate coupons and promotional information based on the user's usage trends, means for transmitting the generated information to the user's terminal, means for displaying the information on the user's terminal, means for providing additional store information and congestion status based on information selected by the user, means for acquiring the user's location information and displaying a route to the store, means for generating a QR code or barcode and presenting it at the store when using a coupon, and means for transmitting a push notification including the generated coupon information to the user's terminal. This enables the provision of personalized information according to the preferences and behavioral patterns of each user, and allows coupons and promotional information valuable to the user to be provided promptly and at an appropriate time.

[0140] "User activity data" is a collection of information about a user's behavior, such as purchase history, transaction data, browsing history, and location information.

[0141] A "machine learning algorithm" is a mathematical model or computational method for finding patterns and making predictions based on collected data.

[0142] A "coupon" is a digital or physical certificate offering a discount or special offer on a specific product or service.

[0143] "Advertising information" refers to information such as messages, images, and texts intended to promote products or advertise services.

[0144] A "terminal" is a mobile device such as a smartphone or tablet that a user can easily carry and use.

[0145] A "push notification" is a real-time notification message sent from the server to the user's device.

[0146] "Location information" refers to information about a user's current location obtained using GPS, Wi-Fi, etc.

[0147] "Means for displaying routes" refers to a mechanism that provides a function for displaying routes from the user's current location to their destination as a map or guide.

[0148] A "QR code" is a two-dimensional barcode used to store coupon and link information.

[0149] A "barcode" is a one-dimensional readable code used to identify and manage products.

[0150] "Store information" is detailed information useful to users, such as the store's location, business hours, and current congestion status.

[0151] "Crowding status" is information that indicates the current number of users of a store or facility, waiting times, etc.

[0152] MODE FOR CARRYING OUT THE INVENTION

[0153] This invention relates to a system that collects user activity data, analyzes and learns from that data, and provides optimal coupons and promotional information to individual users. Specific embodiments of the system are described below.

[0154] Server-side processing

[0155] The server first collects user activity data. Every time a user uses the payment system, transaction data is acquired in real time and stored in a database. For example, information such as the payment date and time, the payment store, and the payment amount is collected. The user's location information is also collected using the GPS function. The server then analyzes the collected data and learns the usage trends of each user. Here, machine learning algorithms such as TensorFlow and Scikit-learn are used to model user preferences and behavioral patterns based on past behavioral data. For example, if a user tends to frequently visit Chinese restaurants in a particular area (e.g., a certain neighborhood), this pattern is learned. Based on the learning results, the server generates coupons and promotional information that are optimal for each user. The generated information is sent to the user's device as a push notification.

[0156] Terminal side processing

[0157] The device receives coupons and promotional information sent from the server and displays them as notifications on the home screen. For example, a "20% off coupon for a nearby Chinese restaurant" may be displayed. When the user clicks on the notification, the device displays additional information, such as the walking time to the store and the current congestion status. The device can also obtain the user's current location using GPS and display the estimated time to the store and route information using Google Maps APIs, etc. Furthermore, when using a coupon, a QR code or barcode can be generated and presented at the store.

[0158] User processing

[0159] Users can check the information displayed on their device and select the coupons or promotions they are interested in. For example, they can click on "Coupons for a Specific Chinese Restaurant" to view more information. If they want to use a coupon, they can present their smartphone at the store and apply the coupon, allowing them to receive a discount.

[0160] Specific examples

[0161] For example, suppose a user visits a Chinese restaurant four times a week. This user's activity data is collected by the server and automatically analyzed and learned from. The server generates a "20% off coupon for Chinese restaurants" for this user and sends it to the user's device. The user can check this coupon on their smartphone and, if they decide to use it, present the coupon at the restaurant to receive the discount.

[0162] Prompt Sentence Examples

[0163] An example prompt for a generative AI model is below:

[0164] "Please help us design a system that learns preferences based on user data and generates the most appropriate coupons for each individual. For example, we will create a process that generates a 20% off coupon for Chinese restaurants based on the frequency of visits to Chinese restaurants."

[0165] In this way, the present invention realizes a system that can provide information tailored to the needs and preferences of each individual user, and provides a service that is convenient and valuable to the user. The roles of the server, terminal, and user are clearly defined, and the entire system works seamlessly together to provide a highly personalized experience.

[0166] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0167] Step 1: Collecting user activity data

[0168] The server captures transaction data in real time each time a user uses the payment system and stores it in a database. Specifically, it collects information on the date and time of payment, the store where the payment was made, the payment amount, and the user's location. This allows consistent user activity data to be accumulated. The input is payment data and location information, and the output is the activity data stored in the database.

[0169] Step 2: Data analysis and training

[0170] The server analyzes the collected data and uses machine learning algorithms (e.g., TensorFlow and Scikit-learn) to learn the usage trends of each user. The input is activity data stored in the database, and the output is the learning results that model the user's preferences and behavioral patterns. Specifically, it identifies patterns of usage frequency and destinations, and analyzes that data to create a predictive model.

[0171] Step 3: Generate coupons and promotions

[0172] The server generates optimal coupons and promotional information for each user based on the learning results. The input is the learning results, and the output is the generated coupons and promotional information. Specifically, the type and content of coupons to be delivered to users is determined based on the inference results of the machine learning model.

[0173] Step 4: Send coupons and promotional information

[0174] The server sends the generated coupons and promotional information to the user's device as push notifications. The input is the generated coupons and promotional information, and the output is the notification sent to the device. Specifically, the notification message is sent via an HTTP request and displayed in real time on the user's device.

[0175] Step 5: View and select notifications

[0176] The device receives coupons and promotional information sent from the server and displays them in the form of notifications on the home screen. For example, a message such as "20% off coupon for Chinese restaurants" may be displayed. When the user clicks on the notification, more information is displayed. The input is the received notification data, and the output is the notification displayed on the home screen.

[0177] Step 6: Provide additional information

[0178] The device displays route information to the store and the current congestion status based on the information selected by the user. The input is the information the user clicks on the notification, and the output is the additional information displayed on the device. Specifically, it uses the Google Maps API to calculate and display the route to the store and the required time.

[0179] Step 7: Present and redeem the coupon

[0180] When a user wants to use a coupon, the terminal generates a QR code or barcode and presents it at the store. The input is the coupon information, and the output is the generated QR code or barcode. Specifically, the coupon information is converted into a readable code that can be scanned at the store.

[0181] This allows each processing step to be specifically linked, enabling the provision of fast, personalized information to users.

[0182] 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.

[0183] The present invention relates to a system that collects, analyzes, and learns from users' activity data and emotion data, and then provides optimal coupons and promotional information to each individual user. Specific embodiments of this system are described below.

[0184] Server-side processing

[0185] The server first collects user activity data. Every time a user uses the payment system, transaction data is acquired in real time and stored in a database. For example, payment date and time, store information, payment amount, etc. are collected.

[0186] The server then analyzes the collected data and learns the usage trends of each user. Here, machine learning algorithms are used to model user preferences and behavioral patterns based on past behavioral data. For example, if a user tends to frequently visit Chinese restaurants in a particular area (Minato Ward), this pattern can be learned.

[0187] The server also collects and analyzes the user's emotional data using an emotion engine. The emotion engine can recognize emotions from the user's voice, facial expressions, and text input. For example, it can analyze the text when the user types a message on their smartphone or the tone of their voice command to identify the user's current emotional state.

[0188] The server generates optimal coupons and promotional information for each user based on the learning results and emotional data. The generated information is based on the user's past behavioral data and current emotional state.

[0189] The server sends the generated coupons and promotional information to the user's device as a push notification or message. For example, when sending a coupon for a nearby Chinese restaurant to a user who likes Chinese food, the server attaches information about a restaurant where the user can relax based on the user's current emotional state (e.g., a desire to reduce stress).

[0190] Terminal side processing

[0191] The device receives coupons and promotional information sent from the server and displays them in a pop-up format on the home screen. For example, a "20% off coupon for a nearby Chinese restaurant" may be displayed along with additional information such as "A relaxing environment."

[0192] When the user clicks on the pop-up, the device opens a screen that provides additional information, such as walking time to the store, real-time traffic conditions, etc. Additionally, an emotion engine can analyze the user's voice and text inputs to update their emotional state in real time.

[0193] The device uses GPS to determine the user's current location and calculates the time it will take to get to the store, using location information only if the user gives permission.

[0194] User processing

[0195] Users can review the information displayed on their device and select the coupons and promotions they are interested in. For example, they can click on "Coupons for new Chinese restaurants in Minato Ward" to view more information, and then use the information provided by the emotion engine to select the most suitable restaurant.

[0196] When a user uses a coupon, they present their smartphone at the store and receive a discount by applying the coupon. The store will then check the coupon and apply the corresponding discount.

[0197] Specific examples

[0198] Let's say a user visits a Chinese restaurant in Minato Ward four times a week. The user's activity data is collected by the server and automatically analyzed and learned. Furthermore, if the user is in an emotional state that requires relaxation, the server generates a "20% off coupon that can be used at Chinese restaurants in Minato Ward" along with additional information such as "This restaurant has a relaxing environment" and sends it to the device. The user can check this coupon on their smartphone and present it at the restaurant to receive the discount.

[0199] As described above, this invention realizes a system that can provide information tailored to the needs and emotions of individual users, and provides convenient and valuable services to users. The roles of the server, terminal, and user are clearly defined, and the entire system works seamlessly together to provide a highly personalized experience.

[0200] The processing flow will be explained below.

[0201] Step 1:

[0202] The server collects transaction data in real time when a user uses the payment system, specifically data such as the date and time of payment, store information, and payment amount, and stores the data in a database.

[0203] Step 2:

[0204] The server periodically analyzes collected transaction data in batches, using data analysis algorithms to extract each user's behavioral patterns and usage trends.

[0205] Step 3:

[0206] The server uses machine learning algorithms to learn from the analyzed usage trend data, for example, if a particular user tends to frequently visit a particular type of store in a particular area, it models that pattern.

[0207] Step 4:

[0208] The server collects user emotion data using an emotion engine. The emotion engine recognizes emotions from the user's voice, facial expressions, and text input. For example, it analyzes text and voice commands when the user types a message on a smartphone.

[0209] Step 5:

[0210] The server analyzes the collected emotional data using an emotion engine to identify the user's emotional state and classify it into emotion categories, specifically, stress, joy, sadness, and relaxation.

[0211] Step 6:

[0212] The server generates optimal coupons and promotional information for each user based on the learning results and emotional data, taking into account the user's past behavioral data and current emotional state.

[0213] Step 7:

[0214] The server sends the generated coupons and promotional information to the user's device via push notification. For example, a "20% off coupon for a nearby Chinese restaurant" may be included along with additional information such as "a restaurant with a relaxing environment."

[0215] Step 8:

[0216] The device receives coupons and promotional information sent from the server in the background, stores it in a local database, and then displays it in a pop-up format on the home screen at the appropriate time.

[0217] Step 9:

[0218] When users click on the pop-up, the device opens a screen with additional details, such as walking time to the store, real-time traffic conditions, and a description of the relaxing environment.

[0219] Step 10:

[0220] The device uses GPS to obtain the user's current location, and only if the user gives permission does it use that information to calculate and display the route and travel time to the store.

[0221] Step 11:

[0222] Users can check the information displayed on their device and select the coupons or promotions they are interested in. For example, they can click on "Coupons for a new Chinese restaurant in Minato Ward" to view more information.

[0223] Step 12:

[0224] The user presents the coupon at the store to receive the discount. The store checks the coupon and applies the corresponding discount, allowing the user to receive the discount.

[0225] Example 2

[0226] 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."

[0227] Conventional coupon and promotional information systems have difficulty providing personalized information that takes into account each user's usage trends, and do not deliver appropriate information that reflects the user's emotional state. As a result, information of little value to users is often provided. Furthermore, the provision of real-time information such as the user's current location, travel time to the store, and congestion status is also insufficient. This has led to issues such as reduced convenience and satisfaction for users.

[0228] 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.

[0229] In this invention, the server includes means for collecting user activity data, means for analyzing the collected activity data and learning usage trends for each user, means for collecting and analyzing user emotion data from voice, facial expression, and text input, means for generating appropriate coupons and promotional information based on the user's usage trends and emotion data, means for transmitting the generated information to the user's terminal, means for displaying the information on the user's terminal, and means for providing additional store information and congestion status based on information selected by the user. This makes it possible to provide valuable information tailored to the user's needs and emotional state, thereby improving convenience and satisfaction.

[0230] "User activity data" refers to the behavioral history of a user when using a specific service or system, and includes, for example, payment date and time, payment amount, store information, etc.

[0231] "Means for collection" refers to the combination of hardware and software that the system uses to collect user activity data and emotional data.

[0232] "Means of analysis" refers to algorithms and software that analyze collected data to reveal users' usage trends and emotional states.

[0233] "Means of learning" refers to a method of generating a model using a machine learning algorithm based on user usage trends and emotional data.

[0234] "Emotional data" refers to data on the emotional state extracted from the user's voice, facial expression, text input, etc.

[0235] "Means of generation" refers to algorithms and systems that generate coupons and promotional information tailored to users based on the results of analysis and learning.

[0236] "Transmission means" refers to the communication means and network protocol for transmitting the generated coupons and promotional information to the user's terminal.

[0237] "Displaying means" refers to the display process and interface for visually presenting coupons and promotional information on the user's terminal.

[0238] "Additional store information and congestion status" refers to information such as the time required to reach the store and the current congestion status that is provided along with coupons and promotional information.

[0239] "Location Information" refers to information about a user's current location obtained by GPS or other means.

[0240] "Means for calculating travel time" refers to algorithms or software for calculating travel time from a user to a store based on location information.

[0241] "Permission-based location collection" refers to protocols and permission management systems for collecting location information with user consent.

[0242] This invention is a system that provides optimal coupons and promotional information to individual users by collecting, analyzing, and learning from user activity and emotion data. This system provides useful and valuable information to users through collaboration between the server, terminal, and user.

[0243] Server Processing

[0244] The server first collects user activity data. Specifically, when a user uses the payment system, transaction data such as payment date and time, store information, and payment amount are obtained in real time and stored in a central database. The server polls for data through the payment system's API and immediately stores any new transaction data it detects.

[0245] Next, the server uses an emotion engine to collect the user's emotional data from voice, facial expressions, and text input. The emotion engine determines the user's emotional state using methods such as voice recognition, facial expression analysis, and text analysis. Specific examples include using the Google Cloud Speech-to-Text API and natural language processing toolkits. The server obtains voice and text data from the smartphone app and sends it to the emotion engine to identify emotions.

[0246] The server then uses the collected activity and emotion data to perform machine learning to learn each user's behavioral patterns. This is done using the Python scikit-learn library. The data is fed into the machine learning model to identify each user's behavioral patterns.

[0247] The server then uses a generative algorithm to generate optimal coupons and promotional information for each user based on the learning results and emotion data. A TensorFlow-based generative model is used for this. The generated coupons and promotional information are then sent to the user's device via Google Firebase Cloud Messaging (FCM) or Apple Push Notification Service (APNS).

[0248] Terminal handling

[0249] The device receives coupons and promotional information sent from the server and displays them in a pop-up format on the home screen. The received push notification triggers a specific activity within the app, displaying the coupon information and additional information. When the user clicks on the pop-up, the device provides additional information such as walking time to the store and real-time congestion status.

[0250] For example, the device uses GPS data to obtain the current location, calculates and displays route guidance to the store using the Google Maps API, and obtains congestion information using the Firebase Realtime Database and displays it in real time.

[0251] User Action

[0252] Users can check the information displayed on their device and select coupons or promotional information that interest them. For example, they can click on "Coupons for a new Chinese restaurant in Minato Ward" to view more information. When using a coupon, users present their smartphone at the store and apply the coupon to receive a discount. Feedback information is also sent from within the app to the server and used for future analysis.

[0253] Specific examples

[0254] If a user visits a Chinese restaurant in Minato Ward four times a week, the server collects that activity data and automatically analyzes and learns from it. If the server determines that the user is in an emotional state that requires relaxation, it generates a 20% off coupon for Chinese restaurants in Minato Ward along with additional information such as "This restaurant has a relaxing environment" and sends it to the device. The user can then view the coupon on their smartphone and present it at the restaurant to receive the discount.

[0255] Prompt Sentence Examples

[0256] An example of a prompt to input to a generative AI model is as follows:

[0257] Generate customized coupon information based on user activity and sentiment data, and suggest messages based on the coupon type and user sentiment.

[0258] The above is a specific embodiment for carrying out the present invention. This system makes it possible to provide high-value-added information that meets the needs and emotional state of the user, thereby improving convenience and satisfaction.

[0259] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0260] Step 1:

[0261] The server collects user activity data.

[0262] Input: Transaction data obtained from the payment system (payment date and time, store information, payment amount).

[0263] Processing: Polls activity data through the payment system's API and stores new data in the database whenever it is detected.

[0264] Output: Activity data stored in a database.

[0265] Specific operation: The server periodically sends requests to the payment system's API to obtain new transactions and store them in the database.

[0266] Step 2:

[0267] The server collects emotional data such as voice, facial expressions, and text input.

[0268] Input: Voice data, facial expression data, and text data obtained from a smartphone app.

[0269] Processing: An emotion engine is used to perform speech recognition, facial expression analysis, and text analysis to identify emotional states.

[0270] Output: Identified emotion data.

[0271] Specific operation: Receives voice and text data sent from a smartphone and analyzes sentiment using the Google Cloud Speech-to-Text API and natural language processing toolkit.

[0272] Step 3:

[0273] The server analyzes the collected activity and emotion data to learn each user's usage trends.

[0274] Input: Activity and emotion data stored in a database.

[0275] Processing: We use machine learning algorithms to model your usage habits and behavioral patterns.

[0276] Output: Learned behavioral pattern model.

[0277] Specific operation: Using Python's scikit-learn library, data is input into a learning model and usage trends are analyzed.

[0278] Step 4:

[0279] The server generates coupons and promotional information based on the learning results and emotion data.

[0280] Input: Learned behavioral pattern model and current emotion data.

[0281] Processing: A generation algorithm is used to generate personalized coupons and promotional information.

[0282] Output: Generated coupons and promotions.

[0283] Specific operation: Learning results and emotion data are input into a generative model using TensorFlow to generate individually customized coupon information.

[0284] Step 5:

[0285] The server transmits the generated coupons and advertising information to the user's terminal.

[0286] Input: Generated coupon or promotion information.

[0287] Processing: Sending information to the terminal using a communication protocol.

[0288] Output: Coupons and promotional information sent to the user's device.

[0289] Specific operation: Sends push notifications via Google Firebase Cloud Messaging (FCM) or Apple Push Notification Service (APNS).

[0290] Step 6:

[0291] The terminal displays the received coupons and promotional information.

[0292] Input: Coupons and promotional information received from the server.

[0293] Action: Trigger a notification to display information.

[0294] Output: Coupons and promotional information displayed on the device screen.

[0295] Specific behavior: The device will trigger a specific activity within the app and display information in response to the received push notification.

[0296] Step 7:

[0297] The terminal provides additional store information and crowding status.

[0298] Input: Coupons and promotions selected by the user. GPS data of current location.

[0299] Processing: Obtain any additional information needed and perform calculations.

[0300] Output: Additional information provided to the user (e.g., travel time to the store, how busy it is, etc.).

[0301] Specific operation: Calculates route guidance to the store using the Google Maps API, and obtains and displays congestion information using the Firebase Realtime Database.

[0302] Step 8:

[0303] Users take advantage of coupons, promotions and provide feedback.

[0304] Input: Coupons and promotional information displayed on the device.

[0305] Action: Present a coupon to receive a discount or submit feedback.

[0306] Output: Coupons used and feedback data sent to the server.

[0307] How it works: The user displays the coupon on their smartphone and presents it at the store. Feedback is sent from within the app to the server.

[0308] (Application example 2)

[0309] 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."

[0310] In recent years, there has been a demand for personalized and effective advertising. Existing systems only provide coupons and promotional information based on user activity data, but do not take into account the user's emotional state. As a result, it is difficult to provide appropriate information that is tailored to the user's current situation.

[0311] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user activity data, means for analyzing the collected activity data and learning usage trends for each user, means for collecting and analyzing user emotion data, means for generating advertisements related to the user's emotional state based on the emotion data, and means for generating advertisements based on the user's profile using a generative AI model. This makes it possible to provide more appropriate and effective advertisements based on the user's emotional state and past behavioral data.

[0312] "User activity data" refers to data that reflects a user's daily behavior, including transaction data such as payment date and time, store information, and payment amount.

[0313] "Means of collection" refers to the technical mechanisms and methods for acquiring user activity data and emotional data in real time and storing it in a database.

[0314] "Means of analysis" refers to algorithms and software that analyze collected activity data and learn usage trends for each user.

[0315] "Means of learning" refers to methods and techniques that use machine learning models to model user preferences and behavioral patterns based on past behavioral data.

[0316] "Emotional data" is information about a user's emotional state as recognized from their voice, facial expressions, and text input.

[0317] "Means for collecting and analyzing emotional data" refers to technologies and devices for recognizing and analyzing a user's emotions from voice, facial expressions, and text input.

[0318] The "means for generating" is an algorithm or system that constructs and generates optimal coupons and promotional information based on the learning results and emotional data.

[0319] A "generative AI model" is an artificial intelligence model that is trained on large datasets to generate optimal ads based on user profiles and behavioral patterns.

[0320] A "prompt sentence" is a text-based input sentence used to give specific instructions or requests to a generative AI model.

[0321] "Display means" refers to the technology or screen interface for visually displaying the generated coupon or promotional information on the user's device.

[0322] "Means for providing" refers to a system or method for providing additional store information, congestion status, etc., depending on the information selected by the user.

[0323] "Location information" refers to data about a user's current location obtained using GPS or other means.

[0324] The present invention relates to a system that collects, analyzes, and learns from users' activity data and emotion data, and then provides optimal coupons and promotional information to each individual user. Specific embodiments of this system are described below.

[0325] Server-side processing

[0326] The server first collects user activity data. For example, every time a user uses the payment system, the server obtains transaction data (payment date and time, store information, payment amount, etc.) in real time and stores it in a database.

[0327] The server then analyzes the collected data and learns the usage trends of each user using machine learning algorithms (e.g., libraries such as TensorFlow and Scikit-learn), which model user preferences and behavioral patterns based on past behavioral data.

[0328] The server then uses an emotion engine (e.g., the EmotionRecognition library) to collect and analyze emotion data. It recognizes emotions from the user's voice, facial expressions, and text input to identify their current emotional state. This emotion data is then analyzed by an algorithm to understand each user's emotional state in real time.

[0329] The server generates optimal coupons and promotional information for each user based on the learning results and emotional data. A generative AI model is used for generation, and specific advertisements are generated by providing a prompt. An example of a prompt might be, "We know that the user's emotional state is 'stressed,' and that their preference is 'cafes' based on past behavioral data. Please generate promotional information for relaxing cafes."

[0330] The generated coupons and promotional information are sent to the user's device as push notifications or messages. The server also provides information on nearby stores and their current traffic situation based on the user's current location.

[0331] Terminal side processing

[0332] The device receives coupons and promotional information sent from the server and displays them in a pop-up format on the home screen. For example, a "20% off coupon for a nearby cafe" may be displayed along with additional information such as "A relaxing environment."

[0333] When the user clicks on the pop-up, the device opens a screen that provides additional information, such as walking time to the store and real-time traffic conditions. The emotion engine also analyzes the user's voice and text inputs to update the user's emotional state in real time. The device also uses GPS to determine the user's current location and calculates the estimated time it will take to get to the store. This location information is only used if the user grants permission.

[0334] User processing

[0335] Users can check the information displayed on their device and select coupons or promotional information that they are interested in. For example, they can click on "New Cafe Coupons" to check detailed information and select the most suitable store based on the information provided by the emotion engine. When using a coupon, they can present their smartphone at the store and apply the coupon to receive a discount.

[0336] Such a system will enable the provision of information tailored to the needs and feelings of each individual user, providing a convenient and valuable service to users.

[0337] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0338] Step 1:

[0339] The server collects user activity data (payment date and time, store information, payment amount, etc.). This data is acquired in real time via the payment system and stored in a database. The input is user transaction data, which is saved in the database to generate activity data.

[0340] Step 2:

[0341] The server analyzes the collected activity data. This analysis uses a machine learning algorithm to learn the usage trends of each user. The input is the activity data collected in step 1, and the output is data that models each user's behavioral patterns and preferences. Specific operations include the algorithm analyzing past behavioral data and extracting each user's behavioral patterns.

[0342] Step 3:

[0343] The server collects and analyzes the user's emotional data. It uses an emotion engine (such as the EmotionRecognition library) to recognize emotions from the user's voice, facial expressions, and text input. The input for this process is the user's voice, facial expressions, and text data, and the output is analyzed emotional state data. Specifically, the emotion engine identifies emotions from voice and facial expressions and records that information in a database.

[0344] Step 4:

[0345] The server uses the generative AI model to generate optimal coupons and promotional information based on the learning results and emotional data. This process involves inputting prompt text into the generative AI model to generate specific advertising copy. The input is the learning results and emotional data, and the output is the optimal coupon or promotional information for the user. As a specific example of how this works, an example of a prompt text for the generative AI model is, "We know that the user's emotional state is 'stressed,' and that their preference is 'cafes' based on past behavioral data. Please generate promotional information for relaxing cafes."

[0346] Step 5:

[0347] The server sends the generated coupons and promotional information to the user's device. The input is the advertising information generated in step 4, and the output is the sending of the advertising information to the user's device. Specifically, the information is sent using push notifications or message functions.

[0348] Step 6:

[0349] The device receives coupons and promotional information sent from the server and displays them in a pop-up format on the home screen. The input is advertising information from the server, and the output is the display on the device. Specifically, information such as "20% off coupon for a nearby cafe" and "relaxing environment" is displayed.

[0350] Step 7:

[0351] When the user clicks on the pop-up, the device opens a screen that provides additional information. The input is the user's click, and the output is the display of a detailed information screen. Specific actions include displaying the walking time to the store and real-time congestion information.

[0352] Step 8:

[0353] The device uses an emotion engine to analyze the user's voice and text input and update the emotional state in real time. The input is the user's voice and text data, and the output is updated emotional state data. Specific operations include optimizing the next advertisement or information based on the analyzed emotional information.

[0354] Step 9:

[0355] The user checks the information displayed on the device and selects coupons or promotional information that interests them. The input is the detailed information screen, and the output is the user's selection action. Specific actions include, for example, clicking on a "new cafe coupon" to check the detailed information.

[0356] Step 10:

[0357] When a user uses a coupon, they present their smartphone at the store and receive a discount by applying the coupon. The input is the user's act of presenting the coupon, and the output is the application of the discount. Specific actions include displaying the coupon on the smartphone and the store checking it.

[0358] 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.

[0359] 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.

[0360] 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.

[0361] [Second embodiment]

[0362] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0363] 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.

[0364] 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).

[0365] 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.

[0366] 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.

[0367] 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).

[0368] 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.

[0369] 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.

[0370] 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.

[0371] 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.

[0372] 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.

[0373] 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."

[0374] The present invention relates to a system that collects user activity data, analyzes and learns from that data, and provides optimal coupons and promotional information to individual users. Specific embodiments of this system are described below.

[0375] Server-side processing

[0376] The server first collects user activity data. Every time a user uses the payment system, transaction data is acquired in real time and stored in a database. For example, payment date and time, payment store, payment amount, etc. are collected.

[0377] The server then analyzes the collected data and learns the usage trends of each user. Here, machine learning algorithms are used to model user preferences and behavioral patterns based on past behavioral data. For example, if a user tends to frequently visit Chinese restaurants in a particular area (Minato Ward), this pattern can be learned.

[0378] The server then generates optimal coupons and promotional information for each user based on the learning results. The generated information is sent to the user's device as a push notification or message. For example, a user who likes Chinese food will receive a coupon for a nearby Chinese restaurant.

[0379] Terminal side processing

[0380] The device receives coupons and promotional information sent from the server and displays them in the form of a pop-up on the home screen. For example, a notification might appear saying, "20% off coupon for a nearby Chinese restaurant."

[0381] When a user clicks on the popup, the device displays additional information, such as the walking time to the store and the current traffic situation. The device can also use GPS to determine the user's current location and calculate the time it will take to get to the store.

[0382] User processing

[0383] Users can check the information displayed on their device and select the coupons or promotions they are interested in. For example, they can click on "Coupons for a new Chinese restaurant in Minato Ward" to view more information.

[0384] When a user wants to use a coupon, they can show their smartphone at the store and apply the coupon, allowing them to receive a discount.

[0385] Specific examples

[0386] For example, suppose a user visits a Chinese restaurant in Minato Ward four times a week. This user's activity data is collected by the server and automatically analyzed and learned from. The server generates a "20% off coupon for Chinese restaurants in Minato Ward" for this user and sends it to the user's device. The user can check this coupon on their smartphone and, if they decide to use it, present the coupon at the store to receive the discount.

[0387] In this way, the present invention realizes a system that can provide information tailored to the needs and preferences of each individual user, and provides a convenient and valuable service to users. The roles of the server, terminal, and user are clearly defined, and the entire system works seamlessly together to provide a highly personalized experience.

[0388] The processing flow will be explained below.

[0389] Step 1:

[0390] The server collects transaction data in real time when a user uses the payment system, specifically data such as the date and time of payment, store information, and payment amount, and stores the data in a database.

[0391] Step 2:

[0392] The server periodically analyzes the collected transaction data in batches, where it uses data analysis algorithms to analyze each user's activity data and extract usage trends.

[0393] Step 3:

[0394] The server uses machine learning algorithms to learn from the analyzed usage trends, for example, if a particular user frequently visits a particular type of store in a certain area, it will model that pattern.

[0395] Step 4:

[0396] The server then generates optimal coupons and promotional information for each user based on the learning results. The generated information is based on the user's past behavioral data and current interests.

[0397] Step 5:

[0398] The server then sends the generated coupons and promotional information to the user's device in the form of push notifications or messages, using a communication protocol to send the information quickly and securely.

[0399] Step 6:

[0400] The device receives coupons and promotional information sent from the server in the background, stores it in a local database, and then displays it in a pop-up format on the home screen at the appropriate time.

[0401] Step 7:

[0402] When users click on the pop-up, the device opens a screen with additional details, such as walking time to the store and real-time traffic conditions.

[0403] Step 8:

[0404] The device uses GPS to obtain the user's current location, and only with the user's permission, uses this location information to calculate and display the route and travel time to the store.

[0405] Step 9:

[0406] Users check the information displayed on their device and select the coupons and promotional information they are interested in. They check the details of the coupon they want to use and understand the applicable conditions.

[0407] Step 10:

[0408] The user presents the coupon at the store to receive the discount. The store will verify the coupon and apply the corresponding discount. The verification process is complete when the user receives the discount.

[0409] Example 1

[0410] 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."

[0411] Conventional systems have struggled to provide personalized services based on individual user preferences and behavioral patterns. They also lacked the means to provide users with information that would actually be useful to them at the right time. As a result, it was difficult to provide effective advertising and coupons that met user demand.

[0412] 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.

[0413] In this invention, the server includes means for collecting user activity data, means for saving the collected activity data in a database, means for analyzing the saved data and learning usage trends for each user, means for generating appropriate coupons and promotional information based on the user's usage trends, means for sending the generated information to the user's terminal, means for displaying the information on the user's terminal, and means for providing additional store information and congestion status based on information selected by the user. This makes it possible to provide optimal information at the appropriate time according to the user's preferences and behavioral patterns.

[0414] "User" refers to an individual user of the system.

[0415] "Activity data" refers to data related to the user's behavior, and specifically includes payment information, location information, and the like.

[0416] "Means of collection" refers to the hardware and software used to obtain activity data.

[0417] "Database" refers to the system or function for storing and managing collected data.

[0418] "Means for storage" refers to the function for storing collected activity data in a database.

[0419] "Means for analysis" refers to the function for analyzing user usage trends using collected data.

[0420] "Means of learning" refers to algorithms and functions for modeling user preferences and behavioral patterns based on the analysis results.

[0421] "Means for generating" refers to the function for creating coupons and promotional information suitable for users based on the learning results.

[0422] "Means for sending" refers to the function for sending the generated coupons and promotional information to the user's terminal.

[0423] "Terminal" refers to an electronic device used by a user to receive and display information.

[0424] "Display means" refers to the function for visually displaying coupons and promotional information on the terminal.

[0425] "Selected information" refers to coupons and promotional information selected by the user on the device.

[0426] "Additional store information" refers to detailed store information related to the selected information.

[0427] "Crowd status" refers to data showing the current level of congestion at the store.

[0428] "Location Information" refers to geographic data that indicates a user's current location.

[0429] "Means for calculating travel time" refers to a function for calculating travel time from the user's current location to the store.

[0430] This invention relates to a system that collects user activity data, analyzes and learns from that data, and provides optimal coupons and promotional information to each individual user. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0431] Server-side processing

[0432] The server first uses the payment system's API to collect user activity data. Specifically, it obtains transaction data (payment date and time, payment store, payment amount, etc.) in real time when the user makes a payment and stores it in a database. The database is typically MySQL or MongoDB.

[0433] The server then analyzes the collected data, using machine learning algorithms such as Scikit-learn and TensorFlow to model user preferences and behavioral patterns based on past behavioral data. For example, if a user tends to frequently visit Chinese restaurants in a particular area (Minato Ward), the system will learn that pattern.

[0434] Based on the learning results, the server generates optimal coupons and promotional information for each user. The generated information is sent to the user's device as a push notification or message using FIREBASE Cloud Messaging (FCM). For example, a user who likes Chinese food will receive a coupon for a nearby Chinese restaurant.

[0435] Terminal side processing

[0436] The device receives coupons and promotional information sent from the server and displays them in the form of a pop-up on the home screen. For example, a notification might appear saying, "20% off coupon for a nearby Chinese restaurant."

[0437] When the user clicks on the popup, the device displays additional information, such as the walking time to the store and current traffic conditions using the Google Maps API. The device can also use GPS to determine the user's current location and calculate the time it will take to get to the store.

[0438] User processing

[0439] The user checks the information displayed on the device and selects the coupon or promotional information they are interested in. For example, they click on "Coupon for a new Chinese restaurant in Minato Ward" to check the details.

[0440] When a user wants to use a coupon, they can present their smartphone at the store and apply the coupon, allowing them to receive a discount.

[0441] Specific examples

[0442] For example, suppose a user visits a Chinese restaurant in Minato Ward four times a week. The user's activity data is collected by the server and automatically analyzed and learned from. The server generates a "20% off coupon for the Chinese restaurant in Minato Ward" for the user and sends it to the user's device. The user can check this coupon on their smartphone and, if they decide to use it, present the coupon at the store to receive the discount.

[0443] Example prompts for generative AI models

[0444] If a user visits a Chinese restaurant in Minato Ward four times a week, I want to create an algorithm that generates the most suitable coupons and promotional information for that user. What kind of machine learning method should I use based on past user data?

[0445] As described above, it is possible to provide information tailored to individual needs based on user activity data. This system clarifies the roles played by the server, device, and user, and achieves seamless cooperation, thereby providing a highly personalized experience.

[0446] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0447] Step 1:

[0448] The server collects user activity data. Specifically, when a user uses the payment system, payment information (payment date and time, payment store, payment amount, etc.) is obtained in real time via API. The input is the transaction data of the payment system, and the output is the collected activity data.

[0449] Step 2:

[0450] The server stores the collected data in a database. Specifically, it stores the acquired transaction data in a database such as MySQL or MongoDB. The input is the collected activity data, and the output is the data stored in the database.

[0451] Step 3:

[0452] The server analyzes the data and learns the trends of each user. Specifically, it uses a Python program to analyze the data with machine learning algorithms such as Scikit-learn and TensorFlow to model user preferences and behavioral patterns. The input is the activity data in the database, and the output is a model of the user's behavioral patterns as a result of learning.

[0453] Step 4:

[0454] The server generates optimal coupons and promotional information based on the learning results. Specifically, it uses the output of the machine learning model to apply a predictive algorithm to create optimal coupons and promotional information for each user. The input is a model of the user's behavioral patterns, and the output is the generated coupons and promotional information.

[0455] Step 5:

[0456] The server sends the generated information to the user's device. Specifically, it uses FIREBASE Cloud Messaging (FCM) to send the generated coupons and promotional information to the user's mobile device as push notifications. The input is the generated coupons and promotional information, and the output is the notification sent to the user's device.

[0457] Step 6:

[0458] The device notifies the user of the received information. Specifically, it uses the device's notification system to display a notification in pop-up format on the home screen. For example, it displays a message such as "20% off coupon for a nearby Chinese restaurant." The input is the received coupon or promotional information, and the output is the notification displayed on the home screen.

[0459] Step 7:

[0460] The user checks the notification and selects a coupon or promotional information. Specifically, the user clicks on the displayed notification and takes the action of checking detailed information. The input is the notification displayed on the home screen, and the output is the coupon or promotional information selected by the user.

[0461] Step 8:

[0462] The device displays detailed coupon information, the distance to the store, and the store's congestion status. Specifically, it uses the Google Maps API to calculate the walking time from the user's current location to the store, and also retrieves and displays store congestion status information from a database. The input is the coupon selected by the user and the device's location information, and the output is the store information displayed on the detailed information screen.

[0463] Step 9:

[0464] Users can receive a discount by using a coupon and presenting it at a store. Specifically, they present the coupon displayed on their smartphone at the store to receive the discount. The store confirms that the coupon has been applied by scanning a QR code or barcode. The input is the coupon presented by the user, and the output is the transaction in which the discount was received.

[0465] (Application example 1)

[0466] 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."

[0467] Today's consumers have a wide range of choices and require personalized information tailored to their preferences and behavioral patterns. However, existing systems face challenges in effectively analyzing user activity data and providing optimal coupons and promotional information to individual users. Furthermore, there are still insufficient means to provide this information at the right time and quickly display information that is valuable to users.

[0468] 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.

[0469] In this invention, the server includes means for collecting user activity data, means for analyzing the collected activity data and using a machine learning algorithm to learn usage trends for each user, means for generating appropriate coupons and promotional information based on the user's usage trends, means for transmitting the generated information to the user's terminal, means for displaying the information on the user's terminal, means for providing additional store information and congestion status based on information selected by the user, means for acquiring the user's location information and displaying a route to the store, means for generating a QR code or barcode and presenting it at the store when using a coupon, and means for transmitting a push notification including the generated coupon information to the user's terminal. This enables the provision of personalized information according to the preferences and behavioral patterns of each user, and allows coupons and promotional information valuable to the user to be provided promptly and at an appropriate time.

[0470] "User activity data" is a collection of information about a user's behavior, such as purchase history, transaction data, browsing history, and location information.

[0471] A "machine learning algorithm" is a mathematical model or computational method for finding patterns and making predictions based on collected data.

[0472] A "coupon" is a digital or physical certificate offering a discount or special offer on a specific product or service.

[0473] "Advertising information" refers to information such as messages, images, and texts intended to promote products or advertise services.

[0474] A "terminal" is a mobile device such as a smartphone or tablet that a user can easily carry and use.

[0475] A "push notification" is a real-time notification message sent from the server to the user's device.

[0476] "Location information" refers to information about a user's current location obtained using GPS, Wi-Fi, etc.

[0477] "Means for displaying routes" refers to a mechanism that provides a function for displaying routes from the user's current location to their destination as a map or guide.

[0478] A "QR code" is a two-dimensional barcode used to store coupon and link information.

[0479] A "barcode" is a one-dimensional readable code used to identify and manage products.

[0480] "Store information" is detailed information useful to users, such as the store's location, business hours, and current congestion status.

[0481] "Crowding status" is information that indicates the current number of users of a store or facility, waiting times, etc.

[0482] MODE FOR CARRYING OUT THE INVENTION

[0483] This invention relates to a system that collects user activity data, analyzes and learns from that data, and provides optimal coupons and promotional information to individual users. Specific embodiments of the system are described below.

[0484] Server-side processing

[0485] The server first collects user activity data. Every time a user uses the payment system, transaction data is acquired in real time and stored in a database. For example, information such as the payment date and time, the payment store, and the payment amount is collected. The user's location information is also collected using the GPS function. The server then analyzes the collected data and learns the usage trends of each user. Here, machine learning algorithms such as TensorFlow and Scikit-learn are used to model user preferences and behavioral patterns based on past behavioral data. For example, if a user tends to frequently visit Chinese restaurants in a particular area (e.g., a certain neighborhood), this pattern is learned. Based on the learning results, the server generates coupons and promotional information that are optimal for each user. The generated information is sent to the user's device as a push notification.

[0486] Terminal side processing

[0487] The device receives coupons and promotional information sent from the server and displays them as notifications on the home screen. For example, a "20% off coupon for a nearby Chinese restaurant" may be displayed. When the user clicks on the notification, the device displays additional information, such as the walking time to the store and the current congestion status. The device can also obtain the user's current location using GPS and display the estimated time to the store and route information using Google Maps APIs, etc. Furthermore, when using a coupon, a QR code or barcode can be generated and presented at the store.

[0488] User processing

[0489] Users can check the information displayed on their device and select the coupons or promotions they are interested in. For example, they can click on "Coupons for a Specific Chinese Restaurant" to view more information. If they want to use a coupon, they can present their smartphone at the store and apply the coupon, allowing them to receive a discount.

[0490] Specific examples

[0491] For example, suppose a user visits a Chinese restaurant four times a week. This user's activity data is collected by the server and automatically analyzed and learned from. The server generates a "20% off coupon for Chinese restaurants" for this user and sends it to the user's device. The user can check this coupon on their smartphone and, if they decide to use it, present the coupon at the restaurant to receive the discount.

[0492] Prompt Sentence Examples

[0493] An example prompt for a generative AI model is below:

[0494] "Please help us design a system that learns preferences based on user data and generates the most appropriate coupons for each individual. For example, we will create a process that generates a 20% off coupon for Chinese restaurants based on the frequency of visits to Chinese restaurants."

[0495] In this way, the present invention realizes a system that can provide information tailored to the needs and preferences of each individual user, and provides a service that is convenient and valuable to the user. The roles of the server, terminal, and user are clearly defined, and the entire system works seamlessly together to provide a highly personalized experience.

[0496] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0497] Step 1: Collecting user activity data

[0498] The server captures transaction data in real time each time a user uses the payment system and stores it in a database. Specifically, it collects information on the date and time of payment, the store where the payment was made, the payment amount, and the user's location. This allows consistent user activity data to be accumulated. The input is payment data and location information, and the output is the activity data stored in the database.

[0499] Step 2: Data analysis and training

[0500] The server analyzes the collected data and uses machine learning algorithms (e.g., TensorFlow and Scikit-learn) to learn the usage trends of each user. The input is activity data stored in the database, and the output is the learning results that model the user's preferences and behavioral patterns. Specifically, it identifies patterns of usage frequency and destinations, and analyzes that data to create a predictive model.

[0501] Step 3: Generate coupons and promotions

[0502] The server generates optimal coupons and promotional information for each user based on the learning results. The input is the learning results, and the output is the generated coupons and promotional information. Specifically, the type and content of coupons to be delivered to users is determined based on the inference results of the machine learning model.

[0503] Step 4: Send coupons and promotional information

[0504] The server sends the generated coupons and promotional information to the user's device as push notifications. The input is the generated coupons and promotional information, and the output is the notification sent to the device. Specifically, the notification message is sent via an HTTP request and displayed in real time on the user's device.

[0505] Step 5: View and select notifications

[0506] The device receives coupons and promotional information sent from the server and displays them in the form of notifications on the home screen. For example, a message such as "20% off coupon for Chinese restaurants" may be displayed. When the user clicks on the notification, more information is displayed. The input is the received notification data, and the output is the notification displayed on the home screen.

[0507] Step 6: Provide additional information

[0508] The device displays route information to the store and the current congestion status based on the information selected by the user. The input is the information the user clicks on the notification, and the output is the additional information displayed on the device. Specifically, it uses the Google Maps API to calculate and display the route to the store and the required time.

[0509] Step 7: Present and redeem the coupon

[0510] When a user wants to use a coupon, the terminal generates a QR code or barcode and presents it at the store. The input is the coupon information, and the output is the generated QR code or barcode. Specifically, the coupon information is converted into a readable code that can be scanned at the store.

[0511] This allows each processing step to be specifically linked, enabling the provision of fast, personalized information to users.

[0512] 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.

[0513] The present invention relates to a system that collects, analyzes, and learns from users' activity data and emotion data, and then provides optimal coupons and promotional information to each individual user. Specific embodiments of this system are described below.

[0514] Server-side processing

[0515] The server first collects user activity data. Every time a user uses the payment system, transaction data is acquired in real time and stored in a database. For example, payment date and time, store information, payment amount, etc. are collected.

[0516] The server then analyzes the collected data and learns the usage trends of each user. Here, machine learning algorithms are used to model user preferences and behavioral patterns based on past behavioral data. For example, if a user tends to frequently visit Chinese restaurants in a particular area (Minato Ward), this pattern can be learned.

[0517] The server also collects and analyzes the user's emotional data using an emotion engine. The emotion engine can recognize emotions from the user's voice, facial expressions, and text input. For example, it can analyze the text when the user types a message on their smartphone or the tone of their voice command to identify the user's current emotional state.

[0518] The server generates optimal coupons and promotional information for each user based on the learning results and emotional data. The generated information is based on the user's past behavioral data and current emotional state.

[0519] The server sends the generated coupons and promotional information to the user's device as a push notification or message. For example, when sending a coupon for a nearby Chinese restaurant to a user who likes Chinese food, the server attaches information about a restaurant where the user can relax based on the user's current emotional state (e.g., a desire to reduce stress).

[0520] Terminal side processing

[0521] The device receives coupons and promotional information sent from the server and displays them in a pop-up format on the home screen. For example, a "20% off coupon for a nearby Chinese restaurant" may be displayed along with additional information such as "A relaxing environment."

[0522] When the user clicks on the pop-up, the device opens a screen that provides additional information, such as walking time to the store, real-time traffic conditions, etc. Additionally, an emotion engine can analyze the user's voice and text inputs to update their emotional state in real time.

[0523] The device uses GPS to determine the user's current location and calculates the time it will take to get to the store, using location information only if the user gives permission.

[0524] User processing

[0525] Users can review the information displayed on their device and select the coupons and promotions they are interested in. For example, they can click on "Coupons for new Chinese restaurants in Minato Ward" to view more information, and then use the information provided by the emotion engine to select the most suitable restaurant.

[0526] When a user uses a coupon, they present their smartphone at the store and receive a discount by applying the coupon. The store will then check the coupon and apply the corresponding discount.

[0527] Specific examples

[0528] Let's say a user visits a Chinese restaurant in Minato Ward four times a week. The user's activity data is collected by the server and automatically analyzed and learned. Furthermore, if the user is in an emotional state that requires relaxation, the server generates a "20% off coupon that can be used at Chinese restaurants in Minato Ward" along with additional information such as "This restaurant has a relaxing environment" and sends it to the device. The user can check this coupon on their smartphone and present it at the restaurant to receive the discount.

[0529] As described above, this invention realizes a system that can provide information tailored to the needs and emotions of individual users, and provides convenient and valuable services to users. The roles of the server, terminal, and user are clearly defined, and the entire system works seamlessly together to provide a highly personalized experience.

[0530] The processing flow will be explained below.

[0531] Step 1:

[0532] The server collects transaction data in real time when a user uses the payment system, specifically data such as the date and time of payment, store information, and payment amount, and stores the data in a database.

[0533] Step 2:

[0534] The server periodically analyzes collected transaction data in batches, using data analysis algorithms to extract each user's behavioral patterns and usage trends.

[0535] Step 3:

[0536] The server uses machine learning algorithms to learn from the analyzed usage trend data, for example, if a particular user tends to frequently visit a particular type of store in a particular area, it models that pattern.

[0537] Step 4:

[0538] The server collects user emotion data using an emotion engine. The emotion engine recognizes emotions from the user's voice, facial expressions, and text input. For example, it analyzes text and voice commands when the user types a message on a smartphone.

[0539] Step 5:

[0540] The server analyzes the collected emotional data using an emotion engine to identify the user's emotional state and classify it into emotion categories, specifically, stress, joy, sadness, and relaxation.

[0541] Step 6:

[0542] The server generates optimal coupons and promotional information for each user based on the learning results and emotional data, taking into account the user's past behavioral data and current emotional state.

[0543] Step 7:

[0544] The server sends the generated coupons and promotional information to the user's device via push notification. For example, a "20% off coupon for a nearby Chinese restaurant" may be included along with additional information such as "a restaurant with a relaxing environment."

[0545] Step 8:

[0546] The device receives coupons and promotional information sent from the server in the background, stores it in a local database, and then displays it in a pop-up format on the home screen at the appropriate time.

[0547] Step 9:

[0548] When users click on the pop-up, the device opens a screen with additional details, such as walking time to the store, real-time traffic conditions, and a description of the relaxing environment.

[0549] Step 10:

[0550] The device uses GPS to obtain the user's current location, and only if the user gives permission does it use that information to calculate and display the route and travel time to the store.

[0551] Step 11:

[0552] Users can check the information displayed on their device and select the coupons or promotions they are interested in. For example, they can click on "Coupons for a new Chinese restaurant in Minato Ward" to view more information.

[0553] Step 12:

[0554] The user presents the coupon at the store to receive the discount. The store checks the coupon and applies the corresponding discount, allowing the user to receive the discount.

[0555] Example 2

[0556] 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."

[0557] Conventional coupon and promotional information systems have difficulty providing personalized information that takes into account each user's usage trends, and do not deliver appropriate information that reflects the user's emotional state. As a result, information of little value to users is often provided. Furthermore, the provision of real-time information such as the user's current location, travel time to the store, and congestion status is also insufficient. This has led to issues such as reduced convenience and satisfaction for users.

[0558] 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.

[0559] In this invention, the server includes means for collecting user activity data, means for analyzing the collected activity data and learning usage trends for each user, means for collecting and analyzing user emotion data from voice, facial expression, and text input, means for generating appropriate coupons and promotional information based on the user's usage trends and emotion data, means for transmitting the generated information to the user's terminal, means for displaying the information on the user's terminal, and means for providing additional store information and congestion status based on information selected by the user. This makes it possible to provide valuable information tailored to the user's needs and emotional state, thereby improving convenience and satisfaction.

[0560] "User activity data" refers to the behavioral history of a user when using a specific service or system, and includes, for example, payment date and time, payment amount, store information, etc.

[0561] "Means for collection" refers to the combination of hardware and software that the system uses to collect user activity data and emotional data.

[0562] "Means of analysis" refers to algorithms and software that analyze collected data to reveal users' usage trends and emotional states.

[0563] "Means of learning" refers to a method of generating a model using a machine learning algorithm based on user usage trends and emotional data.

[0564] "Emotional data" refers to data on the emotional state extracted from the user's voice, facial expression, text input, etc.

[0565] "Means of generation" refers to algorithms and systems that generate coupons and promotional information tailored to users based on the results of analysis and learning.

[0566] "Transmission means" refers to the communication means and network protocol for transmitting the generated coupons and promotional information to the user's terminal.

[0567] "Displaying means" refers to the display process and interface for visually presenting coupons and promotional information on the user's terminal.

[0568] "Additional store information and congestion status" refers to information such as the time required to reach the store and the current congestion status that is provided along with coupons and promotional information.

[0569] "Location Information" refers to information about a user's current location obtained by GPS or other means.

[0570] "Means for calculating travel time" refers to algorithms or software for calculating travel time from a user to a store based on location information.

[0571] "Permission-based location collection" refers to protocols and permission management systems for collecting location information with user consent.

[0572] This invention is a system that provides optimal coupons and promotional information to individual users by collecting, analyzing, and learning from user activity and emotion data. This system provides useful and valuable information to users through collaboration between the server, terminal, and user.

[0573] Server Processing

[0574] The server first collects user activity data. Specifically, when a user uses the payment system, transaction data such as payment date and time, store information, and payment amount are obtained in real time and stored in a central database. The server polls for data through the payment system's API and immediately stores any new transaction data it detects.

[0575] Next, the server uses an emotion engine to collect the user's emotional data from voice, facial expressions, and text input. The emotion engine determines the user's emotional state using methods such as voice recognition, facial expression analysis, and text analysis. Specific examples include using the Google Cloud Speech-to-Text API and natural language processing toolkits. The server obtains voice and text data from the smartphone app and sends it to the emotion engine to identify emotions.

[0576] The server then uses the collected activity and emotion data to perform machine learning to learn each user's behavioral patterns. This is done using the Python scikit-learn library. The data is fed into the machine learning model to identify each user's behavioral patterns.

[0577] The server then uses a generative algorithm to generate optimal coupons and promotional information for each user based on the learning results and emotion data. A TensorFlow-based generative model is used for this. The generated coupons and promotional information are then sent to the user's device via Google Firebase Cloud Messaging (FCM) or Apple Push Notification Service (APNS).

[0578] Terminal handling

[0579] The device receives coupons and promotional information sent from the server and displays them in a pop-up format on the home screen. The received push notification triggers a specific activity within the app, displaying the coupon information and additional information. When the user clicks on the pop-up, the device provides additional information such as walking time to the store and real-time congestion status.

[0580] For example, the device uses GPS data to obtain the current location, calculates and displays route guidance to the store using the Google Maps API, and obtains congestion information using the Firebase Realtime Database and displays it in real time.

[0581] User Action

[0582] Users can check the information displayed on their device and select coupons or promotional information that interest them. For example, they can click on "Coupons for a new Chinese restaurant in Minato Ward" to view more information. When using a coupon, users present their smartphone at the store and apply the coupon to receive a discount. Feedback information is also sent from within the app to the server and used for future analysis.

[0583] Specific examples

[0584] If a user visits a Chinese restaurant in Minato Ward four times a week, the server collects that activity data and automatically analyzes and learns from it. If the server determines that the user is in an emotional state that requires relaxation, it generates a 20% off coupon for Chinese restaurants in Minato Ward along with additional information such as "This restaurant has a relaxing environment" and sends it to the device. The user can then view the coupon on their smartphone and present it at the restaurant to receive the discount.

[0585] Prompt Sentence Examples

[0586] An example of a prompt to input to a generative AI model is as follows:

[0587] Generate customized coupon information based on user activity and sentiment data, and suggest messages based on the coupon type and user sentiment.

[0588] The above is a specific embodiment for carrying out the present invention. This system makes it possible to provide high-value-added information that meets the needs and emotional state of the user, thereby improving convenience and satisfaction.

[0589] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0590] Step 1:

[0591] The server collects user activity data.

[0592] Input: Transaction data obtained from the payment system (payment date and time, store information, payment amount).

[0593] Processing: Polls activity data through the payment system's API and stores new data in the database whenever it is detected.

[0594] Output: Activity data stored in a database.

[0595] Specific operation: The server periodically sends requests to the payment system's API to obtain new transactions and store them in the database.

[0596] Step 2:

[0597] The server collects emotional data such as voice, facial expressions, and text input.

[0598] Input: Voice data, facial expression data, and text data obtained from a smartphone app.

[0599] Processing: An emotion engine is used to perform speech recognition, facial expression analysis, and text analysis to identify emotional states.

[0600] Output: Identified emotion data.

[0601] Specific operation: Receives voice and text data sent from a smartphone and analyzes sentiment using the Google Cloud Speech-to-Text API and natural language processing toolkit.

[0602] Step 3:

[0603] The server analyzes the collected activity and emotion data to learn each user's usage trends.

[0604] Input: Activity and emotion data stored in a database.

[0605] Processing: We use machine learning algorithms to model your usage habits and behavioral patterns.

[0606] Output: Learned behavioral pattern model.

[0607] Specific operation: Using Python's scikit-learn library, data is input into a learning model and usage trends are analyzed.

[0608] Step 4:

[0609] The server generates coupons and promotional information based on the learning results and emotion data.

[0610] Input: Learned behavioral pattern model and current emotion data.

[0611] Processing: A generation algorithm is used to generate personalized coupons and promotional information.

[0612] Output: Generated coupons and promotions.

[0613] Specific operation: Learning results and emotion data are input into a generative model using TensorFlow to generate individually customized coupon information.

[0614] Step 5:

[0615] The server transmits the generated coupons and advertising information to the user's terminal.

[0616] Input: Generated coupon or promotion information.

[0617] Processing: Sending information to the terminal using a communication protocol.

[0618] Output: Coupons and promotional information sent to the user's device.

[0619] Specific operation: Sends push notifications via Google Firebase Cloud Messaging (FCM) or Apple Push Notification Service (APNS).

[0620] Step 6:

[0621] The terminal displays the received coupons and promotional information.

[0622] Input: Coupons and promotional information received from the server.

[0623] Action: Trigger a notification to display information.

[0624] Output: Coupons and promotional information displayed on the device screen.

[0625] Specific behavior: The device will trigger a specific activity within the app and display information in response to the received push notification.

[0626] Step 7:

[0627] The terminal provides additional store information and crowding status.

[0628] Input: Coupons and promotions selected by the user. GPS data of current location.

[0629] Processing: Obtain any additional information needed and perform calculations.

[0630] Output: Additional information provided to the user (e.g., travel time to the store, how busy it is, etc.).

[0631] Specific operation: Calculates route guidance to the store using the Google Maps API, and obtains and displays congestion information using the Firebase Realtime Database.

[0632] Step 8:

[0633] Users take advantage of coupons, promotions and provide feedback.

[0634] Input: Coupons and promotional information displayed on the device.

[0635] Action: Present a coupon to receive a discount or submit feedback.

[0636] Output: Coupons used and feedback data sent to the server.

[0637] How it works: The user displays the coupon on their smartphone and presents it at the store. Feedback is sent from within the app to the server.

[0638] (Application example 2)

[0639] 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."

[0640] In recent years, there has been a demand for personalized and effective advertising. Existing systems only provide coupons and promotional information based on user activity data, but do not take into account the user's emotional state. As a result, it is difficult to provide appropriate information that is tailored to the user's current situation.

[0641] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user activity data, means for analyzing the collected activity data and learning usage trends for each user, means for collecting and analyzing user emotion data, means for generating advertisements related to the user's emotional state based on the emotion data, and means for generating advertisements based on the user's profile using a generative AI model. This makes it possible to provide more appropriate and effective advertisements based on the user's emotional state and past behavioral data.

[0642] "User activity data" refers to data that reflects a user's daily behavior, including transaction data such as payment date and time, store information, and payment amount.

[0643] "Means of collection" refers to the technical mechanisms and methods for acquiring user activity data and emotional data in real time and storing it in a database.

[0644] "Means of analysis" refers to algorithms and software that analyze collected activity data and learn usage trends for each user.

[0645] "Means of learning" refers to methods and techniques that use machine learning models to model user preferences and behavioral patterns based on past behavioral data.

[0646] "Emotional data" is information about a user's emotional state as recognized from their voice, facial expressions, and text input.

[0647] "Means for collecting and analyzing emotional data" refers to technologies and devices for recognizing and analyzing a user's emotions from voice, facial expressions, and text input.

[0648] The "means for generating" is an algorithm or system that constructs and generates optimal coupons and promotional information based on the learning results and emotional data.

[0649] A "generative AI model" is an artificial intelligence model that is trained on large datasets to generate optimal ads based on user profiles and behavioral patterns.

[0650] A "prompt sentence" is a text-based input sentence used to give specific instructions or requests to a generative AI model.

[0651] "Display means" refers to the technology or screen interface for visually displaying the generated coupon or promotional information on the user's device.

[0652] "Means for providing" refers to a system or method for providing additional store information, congestion status, etc., depending on the information selected by the user.

[0653] "Location information" refers to data about a user's current location obtained using GPS or other means.

[0654] The present invention relates to a system that collects, analyzes, and learns from users' activity data and emotion data, and then provides optimal coupons and promotional information to each individual user. Specific embodiments of this system are described below.

[0655] Server-side processing

[0656] The server first collects user activity data. For example, every time a user uses the payment system, the server obtains transaction data (payment date and time, store information, payment amount, etc.) in real time and stores it in a database.

[0657] The server then analyzes the collected data and learns the usage trends of each user using machine learning algorithms (e.g., libraries such as TensorFlow and Scikit-learn), which model user preferences and behavioral patterns based on past behavioral data.

[0658] The server then uses an emotion engine (e.g., the EmotionRecognition library) to collect and analyze emotion data. It recognizes emotions from the user's voice, facial expressions, and text input to identify their current emotional state. This emotion data is then analyzed by an algorithm to understand each user's emotional state in real time.

[0659] The server generates optimal coupons and promotional information for each user based on the learning results and emotional data. A generative AI model is used for generation, and specific advertisements are generated by providing a prompt. An example of a prompt might be, "We know that the user's emotional state is 'stressed,' and that their preference is 'cafes' based on past behavioral data. Please generate promotional information for relaxing cafes."

[0660] The generated coupons and promotional information are sent to the user's device as push notifications or messages. The server also provides information on nearby stores and their current traffic situation based on the user's current location.

[0661] Terminal side processing

[0662] The device receives coupons and promotional information sent from the server and displays them in a pop-up format on the home screen. For example, a "20% off coupon for a nearby cafe" may be displayed along with additional information such as "A relaxing environment."

[0663] When the user clicks on the pop-up, the device opens a screen that provides additional information, such as walking time to the store and real-time traffic conditions. The emotion engine also analyzes the user's voice and text inputs to update the user's emotional state in real time. The device also uses GPS to determine the user's current location and calculates the estimated time it will take to get to the store. This location information is only used if the user grants permission.

[0664] User processing

[0665] Users can check the information displayed on their device and select coupons or promotional information that they are interested in. For example, they can click on "New Cafe Coupons" to check detailed information and select the most suitable store based on the information provided by the emotion engine. When using a coupon, they can present their smartphone at the store and apply the coupon to receive a discount.

[0666] Such a system will enable the provision of information tailored to the needs and feelings of each individual user, providing a convenient and valuable service to users.

[0667] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0668] Step 1:

[0669] The server collects user activity data (payment date and time, store information, payment amount, etc.). This data is acquired in real time via the payment system and stored in a database. The input is user transaction data, which is saved in the database to generate activity data.

[0670] Step 2:

[0671] The server analyzes the collected activity data. This analysis uses a machine learning algorithm to learn the usage trends of each user. The input is the activity data collected in step 1, and the output is data that models each user's behavioral patterns and preferences. Specific operations include the algorithm analyzing past behavioral data and extracting each user's behavioral patterns.

[0672] Step 3:

[0673] The server collects and analyzes the user's emotional data. It uses an emotion engine (such as the EmotionRecognition library) to recognize emotions from the user's voice, facial expressions, and text input. The input for this process is the user's voice, facial expressions, and text data, and the output is analyzed emotional state data. Specifically, the emotion engine identifies emotions from voice and facial expressions and records that information in a database.

[0674] Step 4:

[0675] The server uses the generative AI model to generate optimal coupons and promotional information based on the learning results and emotional data. This process involves inputting prompt text into the generative AI model to generate specific advertising copy. The input is the learning results and emotional data, and the output is the optimal coupon or promotional information for the user. As a specific example of how this works, an example of a prompt text for the generative AI model is, "We know that the user's emotional state is 'stressed,' and that their preference is 'cafes' based on past behavioral data. Please generate promotional information for relaxing cafes."

[0676] Step 5:

[0677] The server sends the generated coupons and promotional information to the user's device. The input is the advertising information generated in step 4, and the output is the sending of the advertising information to the user's device. Specifically, the information is sent using push notifications or message functions.

[0678] Step 6:

[0679] The device receives coupons and promotional information sent from the server and displays them in a pop-up format on the home screen. The input is advertising information from the server, and the output is the display on the device. Specifically, information such as "20% off coupon for a nearby cafe" and "relaxing environment" is displayed.

[0680] Step 7:

[0681] When the user clicks on the pop-up, the device opens a screen that provides additional information. The input is the user's click, and the output is the display of a detailed information screen. Specific actions include displaying the walking time to the store and real-time congestion information.

[0682] Step 8:

[0683] The device uses an emotion engine to analyze the user's voice and text input and update the emotional state in real time. The input is the user's voice and text data, and the output is updated emotional state data. Specific operations include optimizing the next advertisement or information based on the analyzed emotional information.

[0684] Step 9:

[0685] The user checks the information displayed on the device and selects coupons or promotional information that interests them. The input is the detailed information screen, and the output is the user's selection action. Specific actions include, for example, clicking on a "new cafe coupon" to check the detailed information.

[0686] Step 10:

[0687] When a user uses a coupon, they present their smartphone at the store and receive a discount by applying the coupon. The input is the user's act of presenting the coupon, and the output is the application of the discount. Specific actions include displaying the coupon on the smartphone and the store checking it.

[0688] 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.

[0689] 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.

[0690] 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.

[0691] [Third embodiment]

[0692] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0693] 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.

[0694] 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).

[0695] 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.

[0696] 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.

[0697] 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).

[0698] 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.

[0699] 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.

[0700] 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.

[0701] 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.

[0702] 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.

[0703] 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."

[0704] The present invention relates to a system that collects user activity data, analyzes and learns from that data, and provides optimal coupons and promotional information to individual users. Specific embodiments of this system are described below.

[0705] Server-side processing

[0706] The server first collects user activity data. Every time a user uses the payment system, transaction data is acquired in real time and stored in a database. For example, payment date and time, payment store, payment amount, etc. are collected.

[0707] The server then analyzes the collected data and learns the usage trends of each user. Here, machine learning algorithms are used to model user preferences and behavioral patterns based on past behavioral data. For example, if a user tends to frequently visit Chinese restaurants in a particular area (Minato Ward), this pattern can be learned.

[0708] The server then generates optimal coupons and promotional information for each user based on the learning results. The generated information is sent to the user's device as a push notification or message. For example, a user who likes Chinese food will receive a coupon for a nearby Chinese restaurant.

[0709] Terminal side processing

[0710] The device receives coupons and promotional information sent from the server and displays them in the form of a pop-up on the home screen. For example, a notification might appear saying, "20% off coupon for a nearby Chinese restaurant."

[0711] When a user clicks on the popup, the device displays additional information, such as the walking time to the store and the current traffic situation. The device can also use GPS to determine the user's current location and calculate the time it will take to get to the store.

[0712] User processing

[0713] Users can check the information displayed on their device and select the coupons or promotions they are interested in. For example, they can click on "Coupons for a new Chinese restaurant in Minato Ward" to view more information.

[0714] When a user wants to use a coupon, they can show their smartphone at the store and apply the coupon, allowing them to receive a discount.

[0715] Specific examples

[0716] For example, suppose a user visits a Chinese restaurant in Minato Ward four times a week. This user's activity data is collected by the server and automatically analyzed and learned from. The server generates a "20% off coupon for Chinese restaurants in Minato Ward" for this user and sends it to the user's device. The user can check this coupon on their smartphone and, if they decide to use it, present the coupon at the store to receive the discount.

[0717] In this way, the present invention realizes a system that can provide information tailored to the needs and preferences of each individual user, and provides a convenient and valuable service to users. The roles of the server, terminal, and user are clearly defined, and the entire system works seamlessly together to provide a highly personalized experience.

[0718] The processing flow will be explained below.

[0719] Step 1:

[0720] The server collects transaction data in real time when a user uses the payment system, specifically data such as the date and time of payment, store information, and payment amount, and stores the data in a database.

[0721] Step 2:

[0722] The server periodically analyzes the collected transaction data in batches, where it uses data analysis algorithms to analyze each user's activity data and extract usage trends.

[0723] Step 3:

[0724] The server uses machine learning algorithms to learn from the analyzed usage trends, for example, if a particular user frequently visits a particular type of store in a certain area, it will model that pattern.

[0725] Step 4:

[0726] The server then generates optimal coupons and promotional information for each user based on the learning results. The generated information is based on the user's past behavioral data and current interests.

[0727] Step 5:

[0728] The server then sends the generated coupons and promotional information to the user's device in the form of push notifications or messages, using a communication protocol to send the information quickly and securely.

[0729] Step 6:

[0730] The device receives coupons and promotional information sent from the server in the background, stores it in a local database, and then displays it in a pop-up format on the home screen at the appropriate time.

[0731] Step 7:

[0732] When users click on the pop-up, the device opens a screen with additional details, such as walking time to the store and real-time traffic conditions.

[0733] Step 8:

[0734] The device uses GPS to obtain the user's current location, and only with the user's permission, uses this location information to calculate and display the route and travel time to the store.

[0735] Step 9:

[0736] Users check the information displayed on their device and select the coupons and promotional information they are interested in. They check the details of the coupon they want to use and understand the applicable conditions.

[0737] Step 10:

[0738] The user presents the coupon at the store to receive the discount. The store will verify the coupon and apply the corresponding discount. The verification process is complete when the user receives the discount.

[0739] Example 1

[0740] 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."

[0741] Conventional systems have struggled to provide personalized services based on individual user preferences and behavioral patterns. They also lacked the means to provide users with information that would actually be useful to them at the right time. As a result, it was difficult to provide effective advertising and coupons that met user demand.

[0742] 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.

[0743] In this invention, the server includes means for collecting user activity data, means for saving the collected activity data in a database, means for analyzing the saved data and learning usage trends for each user, means for generating appropriate coupons and promotional information based on the user's usage trends, means for sending the generated information to the user's terminal, means for displaying the information on the user's terminal, and means for providing additional store information and congestion status based on information selected by the user. This makes it possible to provide optimal information at the appropriate time according to the user's preferences and behavioral patterns.

[0744] "User" refers to an individual user of the system.

[0745] "Activity data" refers to data related to the user's behavior, and specifically includes payment information, location information, and the like.

[0746] "Means of collection" refers to the hardware and software used to obtain activity data.

[0747] "Database" refers to the system or function for storing and managing collected data.

[0748] "Means for storage" refers to the function for storing collected activity data in a database.

[0749] "Means for analysis" refers to the function for analyzing user usage trends using collected data.

[0750] "Means of learning" refers to algorithms and functions for modeling user preferences and behavioral patterns based on the analysis results.

[0751] "Means for generating" refers to the function for creating coupons and promotional information suitable for users based on the learning results.

[0752] "Means for sending" refers to the function for sending the generated coupons and promotional information to the user's terminal.

[0753] "Terminal" refers to an electronic device used by a user to receive and display information.

[0754] "Display means" refers to the function for visually displaying coupons and promotional information on the terminal.

[0755] "Selected information" refers to coupons and promotional information selected by the user on the device.

[0756] "Additional store information" refers to detailed store information related to the selected information.

[0757] "Crowd status" refers to data showing the current level of congestion at the store.

[0758] "Location Information" refers to geographic data that indicates a user's current location.

[0759] "Means for calculating travel time" refers to a function for calculating travel time from the user's current location to the store.

[0760] This invention relates to a system that collects user activity data, analyzes and learns from that data, and provides optimal coupons and promotional information to each individual user. This system operates in cooperation with three parties: a server, a terminal, and a user.

[0761] Server-side processing

[0762] The server first uses the payment system's API to collect user activity data. Specifically, it obtains transaction data (payment date and time, payment store, payment amount, etc.) in real time when the user makes a payment and stores it in a database. The database is typically MySQL or MongoDB.

[0763] The server then analyzes the collected data, using machine learning algorithms such as Scikit-learn and TensorFlow to model user preferences and behavioral patterns based on past behavioral data. For example, if a user tends to frequently visit Chinese restaurants in a particular area (Minato Ward), the system will learn that pattern.

[0764] Based on the learning results, the server generates optimal coupons and promotional information for each user. The generated information is sent to the user's device as a push notification or message using FIREBASE Cloud Messaging (FCM). For example, a user who likes Chinese food will receive a coupon for a nearby Chinese restaurant.

[0765] Terminal side processing

[0766] The device receives coupons and promotional information sent from the server and displays them in the form of a pop-up on the home screen. For example, a notification might appear saying, "20% off coupon for a nearby Chinese restaurant."

[0767] When the user clicks on the popup, the device displays additional information, such as the walking time to the store and current traffic conditions using the Google Maps API. The device can also use GPS to determine the user's current location and calculate the time it will take to get to the store.

[0768] User processing

[0769] The user checks the information displayed on the device and selects the coupon or promotional information they are interested in. For example, they click on "Coupon for a new Chinese restaurant in Minato Ward" to check the details.

[0770] When a user wants to use a coupon, they can present their smartphone at the store and apply the coupon, allowing them to receive a discount.

[0771] Specific examples

[0772] For example, suppose a user visits a Chinese restaurant in Minato Ward four times a week. The user's activity data is collected by the server and automatically analyzed and learned from. The server generates a "20% off coupon for the Chinese restaurant in Minato Ward" for the user and sends it to the user's device. The user can check this coupon on their smartphone and, if they decide to use it, present the coupon at the store to receive the discount.

[0773] Example prompts for generative AI models

[0774] If a user visits a Chinese restaurant in Minato Ward four times a week, I want to create an algorithm that generates the most suitable coupons and promotional information for that user. What kind of machine learning method should I use based on past user data?

[0775] As described above, it is possible to provide information tailored to individual needs based on user activity data. This system clarifies the roles played by the server, device, and user, and achieves seamless cooperation, thereby providing a highly personalized experience.

[0776] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0777] Step 1:

[0778] The server collects user activity data. Specifically, when a user uses the payment system, payment information (payment date and time, payment store, payment amount, etc.) is obtained in real time via API. The input is the transaction data of the payment system, and the output is the collected activity data.

[0779] Step 2:

[0780] The server stores the collected data in a database. Specifically, it stores the acquired transaction data in a database such as MySQL or MongoDB. The input is the collected activity data, and the output is the data stored in the database.

[0781] Step 3:

[0782] The server analyzes the data and learns the trends of each user. Specifically, it uses a Python program to analyze the data with machine learning algorithms such as Scikit-learn and TensorFlow to model user preferences and behavioral patterns. The input is the activity data in the database, and the output is a model of the user's behavioral patterns as a result of learning.

[0783] Step 4:

[0784] The server generates optimal coupons and promotional information based on the learning results. Specifically, it uses the output of the machine learning model to apply a predictive algorithm to create optimal coupons and promotional information for each user. The input is a model of the user's behavioral patterns, and the output is the generated coupons and promotional information.

[0785] Step 5:

[0786] The server sends the generated information to the user's device. Specifically, it uses FIREBASE Cloud Messaging (FCM) to send the generated coupons and promotional information to the user's mobile device as push notifications. The input is the generated coupons and promotional information, and the output is the notification sent to the user's device.

[0787] Step 6:

[0788] The device notifies the user of the received information. Specifically, it uses the device's notification system to display a notification in pop-up format on the home screen. For example, it displays a message such as "20% off coupon for a nearby Chinese restaurant." The input is the received coupon or promotional information, and the output is the notification displayed on the home screen.

[0789] Step 7:

[0790] The user checks the notification and selects a coupon or promotional information. Specifically, the user clicks on the displayed notification and takes the action of checking detailed information. The input is the notification displayed on the home screen, and the output is the coupon or promotional information selected by the user.

[0791] Step 8:

[0792] The device displays detailed coupon information, the distance to the store, and the store's congestion status. Specifically, it uses the Google Maps API to calculate the walking time from the user's current location to the store, and also retrieves and displays store congestion status information from a database. The input is the coupon selected by the user and the device's location information, and the output is the store information displayed on the detailed information screen.

[0793] Step 9:

[0794] Users can receive a discount by using a coupon and presenting it at a store. Specifically, they present the coupon displayed on their smartphone at the store to receive the discount. The store confirms that the coupon has been applied by scanning a QR code or barcode. The input is the coupon presented by the user, and the output is the transaction in which the discount was received.

[0795] (Application example 1)

[0796] 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."

[0797] Today's consumers have a wide range of choices and require personalized information tailored to their preferences and behavioral patterns. However, existing systems face challenges in effectively analyzing user activity data and providing optimal coupons and promotional information to individual users. Furthermore, there are still insufficient means to provide this information at the right time and quickly display information that is valuable to users.

[0798] 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.

[0799] In this invention, the server includes means for collecting user activity data, means for analyzing the collected activity data and using a machine learning algorithm to learn usage trends for each user, means for generating appropriate coupons and promotional information based on the user's usage trends, means for transmitting the generated information to the user's terminal, means for displaying the information on the user's terminal, means for providing additional store information and congestion status based on information selected by the user, means for acquiring the user's location information and displaying a route to the store, means for generating a QR code or barcode and presenting it at the store when using a coupon, and means for transmitting a push notification including the generated coupon information to the user's terminal. This enables the provision of personalized information according to the preferences and behavioral patterns of each user, and allows coupons and promotional information valuable to the user to be provided promptly and at an appropriate time.

[0800] "User activity data" is a collection of information about a user's behavior, such as purchase history, transaction data, browsing history, and location information.

[0801] A "machine learning algorithm" is a mathematical model or computational method for finding patterns and making predictions based on collected data.

[0802] A "coupon" is a digital or physical certificate offering a discount or special offer on a specific product or service.

[0803] "Advertising information" refers to information such as messages, images, and texts intended to promote products or advertise services.

[0804] A "terminal" is a mobile device such as a smartphone or tablet that a user can easily carry and use.

[0805] A "push notification" is a real-time notification message sent from the server to the user's device.

[0806] "Location information" refers to information about a user's current location obtained using GPS, Wi-Fi, etc.

[0807] "Means for displaying routes" refers to a mechanism that provides a function for displaying routes from the user's current location to their destination as a map or guide.

[0808] A "QR code" is a two-dimensional barcode used to store coupon and link information.

[0809] A "barcode" is a one-dimensional readable code used to identify and manage products.

[0810] "Store information" is detailed information useful to users, such as the store's location, business hours, and current congestion status.

[0811] "Crowding status" is information that indicates the current number of users of a store or facility, waiting times, etc.

[0812] MODE FOR CARRYING OUT THE INVENTION

[0813] This invention relates to a system that collects user activity data, analyzes and learns from that data, and provides optimal coupons and promotional information to individual users. Specific embodiments of the system are described below.

[0814] Server-side processing

[0815] The server first collects user activity data. Every time a user uses the payment system, transaction data is acquired in real time and stored in a database. For example, information such as the payment date and time, the payment store, and the payment amount is collected. The user's location information is also collected using the GPS function. The server then analyzes the collected data and learns the usage trends of each user. Here, machine learning algorithms such as TensorFlow and Scikit-learn are used to model user preferences and behavioral patterns based on past behavioral data. For example, if a user tends to frequently visit Chinese restaurants in a particular area (e.g., a certain neighborhood), this pattern is learned. Based on the learning results, the server generates coupons and promotional information that are optimal for each user. The generated information is sent to the user's device as a push notification.

[0816] Terminal side processing

[0817] The device receives coupons and promotional information sent from the server and displays them as notifications on the home screen. For example, a "20% off coupon for a nearby Chinese restaurant" may be displayed. When the user clicks on the notification, the device displays additional information, such as the walking time to the store and the current congestion status. The device can also obtain the user's current location using GPS and display the estimated time to the store and route information using Google Maps APIs, etc. Furthermore, when using a coupon, a QR code or barcode can be generated and presented at the store.

[0818] User processing

[0819] Users can check the information displayed on their device and select the coupons or promotions they are interested in. For example, they can click on "Coupons for a Specific Chinese Restaurant" to view more information. If they want to use a coupon, they can present their smartphone at the store and apply the coupon, allowing them to receive a discount.

[0820] Specific examples

[0821] For example, suppose a user visits a Chinese restaurant four times a week. This user's activity data is collected by the server and automatically analyzed and learned from. The server generates a "20% off coupon for Chinese restaurants" for this user and sends it to the user's device. The user can check this coupon on their smartphone and, if they decide to use it, present the coupon at the restaurant to receive the discount.

[0822] Prompt Sentence Examples

[0823] An example prompt for a generative AI model is below:

[0824] "Please help us design a system that learns preferences based on user data and generates the most appropriate coupons for each individual. For example, we will create a process that generates a 20% off coupon for Chinese restaurants based on the frequency of visits to Chinese restaurants."

[0825] In this way, the present invention realizes a system that can provide information tailored to the needs and preferences of each individual user, and provides a service that is convenient and valuable to the user. The roles of the server, terminal, and user are clearly defined, and the entire system works seamlessly together to provide a highly personalized experience.

[0826] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0827] Step 1: Collecting user activity data

[0828] The server captures transaction data in real time each time a user uses the payment system and stores it in a database. Specifically, it collects information on the date and time of payment, the store where the payment was made, the payment amount, and the user's location. This allows consistent user activity data to be accumulated. The input is payment data and location information, and the output is the activity data stored in the database.

[0829] Step 2: Data analysis and training

[0830] The server analyzes the collected data and uses machine learning algorithms (e.g., TensorFlow and Scikit-learn) to learn the usage trends of each user. The input is activity data stored in the database, and the output is the learning results that model the user's preferences and behavioral patterns. Specifically, it identifies patterns of usage frequency and destinations, and analyzes that data to create a predictive model.

[0831] Step 3: Generate coupons and promotions

[0832] The server generates optimal coupons and promotional information for each user based on the learning results. The input is the learning results, and the output is the generated coupons and promotional information. Specifically, the type and content of coupons to be delivered to users is determined based on the inference results of the machine learning model.

[0833] Step 4: Send coupons and promotional information

[0834] The server sends the generated coupons and promotional information to the user's device as push notifications. The input is the generated coupons and promotional information, and the output is the notification sent to the device. Specifically, the notification message is sent via an HTTP request and displayed in real time on the user's device.

[0835] Step 5: View and select notifications

[0836] The device receives coupons and promotional information sent from the server and displays them in the form of notifications on the home screen. For example, a message such as "20% off coupon for Chinese restaurants" may be displayed. When the user clicks on the notification, more information is displayed. The input is the received notification data, and the output is the notification displayed on the home screen.

[0837] Step 6: Provide additional information

[0838] The device displays route information to the store and the current congestion status based on the information selected by the user. The input is the information the user clicks on the notification, and the output is the additional information displayed on the device. Specifically, it uses the Google Maps API to calculate and display the route to the store and the required time.

[0839] Step 7: Present and redeem the coupon

[0840] When a user wants to use a coupon, the terminal generates a QR code or barcode and presents it at the store. The input is the coupon information, and the output is the generated QR code or barcode. Specifically, the coupon information is converted into a readable code that can be scanned at the store.

[0841] This allows each processing step to be specifically linked, enabling the provision of fast, personalized information to users.

[0842] 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.

[0843] The present invention relates to a system that collects, analyzes, and learns from users' activity data and emotion data, and then provides optimal coupons and promotional information to each individual user. Specific embodiments of this system are described below.

[0844] Server-side processing

[0845] The server first collects user activity data. Every time a user uses the payment system, transaction data is acquired in real time and stored in a database. For example, payment date and time, store information, payment amount, etc. are collected.

[0846] The server then analyzes the collected data and learns the usage trends of each user. Here, machine learning algorithms are used to model user preferences and behavioral patterns based on past behavioral data. For example, if a user tends to frequently visit Chinese restaurants in a particular area (Minato Ward), this pattern can be learned.

[0847] The server also collects and analyzes the user's emotional data using an emotion engine. The emotion engine can recognize emotions from the user's voice, facial expressions, and text input. For example, it can analyze the text when the user types a message on their smartphone or the tone of their voice command to identify the user's current emotional state.

[0848] The server generates optimal coupons and promotional information for each user based on the learning results and emotional data. The generated information is based on the user's past behavioral data and current emotional state.

[0849] The server sends the generated coupons and promotional information to the user's device as a push notification or message. For example, when sending a coupon for a nearby Chinese restaurant to a user who likes Chinese food, the server attaches information about a restaurant where the user can relax based on the user's current emotional state (e.g., a desire to reduce stress).

[0850] Terminal side processing

[0851] The device receives coupons and promotional information sent from the server and displays them in a pop-up format on the home screen. For example, a "20% off coupon for a nearby Chinese restaurant" may be displayed along with additional information such as "A relaxing environment."

[0852] When the user clicks on the pop-up, the device opens a screen that provides additional information, such as walking time to the store, real-time traffic conditions, etc. Additionally, an emotion engine can analyze the user's voice and text inputs to update their emotional state in real time.

[0853] The device uses GPS to determine the user's current location and calculates the time it will take to get to the store, using location information only if the user gives permission.

[0854] User processing

[0855] Users can review the information displayed on their device and select the coupons and promotions they are interested in. For example, they can click on "Coupons for new Chinese restaurants in Minato Ward" to view more information, and then use the information provided by the emotion engine to select the most suitable restaurant.

[0856] When a user uses a coupon, they present their smartphone at the store and receive a discount by applying the coupon. The store will then check the coupon and apply the corresponding discount.

[0857] Specific examples

[0858] Let's say a user visits a Chinese restaurant in Minato Ward four times a week. The user's activity data is collected by the server and automatically analyzed and learned. Furthermore, if the user is in an emotional state that requires relaxation, the server generates a "20% off coupon that can be used at Chinese restaurants in Minato Ward" along with additional information such as "This restaurant has a relaxing environment" and sends it to the device. The user can check this coupon on their smartphone and present it at the restaurant to receive the discount.

[0859] As described above, this invention realizes a system that can provide information tailored to the needs and emotions of individual users, and provides convenient and valuable services to users. The roles of the server, terminal, and user are clearly defined, and the entire system works seamlessly together to provide a highly personalized experience.

[0860] The processing flow will be explained below.

[0861] Step 1:

[0862] The server collects transaction data in real time when a user uses the payment system, specifically data such as the date and time of payment, store information, and payment amount, and stores the data in a database.

[0863] Step 2:

[0864] The server periodically analyzes collected transaction data in batches, using data analysis algorithms to extract each user's behavioral patterns and usage trends.

[0865] Step 3:

[0866] The server uses machine learning algorithms to learn from the analyzed usage trend data, for example, if a particular user tends to frequently visit a particular type of store in a particular area, it models that pattern.

[0867] Step 4:

[0868] The server collects user emotion data using an emotion engine. The emotion engine recognizes emotions from the user's voice, facial expressions, and text input. For example, it analyzes text and voice commands when the user types a message on a smartphone.

[0869] Step 5:

[0870] The server analyzes the collected emotional data using an emotion engine to identify the user's emotional state and classify it into emotion categories, specifically, stress, joy, sadness, and relaxation.

[0871] Step 6:

[0872] The server generates optimal coupons and promotional information for each user based on the learning results and emotional data, taking into account the user's past behavioral data and current emotional state.

[0873] Step 7:

[0874] The server sends the generated coupons and promotional information to the user's device via push notification. For example, a "20% off coupon for a nearby Chinese restaurant" may be included along with additional information such as "a restaurant with a relaxing environment."

[0875] Step 8:

[0876] The device receives coupons and promotional information sent from the server in the background, stores it in a local database, and then displays it in a pop-up format on the home screen at the appropriate time.

[0877] Step 9:

[0878] When users click on the pop-up, the device opens a screen with additional details, such as walking time to the store, real-time traffic conditions, and a description of the relaxing environment.

[0879] Step 10:

[0880] The device uses GPS to obtain the user's current location, and only if the user gives permission does it use that information to calculate and display the route and travel time to the store.

[0881] Step 11:

[0882] Users can check the information displayed on their device and select the coupons or promotions they are interested in. For example, they can click on "Coupons for a new Chinese restaurant in Minato Ward" to view more information.

[0883] Step 12:

[0884] The user presents the coupon at the store to receive the discount. The store checks the coupon and applies the corresponding discount, allowing the user to receive the discount.

[0885] Example 2

[0886] 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."

[0887] Conventional coupon and promotional information systems have difficulty providing personalized information that takes into account each user's usage trends, and do not deliver appropriate information that reflects the user's emotional state. As a result, information of little value to users is often provided. Furthermore, the provision of real-time information such as the user's current location, travel time to the store, and congestion status is also insufficient. This has led to issues such as reduced convenience and satisfaction for users.

[0888] 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.

[0889] In this invention, the server includes means for collecting user activity data, means for analyzing the collected activity data and learning usage trends for each user, means for collecting and analyzing user emotion data from voice, facial expression, and text input, means for generating appropriate coupons and promotional information based on the user's usage trends and emotion data, means for transmitting the generated information to the user's terminal, means for displaying the information on the user's terminal, and means for providing additional store information and congestion status based on information selected by the user. This makes it possible to provide valuable information tailored to the user's needs and emotional state, thereby improving convenience and satisfaction.

[0890] "User activity data" refers to the behavioral history of a user when using a specific service or system, and includes, for example, payment date and time, payment amount, store information, etc.

[0891] "Means for collection" refers to the combination of hardware and software that the system uses to collect user activity data and emotional data.

[0892] "Means of analysis" refers to algorithms and software that analyze collected data to reveal users' usage trends and emotional states.

[0893] "Means of learning" refers to a method of generating a model using a machine learning algorithm based on user usage trends and emotional data.

[0894] "Emotional data" refers to data on the emotional state extracted from the user's voice, facial expression, text input, etc.

[0895] "Means of generation" refers to algorithms and systems that generate coupons and promotional information tailored to users based on the results of analysis and learning.

[0896] "Transmission means" refers to the communication means and network protocol for transmitting the generated coupons and promotional information to the user's terminal.

[0897] "Displaying means" refers to the display process and interface for visually presenting coupons and promotional information on the user's terminal.

[0898] "Additional store information and congestion status" refers to information such as the time required to reach the store and the current congestion status that is provided along with coupons and promotional information.

[0899] "Location Information" refers to information about a user's current location obtained by GPS or other means.

[0900] "Means for calculating travel time" refers to algorithms or software for calculating travel time from a user to a store based on location information.

[0901] "Permission-based location collection" refers to protocols and permission management systems for collecting location information with user consent.

[0902] This invention is a system that provides optimal coupons and promotional information to individual users by collecting, analyzing, and learning from user activity and emotion data. This system provides useful and valuable information to users through collaboration between the server, terminal, and user.

[0903] Server Processing

[0904] The server first collects user activity data. Specifically, when a user uses the payment system, transaction data such as payment date and time, store information, and payment amount are obtained in real time and stored in a central database. The server polls for data through the payment system's API and immediately stores any new transaction data it detects.

[0905] Next, the server uses an emotion engine to collect the user's emotional data from voice, facial expressions, and text input. The emotion engine determines the user's emotional state using methods such as voice recognition, facial expression analysis, and text analysis. Specific examples include using the Google Cloud Speech-to-Text API and natural language processing toolkits. The server obtains voice and text data from the smartphone app and sends it to the emotion engine to identify emotions.

[0906] The server then uses the collected activity and emotion data to perform machine learning to learn each user's behavioral patterns. This is done using the Python scikit-learn library. The data is fed into the machine learning model to identify each user's behavioral patterns.

[0907] The server then uses a generative algorithm to generate optimal coupons and promotional information for each user based on the learning results and emotion data. A TensorFlow-based generative model is used for this. The generated coupons and promotional information are then sent to the user's device via Google Firebase Cloud Messaging (FCM) or Apple Push Notification Service (APNS).

[0908] Terminal handling

[0909] The device receives coupons and promotional information sent from the server and displays them in a pop-up format on the home screen. The received push notification triggers a specific activity within the app, displaying the coupon information and additional information. When the user clicks on the pop-up, the device provides additional information such as walking time to the store and real-time congestion status.

[0910] For example, the device uses GPS data to obtain the current location, calculates and displays route guidance to the store using the Google Maps API, and obtains congestion information using the Firebase Realtime Database and displays it in real time.

[0911] User Action

[0912] Users can check the information displayed on their device and select coupons or promotional information that interest them. For example, they can click on "Coupons for a new Chinese restaurant in Minato Ward" to view more information. When using a coupon, users present their smartphone at the store and apply the coupon to receive a discount. Feedback information is also sent from within the app to the server and used for future analysis.

[0913] Specific examples

[0914] If a user visits a Chinese restaurant in Minato Ward four times a week, the server collects that activity data and automatically analyzes and learns from it. If the server determines that the user is in an emotional state that requires relaxation, it generates a 20% off coupon for Chinese restaurants in Minato Ward along with additional information such as "This restaurant has a relaxing environment" and sends it to the device. The user can then view the coupon on their smartphone and present it at the restaurant to receive the discount.

[0915] Prompt Sentence Examples

[0916] An example of a prompt to input to a generative AI model is as follows:

[0917] Generate customized coupon information based on user activity and sentiment data, and suggest messages based on the coupon type and user sentiment.

[0918] The above is a specific embodiment for carrying out the present invention. This system makes it possible to provide high-value-added information that meets the needs and emotional state of the user, thereby improving convenience and satisfaction.

[0919] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0920] Step 1:

[0921] The server collects user activity data.

[0922] Input: Transaction data obtained from the payment system (payment date and time, store information, payment amount).

[0923] Processing: Polls activity data through the payment system's API and stores new data in the database whenever it is detected.

[0924] Output: Activity data stored in a database.

[0925] Specific operation: The server periodically sends requests to the payment system's API to obtain new transactions and store them in the database.

[0926] Step 2:

[0927] The server collects emotional data such as voice, facial expressions, and text input.

[0928] Input: Voice data, facial expression data, and text data obtained from a smartphone app.

[0929] Processing: An emotion engine is used to perform speech recognition, facial expression analysis, and text analysis to identify emotional states.

[0930] Output: Identified emotion data.

[0931] Specific operation: Receives voice and text data sent from a smartphone and analyzes sentiment using the Google Cloud Speech-to-Text API and natural language processing toolkit.

[0932] Step 3:

[0933] The server analyzes the collected activity and emotion data to learn each user's usage trends.

[0934] Input: Activity and emotion data stored in a database.

[0935] Processing: We use machine learning algorithms to model your usage habits and behavioral patterns.

[0936] Output: Learned behavioral pattern model.

[0937] Specific operation: Using Python's scikit-learn library, data is input into a learning model and usage trends are analyzed.

[0938] Step 4:

[0939] The server generates coupons and promotional information based on the learning results and emotion data.

[0940] Input: Learned behavioral pattern model and current emotion data.

[0941] Processing: A generation algorithm is used to generate personalized coupons and promotional information.

[0942] Output: Generated coupons and promotions.

[0943] Specific operation: Learning results and emotion data are input into a generative model using TensorFlow to generate individually customized coupon information.

[0944] Step 5:

[0945] The server transmits the generated coupons and advertising information to the user's terminal.

[0946] Input: Generated coupon or promotion information.

[0947] Processing: Sending information to the terminal using a communication protocol.

[0948] Output: Coupons and promotional information sent to the user's device.

[0949] Specific operation: Sends push notifications via Google Firebase Cloud Messaging (FCM) or Apple Push Notification Service (APNS).

[0950] Step 6:

[0951] The terminal displays the received coupons and promotional information.

[0952] Input: Coupons and promotional information received from the server.

[0953] Action: Trigger a notification to display information.

[0954] Output: Coupons and promotional information displayed on the device screen.

[0955] Specific behavior: The device will trigger a specific activity within the app and display information in response to the received push notification.

[0956] Step 7:

[0957] The terminal provides additional store information and crowding status.

[0958] Input: Coupons and promotions selected by the user. GPS data of current location.

[0959] Processing: Obtain any additional information needed and perform calculations.

[0960] Output: Additional information provided to the user (e.g., travel time to the store, how busy it is, etc.).

[0961] Specific operation: Calculates route guidance to the store using the Google Maps API, and obtains and displays congestion information using the Firebase Realtime Database.

[0962] Step 8:

[0963] Users take advantage of coupons, promotions and provide feedback.

[0964] Input: Coupons and promotional information displayed on the device.

[0965] Action: Present a coupon to receive a discount or submit feedback.

[0966] Output: Coupons used and feedback data sent to the server.

[0967] How it works: The user displays the coupon on their smartphone and presents it at the store. Feedback is sent from within the app to the server.

[0968] (Application example 2)

[0969] 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."

[0970] In recent years, there has been a demand for personalized and effective advertising. Existing systems only provide coupons and promotional information based on user activity data, but do not take into account the user's emotional state. As a result, it is difficult to provide appropriate information that is tailored to the user's current situation.

[0971] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user activity data, means for analyzing the collected activity data and learning usage trends for each user, means for collecting and analyzing user emotion data, means for generating advertisements related to the user's emotional state based on the emotion data, and means for generating advertisements based on the user's profile using a generative AI model. This makes it possible to provide more appropriate and effective advertisements based on the user's emotional state and past behavioral data.

[0972] "User activity data" refers to data that reflects a user's daily behavior, including transaction data such as payment date and time, store information, and payment amount.

[0973] "Means of collection" refers to the technical mechanisms and methods for acquiring user activity data and emotional data in real time and storing it in a database.

[0974] "Means of analysis" refers to algorithms and software that analyze collected activity data and learn usage trends for each user.

[0975] "Means of learning" refers to methods and techniques that use machine learning models to model user preferences and behavioral patterns based on past behavioral data.

[0976] "Emotional data" is information about a user's emotional state as recognized from their voice, facial expressions, and text input.

[0977] "Means for collecting and analyzing emotional data" refers to technologies and devices for recognizing and analyzing a user's emotions from voice, facial expressions, and text input.

[0978] The "means for generating" is an algorithm or system that constructs and generates optimal coupons and promotional information based on the learning results and emotional data.

[0979] A "generative AI model" is an artificial intelligence model that is trained on large datasets to generate optimal ads based on user profiles and behavioral patterns.

[0980] A "prompt sentence" is a text-based input sentence used to give specific instructions or requests to a generative AI model.

[0981] "Display means" refers to the technology or screen interface for visually displaying the generated coupon or promotional information on the user's device.

[0982] "Means for providing" refers to a system or method for providing additional store information, congestion status, etc., depending on the information selected by the user.

[0983] "Location information" refers to data about a user's current location obtained using GPS or other means.

[0984] The present invention relates to a system that collects, analyzes, and learns from users' activity data and emotion data, and then provides optimal coupons and promotional information to each individual user. Specific embodiments of this system are described below.

[0985] Server-side processing

[0986] The server first collects user activity data. For example, every time a user uses the payment system, the server obtains transaction data (payment date and time, store information, payment amount, etc.) in real time and stores it in a database.

[0987] The server then analyzes the collected data and learns the usage trends of each user using machine learning algorithms (e.g., libraries such as TensorFlow and Scikit-learn), which model user preferences and behavioral patterns based on past behavioral data.

[0988] The server then uses an emotion engine (e.g., the EmotionRecognition library) to collect and analyze emotion data. It recognizes emotions from the user's voice, facial expressions, and text input to identify their current emotional state. This emotion data is then analyzed by an algorithm to understand each user's emotional state in real time.

[0989] The server generates optimal coupons and promotional information for each user based on the learning results and emotional data. A generative AI model is used for generation, and specific advertisements are generated by providing a prompt. An example of a prompt might be, "We know that the user's emotional state is 'stressed,' and that their preference is 'cafes' based on past behavioral data. Please generate promotional information for relaxing cafes."

[0990] The generated coupons and promotional information are sent to the user's device as push notifications or messages. The server also provides information on nearby stores and their current traffic situation based on the user's current location.

[0991] Terminal side processing

[0992] The device receives coupons and promotional information sent from the server and displays them in a pop-up format on the home screen. For example, a "20% off coupon for a nearby cafe" may be displayed along with additional information such as "A relaxing environment."

[0993] When the user clicks on the pop-up, the device opens a screen that provides additional information, such as walking time to the store and real-time traffic conditions. The emotion engine also analyzes the user's voice and text inputs to update the user's emotional state in real time. The device also uses GPS to determine the user's current location and calculates the estimated time it will take to get to the store. This location information is only used if the user grants permission.

[0994] User processing

[0995] Users can check the information displayed on their device and select coupons or promotional information that they are interested in. For example, they can click on "New Cafe Coupons" to check detailed information and select the most suitable store based on the information provided by the emotion engine. When using a coupon, they can present their smartphone at the store and apply the coupon to receive a discount.

[0996] Such a system will enable the provision of information tailored to the needs and feelings of each individual user, providing a convenient and valuable service to users.

[0997] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0998] Step 1:

[0999] The server collects user activity data (payment date and time, store information, payment amount, etc.). This data is acquired in real time via the payment system and stored in a database. The input is user transaction data, which is saved in the database to generate activity data.

[1000] Step 2:

[1001] The server analyzes the collected activity data. This analysis uses a machine learning algorithm to learn the usage trends of each user. The input is the activity data collected in step 1, and the output is data that models each user's behavioral patterns and preferences. Specific operations include the algorithm analyzing past behavioral data and extracting each user's behavioral patterns.

[1002] Step 3:

[1003] The server collects and analyzes the user's emotional data. It uses an emotion engine (such as the EmotionRecognition library) to recognize emotions from the user's voice, facial expressions, and text input. The input for this process is the user's voice, facial expressions, and text data, and the output is analyzed emotional state data. Specifically, the emotion engine identifies emotions from voice and facial expressions and records that information in a database.

[1004] Step 4:

[1005] The server uses the generative AI model to generate optimal coupons and promotional information based on the learning results and emotional data. This process involves inputting prompt text into the generative AI model to generate specific advertising copy. The input is the learning results and emotional data, and the output is the optimal coupon or promotional information for the user. As a specific example of how this works, an example of a prompt text for the generative AI model is, "We know that the user's emotional state is 'stressed,' and that their preference is 'cafes' based on past behavioral data. Please generate promotional information for relaxing cafes."

[1006] Step 5:

[1007] The server sends the generated coupons and promotional information to the user's device. The input is the advertising information generated in step 4, and the output is the sending of the advertising information to the user's device. Specifically, the information is sent using push notifications or message functions.

[1008] Step 6:

[1009] The device receives coupons and promotional information sent from the server and displays them in a pop-up format on the home screen. The input is advertising information from the server, and the output is the display on the device. Specifically, information such as "20% off coupon for a nearby cafe" and "relaxing environment" is displayed.

[1010] Step 7:

[1011] When the user clicks on the pop-up, the device opens a screen that provides additional information. The input is the user's click, and the output is the display of a detailed information screen. Specific actions include displaying the walking time to the store and real-time congestion information.

[1012] Step 8:

[1013] The device uses an emotion engine to analyze the user's voice and text input and update the emotional state in real time. The input is the user's voice and text data, and the output is updated emotional state data. Specific operations include optimizing the next advertisement or information based on the analyzed emotional information.

[1014] Step 9:

[1015] The user checks the information displayed on the device and selects coupons or promotional information that interests them. The input is the detailed information screen, and the output is the user's selection action. Specific actions include, for example, clicking on a "new cafe coupon" to check the detailed information.

[1016] Step 10:

[1017] When a user uses a coupon, they present their smartphone at the store and receive a discount by applying the coupon. The input is the user's act of presenting the coupon, and the output is the application of the discount. Specific actions include displaying the coupon on the smartphone and the store checking it.

[1018] 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.

[1019] 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.

[1020] 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.

[1021] [Fourth embodiment]

[1022] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1023] 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.

[1024] 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).

[1025] 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.

[1026] 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.

[1027] 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).

[1028] 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.

[1029] 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.

[1030] 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.

[1031] 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.

[1032] 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.

[1033] 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.

[1034] 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."

[1035] The present invention relates to a system that collects user activity data, analyzes and learns from that data, and provides optimal coupons and promotional information to individual users. Specific embodiments of this system are described below.

[1036] Server-side processing

[1037] The server first collects user activity data. Every time a user uses the payment system, transaction data is acquired in real time and stored in a database. For example, payment date and time, payment store, payment amount, etc. are collected.

[1038] The server then analyzes the collected data and learns the usage trends of each user. Here, machine learning algorithms are used to model user preferences and behavioral patterns based on past behavioral data. For example, if a user tends to frequently visit Chinese restaurants in a particular area (Minato Ward), this pattern can be learned.

[1039] The server then generates optimal coupons and promotional information for each user based on the learning results. The generated information is sent to the user's device as a push notification or message. For example, a user who likes Chinese food will receive a coupon for a nearby Chinese restaurant.

[1040] Terminal side processing

[1041] The device receives coupons and promotional information sent from the server and displays them in the form of a pop-up on the home screen. For example, a notification might appear saying, "20% off coupon for a nearby Chinese restaurant."

[1042] When a user clicks on the popup, the device displays additional information, such as the walking time to the store and the current traffic situation. The device can also use GPS to determine the user's current location and calculate the time it will take to get to the store.

[1043] User processing

[1044] Users can check the information displayed on their device and select the coupons or promotions they are interested in. For example, they can click on "Coupons for a new Chinese restaurant in Minato Ward" to view more information.

[1045] When a user wants to use a coupon, they can show their smartphone at the store and apply the coupon, allowing them to receive a discount.

[1046] Specific examples

[1047] For example, suppose a user visits a Chinese restaurant in Minato Ward four times a week. This user's activity data is collected by the server and automatically analyzed and learned from. The server generates a "20% off coupon for Chinese restaurants in Minato Ward" for this user and sends it to the user's device. The user can check this coupon on their smartphone and, if they decide to use it, present the coupon at the store to receive the discount.

[1048] In this way, the present invention realizes a system that can provide information tailored to the needs and preferences of each individual user, and provides a convenient and valuable service to users. The roles of the server, terminal, and user are clearly defined, and the entire system works seamlessly together to provide a highly personalized experience.

[1049] The processing flow will be explained below.

[1050] Step 1:

[1051] The server collects transaction data in real time when a user uses the payment system, specifically data such as the date and time of payment, store information, and payment amount, and stores the data in a database.

[1052] Step 2:

[1053] The server periodically analyzes the collected transaction data in batches, where it uses data analysis algorithms to analyze each user's activity data and extract usage trends.

[1054] Step 3:

[1055] The server uses machine learning algorithms to learn from the analyzed usage trends, for example, if a particular user frequently visits a particular type of store in a certain area, it will model that pattern.

[1056] Step 4:

[1057] The server then generates optimal coupons and promotional information for each user based on the learning results. The generated information is based on the user's past behavioral data and current interests.

[1058] Step 5:

[1059] The server then sends the generated coupons and promotional information to the user's device in the form of push notifications or messages, using a communication protocol to send the information quickly and securely.

[1060] Step 6:

[1061] The device receives coupons and promotional information sent from the server in the background, stores it in a local database, and then displays it in a pop-up format on the home screen at the appropriate time.

[1062] Step 7:

[1063] When users click on the pop-up, the device opens a screen with additional details, such as walking time to the store and real-time traffic conditions.

[1064] Step 8:

[1065] The device uses GPS to obtain the user's current location, and only with the user's permission, uses this location information to calculate and display the route and travel time to the store.

[1066] Step 9:

[1067] Users check the information displayed on their device and select the coupons and promotional information they are interested in. They check the details of the coupon they want to use and understand the applicable conditions.

[1068] Step 10:

[1069] The user presents the coupon at the store to receive the discount. The store will verify the coupon and apply the corresponding discount. The verification process is complete when the user receives the discount.

[1070] Example 1

[1071] 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."

[1072] Conventional systems have struggled to provide personalized services based on individual user preferences and behavioral patterns. They also lacked the means to provide users with information that would actually be useful to them at the right time. As a result, it was difficult to provide effective advertising and coupons that met user demand.

[1073] 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.

[1074] In this invention, the server includes means for collecting user activity data, means for saving the collected activity data in a database, means for analyzing the saved data and learning usage trends for each user, means for generating appropriate coupons and promotional information based on the user's usage trends, means for sending the generated information to the user's terminal, means for displaying the information on the user's terminal, and means for providing additional store information and congestion status based on information selected by the user. This makes it possible to provide optimal information at the appropriate time according to the user's preferences and behavioral patterns.

[1075] "User" refers to an individual user of the system.

[1076] "Activity data" refers to data related to the user's behavior, and specifically includes payment information, location information, and the like.

[1077] "Means of collection" refers to the hardware and software used to obtain activity data.

[1078] "Database" refers to the system or function for storing and managing collected data.

[1079] "Means for storage" refers to the function for storing collected activity data in a database.

[1080] "Means for analysis" refers to the function for analyzing user usage trends using collected data.

[1081] "Means of learning" refers to algorithms and functions for modeling user preferences and behavioral patterns based on the analysis results.

[1082] "Means for generating" refers to the function for creating coupons and promotional information suitable for users based on the learning results.

[1083] "Means for sending" refers to the function for sending the generated coupons and promotional information to the user's terminal.

[1084] "Terminal" refers to an electronic device used by a user to receive and display information.

[1085] "Display means" refers to the function for visually displaying coupons and promotional information on the terminal.

[1086] "Selected information" refers to coupons and promotional information selected by the user on the device.

[1087] "Additional store information" refers to detailed store information related to the selected information.

[1088] "Crowd status" refers to data showing the current level of congestion at the store.

[1089] "Location Information" refers to geographic data that indicates a user's current location.

[1090] "Means for calculating travel time" refers to a function for calculating travel time from the user's current location to the store.

[1091] This invention relates to a system that collects user activity data, analyzes and learns from that data, and provides optimal coupons and promotional information to each individual user. This system operates in cooperation with three parties: a server, a terminal, and a user.

[1092] Server-side processing

[1093] The server first uses the payment system's API to collect user activity data. Specifically, it obtains transaction data (payment date and time, payment store, payment amount, etc.) in real time when the user makes a payment and stores it in a database. The database is typically MySQL or MongoDB.

[1094] The server then analyzes the collected data, using machine learning algorithms such as Scikit-learn and TensorFlow to model user preferences and behavioral patterns based on past behavioral data. For example, if a user tends to frequently visit Chinese restaurants in a particular area (Minato Ward), the system will learn that pattern.

[1095] Based on the learning results, the server generates optimal coupons and promotional information for each user. The generated information is sent to the user's device as a push notification or message using FIREBASE Cloud Messaging (FCM). For example, a user who likes Chinese food will receive a coupon for a nearby Chinese restaurant.

[1096] Terminal side processing

[1097] The device receives coupons and promotional information sent from the server and displays them in the form of a pop-up on the home screen. For example, a notification might appear saying, "20% off coupon for a nearby Chinese restaurant."

[1098] When the user clicks on the popup, the device displays additional information, such as the walking time to the store and current traffic conditions using the Google Maps API. The device can also use GPS to determine the user's current location and calculate the time it will take to get to the store.

[1099] User processing

[1100] The user checks the information displayed on the device and selects the coupon or promotional information they are interested in. For example, they click on "Coupon for a new Chinese restaurant in Minato Ward" to check the details.

[1101] When a user wants to use a coupon, they can present their smartphone at the store and apply the coupon, allowing them to receive a discount.

[1102] Specific examples

[1103] For example, suppose a user visits a Chinese restaurant in Minato Ward four times a week. The user's activity data is collected by the server and automatically analyzed and learned from. The server generates a "20% off coupon for the Chinese restaurant in Minato Ward" for the user and sends it to the user's device. The user can check this coupon on their smartphone and, if they decide to use it, present the coupon at the store to receive the discount.

[1104] Example prompts for generative AI models

[1105] If a user visits a Chinese restaurant in Minato Ward four times a week, I want to create an algorithm that generates the most suitable coupons and promotional information for that user. What kind of machine learning method should I use based on past user data?

[1106] As described above, it is possible to provide information tailored to individual needs based on user activity data. This system clarifies the roles played by the server, device, and user, and achieves seamless cooperation, thereby providing a highly personalized experience.

[1107] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1108] Step 1:

[1109] The server collects user activity data. Specifically, when a user uses the payment system, payment information (payment date and time, payment store, payment amount, etc.) is obtained in real time via API. The input is the transaction data of the payment system, and the output is the collected activity data.

[1110] Step 2:

[1111] The server stores the collected data in a database. Specifically, it stores the acquired transaction data in a database such as MySQL or MongoDB. The input is the collected activity data, and the output is the data stored in the database.

[1112] Step 3:

[1113] The server analyzes the data and learns the trends of each user. Specifically, it uses a Python program to analyze the data with machine learning algorithms such as Scikit-learn and TensorFlow to model user preferences and behavioral patterns. The input is the activity data in the database, and the output is a model of the user's behavioral patterns as a result of learning.

[1114] Step 4:

[1115] The server generates optimal coupons and promotional information based on the learning results. Specifically, it uses the output of the machine learning model to apply a predictive algorithm to create optimal coupons and promotional information for each user. The input is a model of the user's behavioral patterns, and the output is the generated coupons and promotional information.

[1116] Step 5:

[1117] The server sends the generated information to the user's device. Specifically, it uses FIREBASE Cloud Messaging (FCM) to send the generated coupons and promotional information to the user's mobile device as push notifications. The input is the generated coupons and promotional information, and the output is the notification sent to the user's device.

[1118] Step 6:

[1119] The device notifies the user of the received information. Specifically, it uses the device's notification system to display a notification in pop-up format on the home screen. For example, it displays a message such as "20% off coupon for a nearby Chinese restaurant." The input is the received coupon or promotional information, and the output is the notification displayed on the home screen.

[1120] Step 7:

[1121] The user checks the notification and selects a coupon or promotional information. Specifically, the user clicks on the displayed notification and takes the action of checking detailed information. The input is the notification displayed on the home screen, and the output is the coupon or promotional information selected by the user.

[1122] Step 8:

[1123] The device displays detailed coupon information, the distance to the store, and the store's congestion status. Specifically, it uses the Google Maps API to calculate the walking time from the user's current location to the store, and also retrieves and displays store congestion status information from a database. The input is the coupon selected by the user and the device's location information, and the output is the store information displayed on the detailed information screen.

[1124] Step 9:

[1125] Users can receive a discount by using a coupon and presenting it at a store. Specifically, they present the coupon displayed on their smartphone at the store to receive the discount. The store confirms that the coupon has been applied by scanning a QR code or barcode. The input is the coupon presented by the user, and the output is the transaction in which the discount was received.

[1126] (Application example 1)

[1127] 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."

[1128] Today's consumers have a wide range of choices and require personalized information tailored to their preferences and behavioral patterns. However, existing systems face challenges in effectively analyzing user activity data and providing optimal coupons and promotional information to individual users. Furthermore, there are still insufficient means to provide this information at the right time and quickly display information that is valuable to users.

[1129] 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.

[1130] In this invention, the server includes means for collecting user activity data, means for analyzing the collected activity data and using a machine learning algorithm to learn usage trends for each user, means for generating appropriate coupons and promotional information based on the user's usage trends, means for transmitting the generated information to the user's terminal, means for displaying the information on the user's terminal, means for providing additional store information and congestion status based on information selected by the user, means for acquiring the user's location information and displaying a route to the store, means for generating a QR code or barcode and presenting it at the store when using a coupon, and means for transmitting a push notification including the generated coupon information to the user's terminal. This enables the provision of personalized information according to the preferences and behavioral patterns of each user, and allows coupons and promotional information valuable to the user to be provided promptly and at an appropriate time.

[1131] "User activity data" is a collection of information about a user's behavior, such as purchase history, transaction data, browsing history, and location information.

[1132] A "machine learning algorithm" is a mathematical model or computational method for finding patterns and making predictions based on collected data.

[1133] A "coupon" is a digital or physical certificate offering a discount or special offer on a specific product or service.

[1134] "Advertising information" refers to information such as messages, images, and texts intended to promote products or advertise services.

[1135] A "terminal" is a mobile device such as a smartphone or tablet that a user can easily carry and use.

[1136] A "push notification" is a real-time notification message sent from the server to the user's device.

[1137] "Location information" refers to information about a user's current location obtained using GPS, Wi-Fi, etc.

[1138] "Means for displaying routes" refers to a mechanism that provides a function for displaying routes from the user's current location to their destination as a map or guide.

[1139] A "QR code" is a two-dimensional barcode used to store coupon and link information.

[1140] A "barcode" is a one-dimensional readable code used to identify and manage products.

[1141] "Store information" is detailed information useful to users, such as the store's location, business hours, and current congestion status.

[1142] "Crowding status" is information that indicates the current number of users of a store or facility, waiting times, etc.

[1143] MODE FOR CARRYING OUT THE INVENTION

[1144] This invention relates to a system that collects user activity data, analyzes and learns from that data, and provides optimal coupons and promotional information to individual users. Specific embodiments of the system are described below.

[1145] Server-side processing

[1146] The server first collects user activity data. Every time a user uses the payment system, transaction data is acquired in real time and stored in a database. For example, information such as the payment date and time, the payment store, and the payment amount is collected. The user's location information is also collected using the GPS function. The server then analyzes the collected data and learns the usage trends of each user. Here, machine learning algorithms such as TensorFlow and Scikit-learn are used to model user preferences and behavioral patterns based on past behavioral data. For example, if a user tends to frequently visit Chinese restaurants in a particular area (e.g., a certain neighborhood), this pattern is learned. Based on the learning results, the server generates coupons and promotional information that are optimal for each user. The generated information is sent to the user's device as a push notification.

[1147] Terminal side processing

[1148] The device receives coupons and promotional information sent from the server and displays them as notifications on the home screen. For example, a "20% off coupon for a nearby Chinese restaurant" may be displayed. When the user clicks on the notification, the device displays additional information, such as the walking time to the store and the current congestion status. The device can also obtain the user's current location using GPS and display the estimated time to the store and route information using Google Maps APIs, etc. Furthermore, when using a coupon, a QR code or barcode can be generated and presented at the store.

[1149] User processing

[1150] Users can check the information displayed on their device and select the coupons or promotions they are interested in. For example, they can click on "Coupons for a Specific Chinese Restaurant" to view more information. If they want to use a coupon, they can present their smartphone at the store and apply the coupon, allowing them to receive a discount.

[1151] Specific examples

[1152] For example, suppose a user visits a Chinese restaurant four times a week. This user's activity data is collected by the server and automatically analyzed and learned from. The server generates a "20% off coupon for Chinese restaurants" for this user and sends it to the user's device. The user can check this coupon on their smartphone and, if they decide to use it, present the coupon at the restaurant to receive the discount.

[1153] Prompt Sentence Examples

[1154] An example prompt for a generative AI model is below:

[1155] "Please help us design a system that learns preferences based on user data and generates the most appropriate coupons for each individual. For example, we will create a process that generates a 20% off coupon for Chinese restaurants based on the frequency of visits to Chinese restaurants."

[1156] In this way, the present invention realizes a system that can provide information tailored to the needs and preferences of each individual user, and provides a service that is convenient and valuable to the user. The roles of the server, terminal, and user are clearly defined, and the entire system works seamlessly together to provide a highly personalized experience.

[1157] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1158] Step 1: Collecting user activity data

[1159] The server captures transaction data in real time each time a user uses the payment system and stores it in a database. Specifically, it collects information on the date and time of payment, the store where the payment was made, the payment amount, and the user's location. This allows consistent user activity data to be accumulated. The input is payment data and location information, and the output is the activity data stored in the database.

[1160] Step 2: Data analysis and training

[1161] The server analyzes the collected data and uses machine learning algorithms (e.g., TensorFlow and Scikit-learn) to learn the usage trends of each user. The input is activity data stored in the database, and the output is the learning results that model the user's preferences and behavioral patterns. Specifically, it identifies patterns of usage frequency and destinations, and analyzes that data to create a predictive model.

[1162] Step 3: Generate coupons and promotions

[1163] The server generates optimal coupons and promotional information for each user based on the learning results. The input is the learning results, and the output is the generated coupons and promotional information. Specifically, the type and content of coupons to be delivered to users is determined based on the inference results of the machine learning model.

[1164] Step 4: Send coupons and promotional information

[1165] The server sends the generated coupons and promotional information to the user's device as push notifications. The input is the generated coupons and promotional information, and the output is the notification sent to the device. Specifically, the notification message is sent via an HTTP request and displayed in real time on the user's device.

[1166] Step 5: View and select notifications

[1167] The device receives coupons and promotional information sent from the server and displays them in the form of notifications on the home screen. For example, a message such as "20% off coupon for Chinese restaurants" may be displayed. When the user clicks on the notification, more information is displayed. The input is the received notification data, and the output is the notification displayed on the home screen.

[1168] Step 6: Provide additional information

[1169] The device displays route information to the store and the current congestion status based on the information selected by the user. The input is the information the user clicks on the notification, and the output is the additional information displayed on the device. Specifically, it uses the Google Maps API to calculate and display the route to the store and the required time.

[1170] Step 7: Present and redeem the coupon

[1171] When a user wants to use a coupon, the terminal generates a QR code or barcode and presents it at the store. The input is the coupon information, and the output is the generated QR code or barcode. Specifically, the coupon information is converted into a readable code that can be scanned at the store.

[1172] This allows each processing step to be specifically linked, enabling the provision of fast, personalized information to users.

[1173] 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.

[1174] The present invention relates to a system that collects, analyzes, and learns from users' activity data and emotion data, and then provides optimal coupons and promotional information to each individual user. Specific embodiments of this system are described below.

[1175] Server-side processing

[1176] The server first collects user activity data. Every time a user uses the payment system, transaction data is acquired in real time and stored in a database. For example, payment date and time, store information, payment amount, etc. are collected.

[1177] The server then analyzes the collected data and learns the usage trends of each user. Here, machine learning algorithms are used to model user preferences and behavioral patterns based on past behavioral data. For example, if a user tends to frequently visit Chinese restaurants in a particular area (Minato Ward), this pattern can be learned.

[1178] The server also collects and analyzes the user's emotional data using an emotion engine. The emotion engine can recognize emotions from the user's voice, facial expressions, and text input. For example, it can analyze the text when the user types a message on their smartphone or the tone of their voice command to identify the user's current emotional state.

[1179] The server generates optimal coupons and promotional information for each user based on the learning results and emotional data. The generated information is based on the user's past behavioral data and current emotional state.

[1180] The server sends the generated coupons and promotional information to the user's device as a push notification or message. For example, when sending a coupon for a nearby Chinese restaurant to a user who likes Chinese food, the server attaches information about a restaurant where the user can relax based on the user's current emotional state (e.g., a desire to reduce stress).

[1181] Terminal side processing

[1182] The device receives coupons and promotional information sent from the server and displays them in a pop-up format on the home screen. For example, a "20% off coupon for a nearby Chinese restaurant" may be displayed along with additional information such as "A relaxing environment."

[1183] When the user clicks on the pop-up, the device opens a screen that provides additional information, such as walking time to the store, real-time traffic conditions, etc. Additionally, an emotion engine can analyze the user's voice and text inputs to update their emotional state in real time.

[1184] The device uses GPS to determine the user's current location and calculates the time it will take to get to the store, using location information only if the user gives permission.

[1185] User processing

[1186] Users can review the information displayed on their device and select the coupons and promotions they are interested in. For example, they can click on "Coupons for new Chinese restaurants in Minato Ward" to view more information, and then use the information provided by the emotion engine to select the most suitable restaurant.

[1187] When a user uses a coupon, they present their smartphone at the store and receive a discount by applying the coupon. The store will then check the coupon and apply the corresponding discount.

[1188] Specific examples

[1189] Let's say a user visits a Chinese restaurant in Minato Ward four times a week. The user's activity data is collected by the server and automatically analyzed and learned. Furthermore, if the user is in an emotional state that requires relaxation, the server generates a "20% off coupon that can be used at Chinese restaurants in Minato Ward" along with additional information such as "This restaurant has a relaxing environment" and sends it to the device. The user can check this coupon on their smartphone and present it at the restaurant to receive the discount.

[1190] As described above, this invention realizes a system that can provide information tailored to the needs and emotions of individual users, and provides convenient and valuable services to users. The roles of the server, terminal, and user are clearly defined, and the entire system works seamlessly together to provide a highly personalized experience.

[1191] The processing flow will be explained below.

[1192] Step 1:

[1193] The server collects transaction data in real time when a user uses the payment system, specifically data such as the date and time of payment, store information, and payment amount, and stores the data in a database.

[1194] Step 2:

[1195] The server periodically analyzes collected transaction data in batches, using data analysis algorithms to extract each user's behavioral patterns and usage trends.

[1196] Step 3:

[1197] The server uses machine learning algorithms to learn from the analyzed usage trend data, for example, if a particular user tends to frequently visit a particular type of store in a particular area, it models that pattern.

[1198] Step 4:

[1199] The server collects user emotion data using an emotion engine. The emotion engine recognizes emotions from the user's voice, facial expressions, and text input. For example, it analyzes text and voice commands when the user types a message on a smartphone.

[1200] Step 5:

[1201] The server analyzes the collected emotional data using an emotion engine to identify the user's emotional state and classify it into emotion categories, specifically, stress, joy, sadness, and relaxation.

[1202] Step 6:

[1203] The server generates optimal coupons and promotional information for each user based on the learning results and emotional data, taking into account the user's past behavioral data and current emotional state.

[1204] Step 7:

[1205] The server sends the generated coupons and promotional information to the user's device via push notification. For example, a "20% off coupon for a nearby Chinese restaurant" may be included along with additional information such as "a restaurant with a relaxing environment."

[1206] Step 8:

[1207] The device receives coupons and promotional information sent from the server in the background, stores it in a local database, and then displays it in a pop-up format on the home screen at the appropriate time.

[1208] Step 9:

[1209] When users click on the pop-up, the device opens a screen with additional details, such as walking time to the store, real-time traffic conditions, and a description of the relaxing environment.

[1210] Step 10:

[1211] The device uses GPS to obtain the user's current location, and only if the user gives permission does it use that information to calculate and display the route and travel time to the store.

[1212] Step 11:

[1213] Users can check the information displayed on their device and select the coupons or promotions they are interested in. For example, they can click on "Coupons for a new Chinese restaurant in Minato Ward" to view more information.

[1214] Step 12:

[1215] The user presents the coupon at the store to receive the discount. The store checks the coupon and applies the corresponding discount, allowing the user to receive the discount.

[1216] Example 2

[1217] 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."

[1218] Conventional coupon and promotional information systems have difficulty providing personalized information that takes into account each user's usage trends, and do not deliver appropriate information that reflects the user's emotional state. As a result, information of little value to users is often provided. Furthermore, the provision of real-time information such as the user's current location, travel time to the store, and congestion status is also insufficient. This has led to issues such as reduced convenience and satisfaction for users.

[1219] 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.

[1220] In this invention, the server includes means for collecting user activity data, means for analyzing the collected activity data and learning usage trends for each user, means for collecting and analyzing user emotion data from voice, facial expression, and text input, means for generating appropriate coupons and promotional information based on the user's usage trends and emotion data, means for transmitting the generated information to the user's terminal, means for displaying the information on the user's terminal, and means for providing additional store information and congestion status based on information selected by the user. This makes it possible to provide valuable information tailored to the user's needs and emotional state, thereby improving convenience and satisfaction.

[1221] "User activity data" refers to the behavioral history of a user when using a specific service or system, and includes, for example, payment date and time, payment amount, store information, etc.

[1222] "Means for collection" refers to the combination of hardware and software that the system uses to collect user activity data and emotional data.

[1223] "Means of analysis" refers to algorithms and software that analyze collected data to reveal users' usage trends and emotional states.

[1224] "Means of learning" refers to a method of generating a model using a machine learning algorithm based on user usage trends and emotional data.

[1225] "Emotional data" refers to data on the emotional state extracted from the user's voice, facial expression, text input, etc.

[1226] "Means of generation" refers to algorithms and systems that generate coupons and promotional information tailored to users based on the results of analysis and learning.

[1227] "Transmission means" refers to the communication means and network protocol for transmitting the generated coupons and promotional information to the user's terminal.

[1228] "Displaying means" refers to the display process and interface for visually presenting coupons and promotional information on the user's terminal.

[1229] "Additional store information and congestion status" refers to information such as the time required to reach the store and the current congestion status that is provided along with coupons and promotional information.

[1230] "Location Information" refers to information about a user's current location obtained by GPS or other means.

[1231] "Means for calculating travel time" refers to algorithms or software for calculating travel time from a user to a store based on location information.

[1232] "Permission-based location collection" refers to protocols and permission management systems for collecting location information with user consent.

[1233] This invention is a system that provides optimal coupons and promotional information to individual users by collecting, analyzing, and learning from user activity and emotion data. This system provides useful and valuable information to users through collaboration between the server, terminal, and user.

[1234] Server Processing

[1235] The server first collects user activity data. Specifically, when a user uses the payment system, transaction data such as payment date and time, store information, and payment amount are obtained in real time and stored in a central database. The server polls for data through the payment system's API and immediately stores any new transaction data it detects.

[1236] Next, the server uses an emotion engine to collect the user's emotional data from voice, facial expressions, and text input. The emotion engine determines the user's emotional state using methods such as voice recognition, facial expression analysis, and text analysis. Specific examples include using the Google Cloud Speech-to-Text API and natural language processing toolkits. The server obtains voice and text data from the smartphone app and sends it to the emotion engine to identify emotions.

[1237] The server then uses the collected activity and emotion data to perform machine learning to learn each user's behavioral patterns. This is done using the Python scikit-learn library. The data is fed into the machine learning model to identify each user's behavioral patterns.

[1238] The server then uses a generative algorithm to generate optimal coupons and promotional information for each user based on the learning results and emotion data. A TensorFlow-based generative model is used for this. The generated coupons and promotional information are then sent to the user's device via Google Firebase Cloud Messaging (FCM) or Apple Push Notification Service (APNS).

[1239] Terminal handling

[1240] The device receives coupons and promotional information sent from the server and displays them in a pop-up format on the home screen. The received push notification triggers a specific activity within the app, displaying the coupon information and additional information. When the user clicks on the pop-up, the device provides additional information such as walking time to the store and real-time congestion status.

[1241] For example, the device uses GPS data to obtain the current location, calculates and displays route guidance to the store using the Google Maps API, and obtains congestion information using the Firebase Realtime Database and displays it in real time.

[1242] User Action

[1243] Users can check the information displayed on their device and select coupons or promotional information that interest them. For example, they can click on "Coupons for a new Chinese restaurant in Minato Ward" to view more information. When using a coupon, users present their smartphone at the store and apply the coupon to receive a discount. Feedback information is also sent from within the app to the server and used for future analysis.

[1244] Specific examples

[1245] If a user visits a Chinese restaurant in Minato Ward four times a week, the server collects that activity data and automatically analyzes and learns from it. If the server determines that the user is in an emotional state that requires relaxation, it generates a 20% off coupon for Chinese restaurants in Minato Ward along with additional information such as "This restaurant has a relaxing environment" and sends it to the device. The user can then view the coupon on their smartphone and present it at the restaurant to receive the discount.

[1246] Prompt Sentence Examples

[1247] An example of a prompt to input to a generative AI model is as follows:

[1248] Generate customized coupon information based on user activity and sentiment data, and suggest messages based on the coupon type and user sentiment.

[1249] The above is a specific embodiment for carrying out the present invention. This system makes it possible to provide high-value-added information that meets the needs and emotional state of the user, thereby improving convenience and satisfaction.

[1250] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1251] Step 1:

[1252] The server collects user activity data.

[1253] Input: Transaction data obtained from the payment system (payment date and time, store information, payment amount).

[1254] Processing: Polls activity data through the payment system's API and stores new data in the database whenever it is detected.

[1255] Output: Activity data stored in a database.

[1256] Specific operation: The server periodically sends requests to the payment system's API to obtain new transactions and store them in the database.

[1257] Step 2:

[1258] The server collects emotional data such as voice, facial expressions, and text input.

[1259] Input: Voice data, facial expression data, and text data obtained from a smartphone app.

[1260] Processing: An emotion engine is used to perform speech recognition, facial expression analysis, and text analysis to identify emotional states.

[1261] Output: Identified emotion data.

[1262] Specific operation: Receives voice and text data sent from a smartphone and analyzes sentiment using the Google Cloud Speech-to-Text API and natural language processing toolkit.

[1263] Step 3:

[1264] The server analyzes the collected activity and emotion data to learn each user's usage trends.

[1265] Input: Activity and emotion data stored in a database.

[1266] Processing: We use machine learning algorithms to model your usage habits and behavioral patterns.

[1267] Output: Learned behavioral pattern model.

[1268] Specific operation: Using Python's scikit-learn library, data is input into a learning model and usage trends are analyzed.

[1269] Step 4:

[1270] The server generates coupons and promotional information based on the learning results and emotion data.

[1271] Input: Learned behavioral pattern model and current emotion data.

[1272] Processing: A generation algorithm is used to generate personalized coupons and promotional information.

[1273] Output: Generated coupons and promotions.

[1274] Specific operation: Learning results and emotion data are input into a generative model using TensorFlow to generate individually customized coupon information.

[1275] Step 5:

[1276] The server transmits the generated coupons and advertising information to the user's terminal.

[1277] Input: Generated coupon or promotion information.

[1278] Processing: Sending information to the terminal using a communication protocol.

[1279] Output: Coupons and promotional information sent to the user's device.

[1280] Specific operation: Sends push notifications via Google Firebase Cloud Messaging (FCM) or Apple Push Notification Service (APNS).

[1281] Step 6:

[1282] The terminal displays the received coupons and promotional information.

[1283] Input: Coupons and promotional information received from the server.

[1284] Action: Trigger a notification to display information.

[1285] Output: Coupons and promotional information displayed on the device screen.

[1286] Specific behavior: The device will trigger a specific activity within the app and display information in response to the received push notification.

[1287] Step 7:

[1288] The terminal provides additional store information and crowding status.

[1289] Input: Coupons and promotions selected by the user. GPS data of current location.

[1290] Processing: Obtain any additional information needed and perform calculations.

[1291] Output: Additional information provided to the user (e.g., travel time to the store, how busy it is, etc.).

[1292] Specific operation: Calculates route guidance to the store using the Google Maps API, and obtains and displays congestion information using the Firebase Realtime Database.

[1293] Step 8:

[1294] Users take advantage of coupons, promotions and provide feedback.

[1295] Input: Coupons and promotional information displayed on the device.

[1296] Action: Present a coupon to receive a discount or submit feedback.

[1297] Output: Coupons used and feedback data sent to the server.

[1298] How it works: The user displays the coupon on their smartphone and presents it at the store. Feedback is sent from within the app to the server.

[1299] (Application example 2)

[1300] 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."

[1301] In recent years, there has been a demand for personalized and effective advertising. Existing systems only provide coupons and promotional information based on user activity data, but do not take into account the user's emotional state. As a result, it is difficult to provide appropriate information that is tailored to the user's current situation.

[1302] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting user activity data, means for analyzing the collected activity data and learning usage trends for each user, means for collecting and analyzing user emotion data, means for generating advertisements related to the user's emotional state based on the emotion data, and means for generating advertisements based on the user's profile using a generative AI model. This makes it possible to provide more appropriate and effective advertisements based on the user's emotional state and past behavioral data.

[1303] "User activity data" refers to data that reflects a user's daily behavior, including transaction data such as payment date and time, store information, and payment amount.

[1304] "Means of collection" refers to the technical mechanisms and methods for acquiring user activity data and emotional data in real time and storing it in a database.

[1305] "Means of analysis" refers to algorithms and software that analyze collected activity data and learn usage trends for each user.

[1306] "Means of learning" refers to methods and techniques that use machine learning models to model user preferences and behavioral patterns based on past behavioral data.

[1307] "Emotional data" is information about a user's emotional state as recognized from their voice, facial expressions, and text input.

[1308] "Means for collecting and analyzing emotional data" refers to technologies and devices for recognizing and analyzing a user's emotions from voice, facial expressions, and text input.

[1309] The "means for generating" is an algorithm or system that constructs and generates optimal coupons and promotional information based on the learning results and emotional data.

[1310] A "generative AI model" is an artificial intelligence model that is trained on large datasets to generate optimal ads based on user profiles and behavioral patterns.

[1311] A "prompt sentence" is a text-based input sentence used to give specific instructions or requests to a generative AI model.

[1312] "Display means" refers to the technology or screen interface for visually displaying the generated coupon or promotional information on the user's device.

[1313] "Means for providing" refers to a system or method for providing additional store information, congestion status, etc., depending on the information selected by the user.

[1314] "Location information" refers to data about a user's current location obtained using GPS or other means.

[1315] The present invention relates to a system that collects, analyzes, and learns from users' activity data and emotion data, and then provides optimal coupons and promotional information to each individual user. Specific embodiments of this system are described below.

[1316] Server-side processing

[1317] The server first collects user activity data. For example, every time a user uses the payment system, the server obtains transaction data (payment date and time, store information, payment amount, etc.) in real time and stores it in a database.

[1318] The server then analyzes the collected data and learns the usage trends of each user using machine learning algorithms (e.g., libraries such as TensorFlow and Scikit-learn), which model user preferences and behavioral patterns based on past behavioral data.

[1319] The server then uses an emotion engine (e.g., the EmotionRecognition library) to collect and analyze emotion data. It recognizes emotions from the user's voice, facial expressions, and text input to identify their current emotional state. This emotion data is then analyzed by an algorithm to understand each user's emotional state in real time.

[1320] The server generates optimal coupons and promotional information for each user based on the learning results and emotional data. A generative AI model is used for generation, and specific advertisements are generated by providing a prompt. An example of a prompt might be, "We know that the user's emotional state is 'stressed,' and that their preference is 'cafes' based on past behavioral data. Please generate promotional information for relaxing cafes."

[1321] The generated coupons and promotional information are sent to the user's device as push notifications or messages. The server also provides information on nearby stores and their current traffic situation based on the user's current location.

[1322] Terminal side processing

[1323] The device receives coupons and promotional information sent from the server and displays them in a pop-up format on the home screen. For example, a "20% off coupon for a nearby cafe" may be displayed along with additional information such as "A relaxing environment."

[1324] When the user clicks on the pop-up, the device opens a screen that provides additional information, such as walking time to the store and real-time traffic conditions. The emotion engine also analyzes the user's voice and text inputs to update the user's emotional state in real time. The device also uses GPS to determine the user's current location and calculates the estimated time it will take to get to the store. This location information is only used if the user grants permission.

[1325] User processing

[1326] Users can check the information displayed on their device and select coupons or promotional information that they are interested in. For example, they can click on "New Cafe Coupons" to check detailed information and select the most suitable store based on the information provided by the emotion engine. When using a coupon, they can present their smartphone at the store and apply the coupon to receive a discount.

[1327] Such a system will enable the provision of information tailored to the needs and feelings of each individual user, providing a convenient and valuable service to users.

[1328] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1329] Step 1:

[1330] The server collects user activity data (payment date and time, store information, payment amount, etc.). This data is acquired in real time via the payment system and stored in a database. The input is user transaction data, which is saved in the database to generate activity data.

[1331] Step 2:

[1332] The server analyzes the collected activity data. This analysis uses a machine learning algorithm to learn the usage trends of each user. The input is the activity data collected in step 1, and the output is data that models each user's behavioral patterns and preferences. Specific operations include the algorithm analyzing past behavioral data and extracting each user's behavioral patterns.

[1333] Step 3:

[1334] The server collects and analyzes the user's emotional data. It uses an emotion engine (such as the EmotionRecognition library) to recognize emotions from the user's voice, facial expressions, and text input. The input for this process is the user's voice, facial expressions, and text data, and the output is analyzed emotional state data. Specifically, the emotion engine identifies emotions from voice and facial expressions and records that information in a database.

[1335] Step 4:

[1336] The server uses the generative AI model to generate optimal coupons and promotional information based on the learning results and emotional data. This process involves inputting prompt text into the generative AI model to generate specific advertising copy. The input is the learning results and emotional data, and the output is the optimal coupon or promotional information for the user. As a specific example of how this works, an example of a prompt text for the generative AI model is, "We know that the user's emotional state is 'stressed,' and that their preference is 'cafes' based on past behavioral data. Please generate promotional information for relaxing cafes."

[1337] Step 5:

[1338] The server sends the generated coupons and promotional information to the user's device. The input is the advertising information generated in step 4, and the output is the sending of the advertising information to the user's device. Specifically, the information is sent using push notifications or message functions.

[1339] Step 6:

[1340] The device receives coupons and promotional information sent from the server and displays them in a pop-up format on the home screen. The input is advertising information from the server, and the output is the display on the device. Specifically, information such as "20% off coupon for a nearby cafe" and "relaxing environment" is displayed.

[1341] Step 7:

[1342] When the user clicks on the pop-up, the device opens a screen that provides additional information. The input is the user's click, and the output is the display of a detailed information screen. Specific actions include displaying the walking time to the store and real-time congestion information.

[1343] Step 8:

[1344] The device uses an emotion engine to analyze the user's voice and text input and update the emotional state in real time. The input is the user's voice and text data, and the output is updated emotional state data. Specific operations include optimizing the next advertisement or information based on the analyzed emotional information.

[1345] Step 9:

[1346] The user checks the information displayed on the device and selects coupons or promotional information that interests them. The input is the detailed information screen, and the output is the user's selection action. Specific actions include, for example, clicking on a "new cafe coupon" to check the detailed information.

[1347] Step 10:

[1348] When a user uses a coupon, they present their smartphone at the store and receive a discount by applying the coupon. The input is the user's act of presenting the coupon, and the output is the application of the discount. Specific actions include displaying the coupon on the smartphone and the store checking it.

[1349] 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.

[1350] 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.

[1351] 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.

[1352] 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.

[1353] 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.

[1354] 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.

[1355] 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).

[1356] 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.

[1357] 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."

[1358] 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.

[1359] 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).

[1360] 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.

[1361] 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.

[1362] 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.

[1363] 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.

[1364] 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.

[1365] 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.

[1366] 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.

[1367] 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.

[1368] 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.

[1369] 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.

[1370] The following is further disclosed regarding the above embodiment.

[1371] (Claim 1)

[1372] A means for collecting user activity data;

[1373] A means of analyzing collected activity data and learning usage trends for each user;

[1374] A means for generating appropriate coupons and promotional information based on the user's usage trends;

[1375] means for transmitting the generated information to a user's terminal;

[1376] a means for displaying the information on the user's terminal;

[1377] A means to provide additional store information and crowding information based on user selections;

[1378] A system including:

[1379] (Claim 2)

[1380] 10. The system of claim 1, further comprising means for obtaining a user's current location using the location information and calculating the time required to reach the store.

[1381] (Claim 3)

[1382] 3. The system of claim 2, further comprising means for obtaining location information based on user permission.

[1383] "Example 1"

[1384] (Claim 1)

[1385] A means for collecting user activity data;

[1386] a means for storing the collected activity data in a database;

[1387] A means of analyzing stored data and learning usage trends for each user;

[1388] A means for generating appropriate coupons and promotional information based on the user's usage trends;

[1389] means for transmitting the generated information to a user's terminal;

[1390] a means for displaying the information on the user's terminal;

[1391] A means to provide additional store information and crowding information based on user selections;

[1392] A system including:

[1393] (Claim 2)

[1394] 10. The system of claim 1, further comprising means for obtaining a user's current location using the location information and calculating the time required to reach the store.

[1395] (Claim 3)

[1396] 10. The system of claim 1, further comprising means for obtaining location information based on user permission.

[1397] "Application Example 1"

[1398] (Claim 1)

[1399] A means for collecting user activity data;

[1400] a means for analyzing the collected activity data and using machine learning algorithms to learn individual user usage patterns;

[1401] A means for generating appropriate coupons and promotional information based on the usage trends of users;

[1402] means for transmitting the generated information to a user terminal;

[1403] means for displaying information on a user's terminal;

[1404] A means to provide additional store information and crowding status based on the information selected by the user;

[1405] A means for acquiring location information of a user and displaying a route to the store;

[1406] When using a coupon, you can generate a QR code or barcode and present it at the store.

[1407] means for sending a push notification including the generated coupon information to a user's terminal;

[1408] A system including:

[1409] (Claim 2)

[1410] 2. The system according to claim 1, further comprising means for obtaining a current location of the user using the location information and calculating the time required to reach the store.

[1411] (Claim 3)

[1412] 10. The system of claim 1, further comprising means for obtaining location information based on user permission.

[1413] "Example 2: Combining Emotion Engines"

[1414] (Claim 1)

[1415] A means for collecting user activity data;

[1416] A means of analyzing collected activity data and learning usage trends for each user;

[1417] A means for collecting and analyzing user emotional data from voice, facial expressions, and text input;

[1418] A means for generating appropriate coupons and promotional information based on the usage trends and emotion data of users;

[1419] means for transmitting the generated information to a user terminal;

[1420] means for displaying information on a user's terminal;

[1421] A means to provide additional store information and crowding status based on the information selected by the user;

[1422] A system including:

[1423] (Claim 2)

[1424] 2. The system according to claim 1, further comprising means for obtaining a current location of the user using the location information and calculating the time required to reach the store.

[1425] (Claim 3)

[1426] 10. The system of claim 1, further comprising means for obtaining location information based on user permission.

[1427] "Application example 2 when combining emotion engines"

[1428] (Claim 1)

[1429] A means for collecting user activity data;

[1430] A means of analyzing collected activity data and learning usage trends for each user;

[1431] A means for generating appropriate coupons and promotional information based on the user's usage trends;

[1432] means for transmitting the generated information to a user's terminal;

[1433] a means for displaying the information on the user's terminal;

[1434] a means for collecting and analyzing user emotional data;

[1435] means for generating advertisements relevant to the emotional state of the user based on the emotional data;

[1436] means for generating advertisements based on a user's profile using a generative AI model;

[1437] A means to provide additional store information and crowding information based on user selections;

[1438] A system including:

[1439] (Claim 2)

[1440] 10. The system of claim 1, further comprising means for obtaining a user's current location using the location information and calculating the time required to reach the store.

[1441] (Claim 3)

[1442] 10. The system of claim 1, further comprising means for obtaining location information based on user permission. [Explanation of symbols]

[1443] 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 collecting user activity data; A means of analyzing collected activity data and learning usage trends for each user; A means for generating appropriate coupons and promotional information based on the user's usage trends; means for transmitting the generated information to a user's terminal; a means for displaying the information on the user's terminal; A means to provide additional store information and crowding information based on user selections; A system including:

2. The system according to claim 1 , further comprising means for obtaining the user's current location using the location information and calculating the time required to reach the store.

3. The system of claim 2 further comprising means for obtaining location information based on user permission.

Images