system

Abstract

We provide the system. [Solution] Information collection means for collecting user transaction history data and behavioral data, A data analysis means for analyzing the collected data and identifying the user's past purchasing trends and behavioral patterns, A proposal generation means for extracting relevant facilities based on the user's current location information and generating preferential treatment according to the analysis results, A means for sending the generated discount information to the user's terminal, A prompt generation means that uses a generative AI model to create prompt sentences related to user trends, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] When a user uses a store by making a mere accidental choice without utilizing past purchase history or behavior history in daily life, there are situations where the user cannot enjoy discounts and benefits that should originally be obtained. Also, the store side lacks specific methods for effectively attracting customers. Thus, efficiently utilizing the user's location information and history data to promote store usage and contribute to improving the store's sales is still an unsolved problem.

Means for Solving the Problems

[0005] This invention provides a system that collects users' payment history and behavioral data, and analyzes this data to identify each user's purchasing and behavioral patterns. This system extracts relevant stores based on the user's current location and generates optimal coupons based on past usage history. Furthermore, by transmitting the generated coupons to the user's terminal in real time, it provides users with highly convenient information and effectively promotes store usage.

[0006] "Information gathering means" refers to a function or device for collecting users' payment history data and behavioral data.

[0007] "Data analysis means" refers to a processing function or program that analyzes collected data to identify the user's past purchasing and behavioral patterns.

[0008] "Recommendation generation means" refers to a function or device that extracts relevant stores based on the user's current location information and generates coupons according to the analysis results.

[0009] "Coupon transmission means" refers to a communication function or program for notifying the user's terminal of the generated coupon information.

[0010] "Evaluation means" refers to an analytical function or device for evaluating a user's level of interest in a store based on their visit frequency and purchased items.

[0011] "Location information acquisition means" refers to a communication function or device for periodically acquiring location information from a user's terminal. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0014] First, the language used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. 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), or Bluetooth (registered trademark).

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the 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.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0026] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] This invention is a system for efficiently acquiring and analyzing payment history data and behavioral data via users' smartphones and mobile devices to provide users with optimal store information and coupons. This system generates highly convenient recommendations based on the data analysis results and provides them to users via push notifications.

[0034] System configuration for carrying out the invention

[0035] The server collects users' payment history and behavioral data. This includes purchase date and time, location, amount, purchased product category, travel route, and visit frequency. The data is collected using partner service providers and location-based services.

[0036] The server analyzes the collected data to identify the user's past purchasing behavior and movement patterns. This allows, for example, to reveal the frequency of use in a particular area and the product categories of interest.

[0037] The server extracts relevant stores based on the user's current location. This identifies stores the user is likely to visit and generates customized coupons based on their past history.

[0038] The server sends the generated coupon information to the user's smartphone or mobile device via push notification. This allows users to receive special offers in real time, motivating them to visit stores.

[0039] Specific usage examples

[0040] For example, suppose a user frequently visits a particular cafe in the afternoon. The server analyzes the user's frequency of visits to that cafe and issues a special discount coupon when the user is near the cafe. At this time, the device displays the coupon as a pop-up notification on the screen, prompting the user to use it. If the user uses the coupon and completes the payment, the record is sent back to the server, and the history data is updated.

[0041] In this way, the system of the present invention is expected to provide users with an optimal purchasing experience without them even realizing it, and also to increase the store's ability to attract customers.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server retrieves user payment history data from partner payment service providers. This includes purchase date and time, store information, payment amount, and purchase category.

[0045] Step 2:

[0046] The device uses a GPS sensor to obtain the user's current location information and transmits it to the server. This location information is updated in real time.

[0047] Step 3:

[0048] The server analyzes user behavior patterns and store visit frequency based on past behavioral data. In particular, it identifies visit patterns for specific areas and stores.

[0049] Step 4:

[0050] The server uses the analysis results to search the database for stores near the user's current location and extracts stores that are likely to interest the user.

[0051] Step 5:

[0052] The server generates coupons optimized for each user based on the extracted stores, referencing past usage history and analysis results. These coupons include discounts and special offers.

[0053] Step 6:

[0054] The server sends the generated coupon information to the device as a push notification. The push notification includes information such as the coupon's validity period and the stores where it can be used.

[0055] Step 7:

[0056] The device displays a push notification for the coupon on the screen, prompting the user to confirm. If the user is interested in the coupon, they can tap it to view more details.

[0057] Step 8:

[0058] When a user uses a coupon to purchase an item at a participating store, the payment information is sent back to the server. This allows the transaction history to be updated in real time.

[0059] Step 9:

[0060] The server updates its database based on newly acquired usage history and continues the analysis process to improve the accuracy of recommendations for future use.

[0061] (Example 1)

[0062] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0063] Modern consumers seek efficient and personalized shopping experiences from a wide range of choices, but traditional sales promotion methods struggle to provide information tailored to individual consumer preferences and needs. Furthermore, retailers face the challenge of finding effective ways to attract customers.

[0064] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0065] In this invention, the server includes data collection means for collecting the user's transaction history and movement data; analysis means for analyzing the collected data and identifying the user's past purchase behavior and movement patterns; and recommendation generation means for extracting relevant nearby commercial facilities based on the user's current location information and generating discount information according to the analysis results. This allows consumers to receive promotional information tailored to their preferences in real time, and enables stores to attract customers effectively.

[0066] "Users" refer to individuals or corporations that receive services from this system, and are particularly those who are the target of data collection and analysis.

[0067] "Transaction history" refers to a collection of data that records a user's past purchasing activities, including details such as date, time, location, and product category.

[0068] "Movement data" refers to data related to the user's location information, indicating the user's travel routes and visit frequency.

[0069] "Data collection methods" refer to systems that collect information from partner providers and devices in order to obtain users' transaction history and movement data.

[0070] "Analysis methods" refer to technologies and algorithms used to identify user behavior patterns and interests based on collected data.

[0071] "Recommendation generation method" refers to the process of creating the most suitable coupons and promotional information for users based on analyzed data.

[0072] A "commercial facility" refers to a place or business that provides goods or services to users.

[0073] "Discount information" refers to information that temporarily lowers the price of goods or services, and refers to discounts offered to users.

[0074] "Information transmission means" refers to the communication technologies and protocols used to deliver generated discount information to the user's mobile device.

[0075] "History update method" refers to a method of updating the database based on the user's coupon usage results to improve the accuracy of future analyses.

[0076] This invention is a system aimed at enabling users to obtain an optimal purchasing experience based on their individual preferences and behaviors. The system primarily involves data collection, analysis, and the provision of information tailored to specific conditions.

[0077] First, the server automatically collects user transaction history and movement data through partner data providers and location services. This includes purchase date and time, product category, and location information. Cloud-based storage and APIs are used for data collection as a secure and efficient method.

[0078] Next, the server uses a dedicated analytical tool to analyze the collected data. Specifically, it utilizes a programming language like Python and the scikit-learn library to employ machine learning algorithms to identify user purchasing patterns and interests. As a result of the analysis, behavioral trends in specific time periods and geographical areas are recognized, and a different profile is formed for each user.

[0079] Next, the server extracts relevant facilities from nearby commercial establishments based on the user's current location. This generates optimal discount information for the commercial establishments the user is likely to visit. During this generation process, the following prompts are input using a generation AI model to maximize the use of discount information tailored to the user's preferences:

[0080] "Generate a coupon to be offered to a specific user on their next visit, based on their purchase history and current location."

[0081] Finally, the generated discount information is sent to the user's device in real time using a push notification service such as Firebase Cloud Messaging. The device immediately displays this information as a notification, presenting it to the user. The results of each discount offer are sent back to the server, and the database is constantly updated. This improves the accuracy of future information provision and enables a more personalized purchasing approach for the user.

[0082] Through this system, users can enjoy a more attractive shopping experience, and commercial facilities can expect to attract more customers effectively.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The server collects data from partner service providers and location services. Specifically, it obtains user transaction history (purchase date and time, product category, etc.) and movement data (location information, visit frequency, etc.) via APIs. The input consists of transaction history and location information corresponding to each user's ID, which is securely stored in cloud storage to form the initial dataset.

[0086] Step 2:

[0087] The server analyzes the collected data. The analysis uses the Python scikit-learn library and applies machine learning algorithms. Specifically, it analyzes user purchasing and movement patterns using clustering techniques. The input is the data collected in step 1, and the output is profile data showing the interests and tendencies of specific users. This enables user-specific targeting.

[0088] Step 3:

[0089] The server extracts relevant commercial facilities using the user's current location information. It searches for nearby stores centered on the user's current location using a geospatial database. The inputs are the user's location information obtained in real time and the profile data generated in step 2. The output is a targeted store list, which will be used for coupon generation later.

[0090] Step 4:

[0091] The server generates discount information using a generative AI model based on a targeted list of stores. It generates coupons optimized for each user based on their purchase history and current location using prompts. Specifically, it uses the prompt, "Generate a coupon to offer on the next visit based on a specific user's purchase history and current location." The inputs are the store list from step 3 and the profile data from step 2, and the output is personalized discount information for each user.

[0092] Step 5:

[0093] The server sends the generated discount information to the user's device via push notification. The coupon is delivered to the user's smartphone via a push notification service such as Firebase Cloud Messaging. The input is the discount information generated in step 4, and the output is a notification displayed on the user's device.

[0094] Step 6:

[0095] When a user uses a coupon and makes a purchase, that information is sent back to the server. The server uses this information to update the database and refine the user's profile. This improves the accuracy of targeting for future purchases and enables more effective recommendations.

[0096] (Application Example 1)

[0097] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0098] Currently, many electronic payment systems and location-based services only provide users with unpersonalized information and benefits, making it difficult to offer optimized suggestions that reflect users' purchasing trends and behavioral patterns. As a result, users often miss opportunities to receive information that is truly valuable to them. Furthermore, this presents a problem for businesses, as they are unable to improve their customer acquisition efficiency.

[0099] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0100] In this invention, the server includes information gathering means for collecting user transaction history data and behavioral data; data analysis means for analyzing the collected data and identifying the user's past purchasing trends and behavioral patterns; suggestion generation means for extracting relevant facilities based on the user's current location information and generating special offers corresponding to the analysis results; and prompt generation means for creating prompt messages related to the user's tendencies using a generation AI model. This enables users to receive valuable information tailored to their preferences, and allows companies to attract customers efficiently.

[0101] "Transaction history data" refers to information that shows records of past purchases and payments made by a user.

[0102] "Behavioral data" refers to information about a user's physical behavior, such as their location, movement patterns, and frequency of visits.

[0103] "Information gathering means" refers to devices or methods for collecting users' transaction history data and behavioral data.

[0104] "Data analysis means" refers to a device or method for analyzing collected data to identify users' purchasing trends and behavioral patterns.

[0105] "Purchasing trends" refer to the behavioral tendencies based on what products and services a user has purchased in the past, as well as the frequency and patterns of those purchases.

[0106] "Behavioral patterns" refer to the patterns of movement and visits that users typically follow on a daily basis, indicating how often they visit specific locations.

[0107] "Privileges" refer to the provision of special discounts or services that allow users to enjoy benefits.

[0108] "Proposal generation means" refers to a device or method for generating customized benefits for users.

[0109] "Prompt generation means" refers to a device or method that uses a generation AI model to create instructional or suggestive statements based on the user's behavioral tendencies.

[0110] A "facility" refers to places, shops, or service providers that users may visit.

[0111] In the system that realizes this invention, a server, a user terminal, and a data processing program using a generation AI model work in conjunction. The server first collects the user's transaction history data and behavioral data from various sources. This includes the user's past purchase history and behavioral history such as location information and store visit frequency. Information collection is performed in real time using a cloud-based database.

[0112] Next, the server analyzes the collected data using data analysis tools to identify users' purchasing trends and behavioral patterns. This analysis utilizes Python data analysis libraries and machine learning algorithms. Specifically, Pandas and Scikit-learn can be used to format and analyze the data.

[0113] Based on the user's current location, the server utilizes location services to extract relevant facilities. This identifies stores and facilities that the user is likely to visit and generates promotional information related to those facilities. The promotional information is then generated using an AI model to create benefits tailored to the user's behavior patterns.

[0114] The generated promotional information is sent from the server to the user's device via push notification. Push technologies such as Firebase Cloud Messaging are used for this notification. By receiving this promotional information, users can take advantage of benefits that are beneficial to their purchasing behavior in a timely manner.

[0115] As a concrete example, when a user approaches a cafe they frequent, a 10% discount coupon offered by that cafe is sent to the user's smartphone. This coupon is generated based on the server's analysis of the user's past purchase history and location information.

[0116] An example of a prompt for a generative AI model would be: "The user tends to buy coffee at a specific cafe every morning. Create a discount suggestion to offer the user the next time they visit that cafe." This allows the user to receive advantageous information tailored to their individual needs.

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] The server collects user transaction history and behavioral data. Inputs include purchase history, location information, and visit frequency, while output is an information database summarizing this data. The server retrieves data from partner service APIs and GPS devices and records it in the cloud database.

[0120] Step 2:

[0121] The server analyzes the collected data. The input is an information database, and the output is an analysis showing users' purchasing trends and behavioral patterns. The server uses Python's Pandas library to format the data and machine learning algorithms to predict behavioral patterns.

[0122] Step 3:

[0123] The server extracts relevant facilities based on the user's current location information. The input is the user's real-time location data and the analysis results from the previous step, and the output is a list of highly relevant facilities. The server retrieves current data from location information services and matches it with the level of interest information obtained from data analysis.

[0124] Step 4:

[0125] The server generates special offers based on the extracted information. The input is a list of facilities and the purchasing trends of users, and the output is customized special offer information. The server runs a generation AI model, creates prompt messages, and generates the most suitable special offer.

[0126] Step 5:

[0127] The server sends the generated special offer information as a push notification to the user's device. The input is the special offer information, and the output is the user's device that received the notification. The server uses Firebase Cloud Messaging to send the special offer information in real time.

[0128] Step 6:

[0129] The user checks the received discount information, visits the store as needed, and uses the coupon. The input is the discount information sent to the device, and the output is the history data of used coupons. The user checks the notification on the device and takes advantage of newly generated discounts.

[0130] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0131] This invention is an information provision system that takes into account the emotional state of users. By analyzing the user's payment history, behavioral data, and emotional state, the system provides the most suitable coupons and related information to the user. This system uses an emotion engine to identify the user's emotional state and generate customized recommendations based on that state.

[0132] System configuration for carrying out the invention

[0133] The server collects users' payment history and behavioral data from partner payment service providers and behavioral data providers. This includes information about stores visited in the past and the categories of products purchased.

[0134] The server uses an emotion engine to analyze the emotional state of the user's current situation. At this stage, it uses data obtained from voice input and facial imagery to identify multiple emotional states the person may be experiencing (e.g., joy, sadness, surprise, etc.).

[0135] The server selects appropriate store information and coupons based on the user's emotional state and past purchase history. By adjusting the information delivered according to the analysis results of the emotion engine, it presents benefits tailored to the user's current emotions.

[0136] The server sends the selected coupon information to the device as a push notification. The device receives the notification and displays it on the user's screen.

[0137] Specific usage examples

[0138] For example, consider a scenario where a user is walking through a shopping mall and joyful laughter is detected in the audio data. Based on this information, the server identifies the emotion of "joy." The server then generates a special coupon for an entertainment facility or amusement-related product that the user has previously enjoyed. This coupon is delivered to the user in real time via their device, and the user checks the notification and chooses to visit the facility.

[0139] In this way, this system responds sensitively to users' emotions, providing a more personalized shopping experience and contributing to increased user satisfaction. Furthermore, it enables stores to target customers based on their emotions, allowing for more efficient promotions.

[0140] The following describes the processing flow.

[0141] Step 1:

[0142] The server receives payment history data from the payment provider. This data includes information about the goods and services the user has purchased in the past.

[0143] Step 2:

[0144] The device uses built-in sensors (camera and microphone) to detect the user's facial expressions and voice tone, and transmits that data to the emotion engine.

[0145] Step 3:

[0146] The server activates an emotion engine to analyze the audio and image data sent by the user. This identifies the user's emotional state (joy, surprise, sadness, etc.).

[0147] Step 4:

[0148] The server combines collected payment history and emotional states to identify stores and products that best match the user's current interests and preferences.

[0149] Step 5:

[0150] The server generates the most suitable coupons or special offers based on the identified store or product. This includes messages tailored to the user's emotional state.

[0151] Step 6:

[0152] The server sends the generated coupon information or special offer to the device in the form of a push notification.

[0153] Step 7:

[0154] The device displays received notifications to the user and provides access to detailed information through an engaging interface.

[0155] Step 8:

[0156] When a user uses a coupon to purchase an item at a store, that information is sent back to the server and stored in the database as part of their usage history.

[0157] Step 9:

[0158] The server initiates an analysis process based on the new usage history stored in the database, contributing to improving the accuracy of the system for future recommendations.

[0159] (Example 2)

[0160] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0161] Conventional information provision systems are limited to providing information based on users' past purchase history and behavioral patterns, and have the challenge of not being able to provide appropriate recommendations that take into account the user's emotional state. In addition, delays and decreased accuracy in real-time information provision also affect user satisfaction.

[0162] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0163] In this invention, the server includes information gathering means for collecting the user's payment history and behavioral data, sentiment analysis means for analyzing the collected data and identifying the user's emotional state, and recommendation generation means for generating relevant information based on the emotional state and purchase history data. This enables the provision of personalized information that corresponds to the user's emotional state.

[0164] "Information gathering means" refers to functions or devices for effectively collecting users' payment history and behavioral data.

[0165] "Emotional analysis means" refers to a function or device that analyzes and identifies a user's emotional state using audio data and image data based on collected data.

[0166] "Recommendation generation means" refers to a function or device that generates information or coupons related to the user based on analyzed emotional state and purchase history data.

[0167] "Information transmission means" refers to a function or device for notifying a user device of the generated information.

[0168] "Location information acquisition means" refers to a function or device for acquiring location information from a user device and determining the user's current location.

[0169] This system is designed to provide information that takes into account the user's emotional state. Specifically, the server acts as the core, collecting and analyzing various data to provide customized recommendations.

[0170] First, the server uses information gathering methods to obtain users' payment history and behavioral data from payment service providers and data providers. This includes data collection via APIs, and a high-performance database server is one example of hardware used. This data may include previously visited stores and categories of products purchased.

[0171] Next, the server employs emotion analysis tools. Specifically, it uses deep learning models to process audio and image data to analyze the user's emotional state. This analysis utilizes an emotion AI engine, which can identify multiple emotional states, such as "joy" or "sadness."

[0172] Subsequently, the server uses recommendation generation tools to generate relevant information based on the analyzed emotional state and past purchase history data. For example, if the emotion of joy is detected, coupons for entertainment facilities can be generated.

[0173] Finally, the server uses an information transmission method to send the generated coupons and information to the device as a push notification. The device receives it and displays it to the user immediately. This allows the user to check available coupons and related information in real time.

[0174] As a concrete example, suppose a user is walking through a shopping mall and their smartphone's microphone picks up the sound of cheerful conversation. In this case, the server identifies the emotion of "joy," generates a discount coupon for the user's favorite amusement facility, and sends it to the device. The device displays a notification, and the user can use the coupon by tapping the notification.

[0175] An example of a prompt message would be, "Detect the emotions of users enjoying themselves from audio data within the shopping mall, and generate coupons tailored to those emotions." By inputting this prompt into the AI ​​generation model, it becomes possible to provide appropriate information.

[0176] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0177] Step 1:

[0178] The server uses information gathering tools to collect users' payment history and behavioral data from partner payment service providers and behavioral data providers. Data obtained via APIs as input includes store visit history and purchased product categories. This data is stored in a database and used as foundational information to identify users' past behavioral patterns.

[0179] Step 2:

[0180] The server uses emotion analysis tools to identify the user's emotional state by analyzing audio and image data. The input data consists of the user's voice and facial expressions, and the emotions are classified based on a deep learning model. This results in the output of labels such as "joy" or "sadness" as the emotional state.

[0181] Step 3:

[0182] The server uses a recommendation generation mechanism to match identified emotional states with past payment history and generate recommendations for the user. Inputs include analyzed emotional states and stored purchase history data, and relevant coupons and information are generated based on these. For example, if an emotional state is "joyful" and the user has frequently visited amusement facilities in the past, a coupon for a special offer at such facilities will be output.

[0183] Step 4:

[0184] The server sends the generated coupon information to the user's device as a push notification using the information transmission method. The input is the coupon information generated in step 3, which is immediately presented to the user when sent to the device. The device receives this information and displays it on the screen along with a notification sound.

[0185] Step 5:

[0186] Users can check notifications received on their devices and, if interested, tap on the notification to view more details. This allows them to activate and use available coupons. For example, a user could receive a coupon for an entertainment facility in a shopping mall, check it on the spot, and then visit the facility.

[0187] (Application Example 2)

[0188] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0189] In today's urban environment, users are surrounded by a vast amount of information, making it difficult to find the most relevant information and benefits for them. In particular, the lack of information tailored to users' emotional states limits their experiences. Therefore, an information delivery system that takes users' emotional states into consideration is needed.

[0190] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0191] In this invention, the server includes information acquisition means, data processing means, and emotion analysis means. This enables the provision of personalized information based on the user's emotional state.

[0192] "Information acquisition means" refers to a medium that has the function of collecting users' economic transaction history data and behavioral pattern data.

[0193] "Data processing means" refers to a medium that has the function of analyzing acquired economic transaction history data and behavioral pattern data to identify the user's past purchasing behavior patterns and behavioral history patterns.

[0194] An "emotion analysis tool" is a medium that has the function of identifying the emotional state of a user and generating information corresponding to that state.

[0195] An "emotion-linked recommendation generation method" is a medium that has the function of generating information based on the emotional state of the user identified by an emotion analysis method.

[0196] A "notification means" is a medium that has the function of notifying the user's device of the generated recommendation information.

[0197] The system based on this invention is designed to provide personalized information tailored to the user's emotional state.

[0198] First, the server uses information acquisition methods to collect users' economic transaction history data and behavioral pattern data. This includes data acquired through smartphones and wearable devices.

[0199] Next, the server uses data processing tools to analyze the acquired data and identify the user's past purchasing behavior patterns and behavioral history patterns. This analysis utilizes data mining techniques and machine learning algorithms.

[0200] The server then uses emotion analysis tools to identify the user's emotional state from their voice and facial image. Emotion analysis libraries such as the Affectiva SDK are sometimes used for this purpose. This analysis makes it possible to recognize emotions such as "joy" and "surprise" in real time.

[0201] The user's device receives information notified from the server and displays it on the screen. Depending on the notification method, recommendation information and coupons tailored to the user's emotional state are presented in a timely manner.

[0202] For example, if a user experiences a feeling of "surprise" when visiting a tourist destination, information about special exhibitions or events within the facility will be recommended. By implementing such a system, users can have experiences they might not have otherwise noticed.

[0203] An example of a prompt message is: "Create a program that analyzes emotional states obtained from voice data in real time and provides the latest information on city events."

[0204] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0205] Step 1:

[0206] The server collects economic transaction history data and behavioral pattern data from the user's smartphone or wearable device via information acquisition means. In this step, the user's transaction history and location information are provided as input, and this data is processed to convert it into an appropriate format for storage in the database. The output is a structured dataset.

[0207] Step 2:

[0208] The server uses data processing tools to analyze the collected data and identify the user's past purchasing behavior patterns and behavioral history patterns. In this step, the stored dataset is used as input, and calculations are performed to identify patterns using data mining techniques. The output is an analytical report showing the user's behavioral characteristics.

[0209] Step 3:

[0210] The server uses emotion analysis tools to analyze audio and facial data acquired from the user's device to identify their current emotional state. Real-time audio and video data are provided as input, and an emotion score is calculated using the Affectiva SDK. The output is tag information indicating the user's emotional state.

[0211] Step 4:

[0212] The server uses an emotion-driven recommendation generation method to generate appropriate recommendation information based on the obtained emotional state and analysis report. The analysis report and emotional state tags are used as input, and a generation AI model is applied based on this to perform calculations that generate suggestions suitable for the user. The output is customized recommendation data.

[0213] Step 5:

[0214] The terminal receives recommendation information sent from the server and displays it as a notification on the user's screen. The received recommendation data is used as input, and the system formats it for display on the user interface. The output is the specific suggestions displayed on the user's terminal.

[0215] Step 6:

[0216] The user reviews the displayed recommendation information and chooses an action based on the information that interests them. In this step, the user checks the notification, and the decision of what action to take is the output.

[0217] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0218] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0219] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0220] [Second Embodiment]

[0221] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0222] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0223] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0224] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0225] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0226] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0227] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0228] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0229] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0230] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0231] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0232] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0233] This invention is a system for efficiently acquiring and analyzing payment history data and behavioral data via users' smartphones and mobile devices to provide users with optimal store information and coupons. This system generates highly convenient recommendations based on the data analysis results and provides them to users via push notifications.

[0234] System configuration for carrying out the invention

[0235] The server collects users' payment history and behavioral data. This includes purchase date and time, location, amount, purchased product category, travel route, and visit frequency. The data is collected using partner service providers and location-based services.

[0236] The server analyzes the collected data to identify the user's past purchasing behavior and movement patterns. This allows, for example, to reveal the frequency of use in a particular area and the product categories of interest.

[0237] The server extracts relevant stores based on the user's current location. This identifies stores the user is likely to visit and generates customized coupons based on their past history.

[0238] The server sends the generated coupon information to the user's smartphone or mobile device via push notification. This allows users to receive special offers in real time, motivating them to visit stores.

[0239] Specific usage examples

[0240] For example, suppose a user frequently visits a particular cafe in the afternoon. The server analyzes the user's frequency of visits to that cafe and issues a special discount coupon when the user is near the cafe. At this time, the device displays the coupon as a pop-up notification on the screen, prompting the user to use it. If the user uses the coupon and completes the payment, the record is sent back to the server, and the history data is updated.

[0241] In this way, the system of the present invention is expected to provide users with an optimal purchasing experience without them even realizing it, and also to increase the store's ability to attract customers.

[0242] The following describes the processing flow.

[0243] Step 1:

[0244] The server retrieves user payment history data from partner payment service providers. This includes purchase date and time, store information, payment amount, and purchase category.

[0245] Step 2:

[0246] The device uses a GPS sensor to obtain the user's current location information and transmits it to the server. This location information is updated in real time.

[0247] Step 3:

[0248] The server analyzes user behavior patterns and store visit frequency based on past behavioral data. In particular, it identifies visit patterns for specific areas and stores.

[0249] Step 4:

[0250] The server uses the analysis results to search the database for stores near the user's current location and extracts stores that are likely to interest the user.

[0251] Step 5:

[0252] The server generates coupons optimized for each user based on the extracted stores, referencing past usage history and analysis results. These coupons include discounts and special offers.

[0253] Step 6:

[0254] The server sends the generated coupon information to the device as a push notification. The push notification includes information such as the coupon's validity period and the stores where it can be used.

[0255] Step 7:

[0256] The device displays a push notification for the coupon on the screen, prompting the user to confirm. If the user is interested in the coupon, they can tap it to view more details.

[0257] Step 8:

[0258] When a user uses a coupon to purchase an item at a participating store, the payment information is sent back to the server. This allows the transaction history to be updated in real time.

[0259] Step 9:

[0260] The server updates its database based on newly acquired usage history and continues the analysis process to improve the accuracy of recommendations for future use.

[0261] (Example 1)

[0262] Next, we will describe Example 1. 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."

[0263] Modern consumers seek efficient and personalized shopping experiences from a wide range of choices, but traditional sales promotion methods struggle to provide information tailored to individual consumer preferences and needs. Furthermore, retailers face the challenge of finding effective ways to attract customers.

[0264] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0265] In this invention, the server includes data collection means for collecting the user's transaction history and movement data; analysis means for analyzing the collected data and identifying the user's past purchase behavior and movement patterns; and recommendation generation means for extracting relevant nearby commercial facilities based on the user's current location information and generating discount information according to the analysis results. This allows consumers to receive promotional information tailored to their preferences in real time, and enables stores to attract customers effectively.

[0266] "Users" refer to individuals or corporations that receive services from this system, and are particularly those who are the target of data collection and analysis.

[0267] "Transaction history" refers to a collection of data that records a user's past purchasing activities, including details such as date, time, location, and product category.

[0268] "Movement data" refers to data related to the user's location information, indicating the user's travel routes and visit frequency.

[0269] "Data collection methods" refer to systems that collect information from partner providers and devices in order to obtain users' transaction history and movement data.

[0270] "Analysis methods" refer to technologies and algorithms used to identify user behavior patterns and interests based on collected data.

[0271] "Recommendation generation method" refers to the process of creating the most suitable coupons and promotional information for users based on analyzed data.

[0272] A "commercial facility" refers to a place or business that provides goods or services to users.

[0273] "Discount information" refers to information that temporarily lowers the price of goods or services, and refers to discounts offered to users.

[0274] "Information transmission means" refers to the communication technologies and protocols used to deliver generated discount information to the user's mobile device.

[0275] "History update method" refers to a method of updating the database based on the user's coupon usage results to improve the accuracy of future analyses.

[0276] This invention is a system aimed at enabling users to obtain an optimal purchasing experience based on their individual preferences and behaviors. The system primarily involves data collection, analysis, and the provision of information tailored to specific conditions.

[0277] First, the server automatically collects user transaction history and movement data through partner data providers and location services. This includes purchase date and time, product category, and location information. Cloud-based storage and APIs are used for data collection as a secure and efficient method.

[0278] Next, the server uses a dedicated analytical tool to analyze the collected data. Specifically, it utilizes a programming language like Python and the scikit-learn library to employ machine learning algorithms to identify user purchasing patterns and interests. As a result of the analysis, behavioral trends in specific time periods and geographical areas are recognized, and a different profile is formed for each user.

[0279] Next, the server extracts relevant facilities from nearby commercial establishments based on the user's current location. This generates optimal discount information for the commercial establishments the user is likely to visit. During this generation process, the following prompts are input using a generation AI model to maximize the use of discount information tailored to the user's preferences:

[0280] "Generate a coupon to be offered to a specific user on their next visit, based on their purchase history and current location."

[0281] Finally, the generated discount information is sent to the user's device in real time using a push notification service such as Firebase Cloud Messaging. The device immediately displays this information as a notification, presenting it to the user. The results of each discount offer are sent back to the server, and the database is constantly updated. This improves the accuracy of future information provision and enables a more personalized purchasing approach for the user.

[0282] Through this system, users can enjoy a more attractive purchasing experience, and commercial facilities can also expect effective customer attraction.

[0283] The flow of the specific process in Example 1 will be described with reference to FIG. 11.

[0284] Step 1:

[0285] The server collects data from partnering service providers and location-based services. Specifically, it obtains the user's transaction history (such as purchase date and time, product category, etc.) and movement data (such as location information, visit frequency, etc.) through APIs. As input, the transaction history and location information corresponding to each user's ID are provided, and an initial dataset is formed by securely storing this in cloud storage.

[0286] Step 2:

[0287] The server analyzes the collected data. As the analysis means, the scikit-learn library of Python is used to apply machine learning algorithms. Specifically, clustering techniques are used to analyze the user's purchase patterns and movement patterns. The input is the data collected in Step 1, and profile data indicating the interests and tendencies of specific users is generated as output. This enables targeting for each user.

[0288] Step 3:

[0289] The server extracts relevant commercial facilities using the user's current location information. It searches for surrounding stores centered on the user's current location using a geospatial database. The input includes the user's location information obtained in real time and the profile data generated in Step 2. The output is a targeted store list, which is used for subsequent coupon generation.

[0290] Step 4:

[0291] The server generates discount information using a generative AI model based on a targeted list of stores. It generates coupons optimized for each user based on their purchase history and current location using prompts. Specifically, it uses the prompt, "Generate a coupon to offer on the next visit based on a specific user's purchase history and current location." The inputs are the store list from step 3 and the profile data from step 2, and the output is personalized discount information for each user.

[0292] Step 5:

[0293] The server sends the generated discount information to the user's device via push notification. The coupon is delivered to the user's smartphone via a push notification service such as Firebase Cloud Messaging. The input is the discount information generated in step 4, and the output is a notification displayed on the user's device.

[0294] Step 6:

[0295] When a user uses a coupon and makes a purchase, that information is sent back to the server. The server uses this information to update the database and refine the user's profile. This improves the accuracy of targeting for future purchases and enables more effective recommendations.

[0296] (Application Example 1)

[0297] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0298] Currently, many electronic payment systems and location-based services only provide users with unpersonalized information and benefits, making it difficult to offer optimized suggestions that reflect users' purchasing trends and behavioral patterns. As a result, users often miss opportunities to receive information that is truly valuable to them. Furthermore, this presents a problem for businesses, as they are unable to improve their customer acquisition efficiency.

[0299] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0300] In this invention, the server includes information gathering means for collecting user transaction history data and behavioral data; data analysis means for analyzing the collected data and identifying the user's past purchasing trends and behavioral patterns; suggestion generation means for extracting relevant facilities based on the user's current location information and generating special offers corresponding to the analysis results; and prompt generation means for creating prompt messages related to the user's tendencies using a generation AI model. This enables users to receive valuable information tailored to their preferences, and allows companies to attract customers efficiently.

[0301] "Transaction history data" refers to information that shows records of past purchases and payments made by a user.

[0302] "Behavioral data" refers to information about a user's physical behavior, such as their location, movement patterns, and frequency of visits.

[0303] "Information gathering means" refers to devices or methods for collecting users' transaction history data and behavioral data.

[0304] "Data analysis means" refers to a device or method for analyzing collected data to identify users' purchasing trends and behavioral patterns.

[0305] "Purchase tendency" refers to the tendency of actions based on what products and services a user has purchased in the past, as well as the frequency and pattern thereof.

[0306] "Behavior pattern" refers to the pattern of movement and visits that a user makes daily, indicating how often a specific location is visited.

[0307] "Privilege" refers to the provision of special discounts and services that a user can enjoy benefits from.

[0308] "Proposal generation means" refers to a device or method for generating customized privileges for a user.

[0309] "Prompt generation means" refers to a device or method for creating instructional texts and proposal texts based on the behavior tendency of a user by using a generation AI model.

[0310] "Facility" refers to a place, shop, or service provider location that a user may visit.

[0311] In the system for realizing this invention, a server, a user terminal, and a data processing program by a generation AI model operate in cooperation. First, the server collects the transaction history data and behavior data of the user from various information sources. This includes the user's past purchase history and behavior history such as location information and store visit frequency. The information collection is performed in real time using a cloud-based database.

[0312] Next, the server analyzes the collected data using data analysis means to identify the purchase tendency and behavior pattern of the user. Python data analysis libraries and machine learning algorithms are used for this analysis. Specifically, data can be shaped and analyzed using Pandas and Scikit-learn.

[0313] Based on the user's current location, the server utilizes location services to extract relevant facilities. This identifies stores and facilities that the user is likely to visit and generates promotional information related to those facilities. The promotional information is then generated using an AI model to create benefits tailored to the user's behavior patterns.

[0314] The generated promotional information is sent from the server to the user's device via push notification. Push technologies such as Firebase Cloud Messaging are used for this notification. By receiving this promotional information, users can take advantage of benefits that are beneficial to their purchasing behavior in a timely manner.

[0315] As a concrete example, when a user approaches a cafe they frequent, a 10% discount coupon offered by that cafe is sent to the user's smartphone. This coupon is generated based on the server's analysis of the user's past purchase history and location information.

[0316] An example of a prompt for a generative AI model would be: "The user tends to buy coffee at a specific cafe every morning. Create a discount suggestion to offer the user the next time they visit that cafe." This allows the user to receive advantageous information tailored to their individual needs.

[0317] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0318] Step 1:

[0319] The server collects user transaction history and behavioral data. Inputs include purchase history, location information, and visit frequency, while output is an information database summarizing this data. The server retrieves data from partner service APIs and GPS devices and records it in the cloud database.

[0320] Step 2:

[0321] The server analyzes the collected data. The input is an information database, and the output is an analysis showing users' purchasing trends and behavioral patterns. The server uses Python's Pandas library to format the data and machine learning algorithms to predict behavioral patterns.

[0322] Step 3:

[0323] The server extracts relevant facilities based on the user's current location information. The input is the user's real-time location data and the analysis results from the previous step, and the output is a list of highly relevant facilities. The server retrieves current data from location information services and matches it with the level of interest information obtained from data analysis.

[0324] Step 4:

[0325] The server generates special offers based on the extracted information. The input is a list of facilities and the purchasing trends of users, and the output is customized special offer information. The server runs a generation AI model, creates prompt messages, and generates the most suitable special offer.

[0326] Step 5:

[0327] The server sends the generated special offer information as a push notification to the user's device. The input is the special offer information, and the output is the user's device that received the notification. The server uses Firebase Cloud Messaging to send the special offer information in real time.

[0328] Step 6:

[0329] The user checks the received discount information, visits the store as needed, and uses the coupon. The input is the discount information sent to the device, and the output is the history data of used coupons. The user checks the notification on the device and takes advantage of newly generated discounts.

[0330] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0331] This invention is an information provision system that takes into account the emotional state of users. By analyzing the user's payment history, behavioral data, and emotional state, the system provides the most suitable coupons and related information to the user. This system uses an emotion engine to identify the user's emotional state and generate customized recommendations based on that state.

[0332] System configuration for carrying out the invention

[0333] The server collects users' payment history and behavioral data from partner payment service providers and behavioral data providers. This includes information about stores visited in the past and the categories of products purchased.

[0334] The server uses an emotion engine to analyze the emotional state of the user's current situation. At this stage, it uses data obtained from voice input and facial imagery to identify multiple emotional states the person may be experiencing (e.g., joy, sadness, surprise, etc.).

[0335] The server selects appropriate store information and coupons based on the user's emotional state and past purchase history. By adjusting the information delivered according to the analysis results of the emotion engine, it presents benefits tailored to the user's current emotions.

[0336] The server sends the selected coupon information to the device as a push notification. The device receives the notification and displays it on the user's screen.

[0337] Specific usage examples

[0338] For example, consider a scenario where a user is walking through a shopping mall and joyful laughter is detected in the audio data. Based on this information, the server identifies the emotion of "joy." The server then generates a special coupon for an entertainment facility or amusement-related product that the user has previously enjoyed. This coupon is delivered to the user in real time via their device, and the user checks the notification and chooses to visit the facility.

[0339] In this way, this system responds sensitively to users' emotions, providing a more personalized shopping experience and contributing to increased user satisfaction. Furthermore, it enables stores to target customers based on their emotions, allowing for more efficient promotions.

[0340] The following describes the processing flow.

[0341] Step 1:

[0342] The server receives payment history data from the payment provider. This data includes information about the goods and services the user has purchased in the past.

[0343] Step 2:

[0344] The device uses built-in sensors (camera and microphone) to detect the user's facial expressions and voice tone, and transmits that data to the emotion engine.

[0345] Step 3:

[0346] The server activates an emotion engine to analyze the audio and image data sent by the user. This identifies the user's emotional state (joy, surprise, sadness, etc.).

[0347] Step 4:

[0348] The server combines collected payment history and emotional states to identify stores and products that best match the user's current interests and preferences.

[0349] Step 5:

[0350] The server generates the most suitable coupons or special offers based on the identified store or product. This includes messages tailored to the user's emotional state.

[0351] Step 6:

[0352] The server sends the generated coupon information or special offer to the device in the form of a push notification.

[0353] Step 7:

[0354] The device displays received notifications to the user and provides access to detailed information through an engaging interface.

[0355] Step 8:

[0356] When a user uses a coupon to purchase an item at a store, that information is sent back to the server and stored in the database as part of their usage history.

[0357] Step 9:

[0358] The server initiates an analysis process based on the new usage history stored in the database, contributing to improving the accuracy of the system for future recommendations.

[0359] (Example 2)

[0360] Next, we will describe Example 2. 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".

[0361] Conventional information provision systems are limited to providing information based on users' past purchase history and behavioral patterns, and have the challenge of not being able to provide appropriate recommendations that take into account the user's emotional state. In addition, delays and decreased accuracy in real-time information provision also affect user satisfaction.

[0362] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0363] In this invention, the server includes information gathering means for collecting the user's payment history and behavioral data, sentiment analysis means for analyzing the collected data and identifying the user's emotional state, and recommendation generation means for generating relevant information based on the emotional state and purchase history data. This enables the provision of personalized information that corresponds to the user's emotional state.

[0364] "Information gathering means" refers to functions or devices for effectively collecting users' payment history and behavioral data.

[0365] "Emotional analysis means" refers to a function or device that analyzes and identifies a user's emotional state using audio data and image data based on collected data.

[0366] "Recommendation generation means" refers to a function or device that generates information or coupons related to the user based on analyzed emotional state and purchase history data.

[0367] "Information transmission means" refers to a function or device for notifying a user device of the generated information.

[0368] "Location information acquisition means" refers to a function or device for acquiring location information from a user device and determining the user's current location.

[0369] This system is designed to provide information that takes into account the user's emotional state. Specifically, the server acts as the core, collecting and analyzing various data to provide customized recommendations.

[0370] First, the server uses information gathering methods to obtain users' payment history and behavioral data from payment service providers and data providers. This includes data collection via APIs, and a high-performance database server is one example of hardware used. This data may include previously visited stores and categories of products purchased.

[0371] Next, the server employs emotion analysis tools. Specifically, it uses deep learning models to process audio and image data to analyze the user's emotional state. This analysis utilizes an emotion AI engine, which can identify multiple emotional states, such as "joy" or "sadness."

[0372] Subsequently, the server uses recommendation generation tools to generate relevant information based on the analyzed emotional state and past purchase history data. For example, if the emotion of joy is detected, coupons for entertainment facilities can be generated.

[0373] Finally, the server uses an information transmission method to send the generated coupons and information to the device as a push notification. The device receives it and displays it to the user immediately. This allows the user to check available coupons and related information in real time.

[0374] As a concrete example, suppose a user is walking through a shopping mall and their smartphone's microphone picks up the sound of cheerful conversation. In this case, the server identifies the emotion of "joy," generates a discount coupon for the user's favorite amusement facility, and sends it to the device. The device displays a notification, and the user can use the coupon by tapping the notification.

[0375] An example of a prompt message would be, "Detect the emotions of users enjoying themselves from audio data within the shopping mall, and generate coupons tailored to those emotions." By inputting this prompt into the AI ​​generation model, it becomes possible to provide appropriate information.

[0376] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0377] Step 1:

[0378] The server uses information gathering tools to collect users' payment history and behavioral data from partner payment service providers and behavioral data providers. Data obtained via APIs as input includes store visit history and purchased product categories. This data is stored in a database and used as foundational information to identify users' past behavioral patterns.

[0379] Step 2:

[0380] The server uses emotion analysis tools to identify the user's emotional state by analyzing audio and image data. The input data consists of the user's voice and facial expressions, and the emotions are classified based on a deep learning model. This results in the output of labels such as "joy" or "sadness" as the emotional state.

[0381] Step 3:

[0382] The server uses a recommendation generation mechanism to match identified emotional states with past payment history and generate recommendations for the user. Inputs include analyzed emotional states and stored purchase history data, and relevant coupons and information are generated based on these. For example, if an emotional state is "joyful" and the user has frequently visited amusement facilities in the past, a coupon for a special offer at such facilities will be output.

[0383] Step 4:

[0384] The server sends the generated coupon information to the user's device as a push notification using the information transmission method. The input is the coupon information generated in step 3, which is immediately presented to the user when sent to the device. The device receives this information and displays it on the screen along with a notification sound.

[0385] Step 5:

[0386] Users can check notifications received on their devices and, if interested, tap on the notification to view more details. This allows them to activate and use available coupons. For example, a user could receive a coupon for an entertainment facility in a shopping mall, check it on the spot, and then visit the facility.

[0387] (Application Example 2)

[0388] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0389] In today's urban environment, users are surrounded by a vast amount of information, making it difficult to find the most relevant information and benefits for them. In particular, the lack of information tailored to users' emotional states limits their experiences. Therefore, an information delivery system that takes users' emotional states into consideration is needed.

[0390] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0391] In this invention, the server includes information acquisition means, data processing means, and emotion analysis means. This enables the provision of personalized information based on the user's emotional state.

[0392] "Information acquisition means" refers to a medium that has the function of collecting users' economic transaction history data and behavioral pattern data.

[0393] "Data processing means" refers to a medium that has the function of analyzing acquired economic transaction history data and behavioral pattern data to identify the user's past purchasing behavior patterns and behavioral history patterns.

[0394] An "emotion analysis tool" is a medium that has the function of identifying the emotional state of a user and generating information corresponding to that state.

[0395] An "emotion-linked recommendation generation method" is a medium that has the function of generating information based on the emotional state of the user identified by an emotion analysis method.

[0396] A "notification means" is a medium that has the function of notifying the user's device of the generated recommendation information.

[0397] The system based on this invention is designed to provide personalized information tailored to the user's emotional state.

[0398] First, the server uses information acquisition methods to collect users' economic transaction history data and behavioral pattern data. This includes data acquired through smartphones and wearable devices.

[0399] Next, the server uses data processing tools to analyze the acquired data and identify the user's past purchasing behavior patterns and behavioral history patterns. This analysis utilizes data mining techniques and machine learning algorithms.

[0400] The server then uses emotion analysis tools to identify the user's emotional state from their voice and facial image. Emotion analysis libraries such as the Affectiva SDK are sometimes used for this purpose. This analysis makes it possible to recognize emotions such as "joy" and "surprise" in real time.

[0401] The user's device receives information notified from the server and displays it on the screen. Depending on the notification method, recommendation information and coupons tailored to the user's emotional state are presented in a timely manner.

[0402] For example, if a user experiences a feeling of "surprise" when visiting a tourist destination, information about special exhibitions or events within the facility will be recommended. By implementing such a system, users can have experiences they might not have otherwise noticed.

[0403] An example of a prompt message is: "Create a program that analyzes emotional states obtained from voice data in real time and provides the latest information on city events."

[0404] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0405] Step 1:

[0406] The server collects economic transaction history data and behavioral pattern data from the user's smartphone or wearable device via information acquisition means. In this step, the user's transaction history and location information are provided as input, and this data is processed to convert it into an appropriate format for storage in the database. The output is a structured dataset.

[0407] Step 2:

[0408] The server uses data processing tools to analyze the collected data and identify the user's past purchasing behavior patterns and behavioral history patterns. In this step, the stored dataset is used as input, and calculations are performed to identify patterns using data mining techniques. The output is an analytical report showing the user's behavioral characteristics.

[0409] Step 3:

[0410] The server uses emotion analysis tools to analyze audio and facial data acquired from the user's device to identify their current emotional state. Real-time audio and video data are provided as input, and an emotion score is calculated using the Affectiva SDK. The output is tag information indicating the user's emotional state.

[0411] Step 4:

[0412] The server uses an emotion-driven recommendation generation method to generate appropriate recommendation information based on the obtained emotional state and analysis report. The analysis report and emotional state tags are used as input, and a generation AI model is applied based on this to perform calculations that generate suggestions suitable for the user. The output is customized recommendation data.

[0413] Step 5:

[0414] The terminal receives recommendation information sent from the server and displays it as a notification on the user's screen. The received recommendation data is used as input, and the system formats it for display on the user interface. The output is the specific suggestions displayed on the user's terminal.

[0415] Step 6:

[0416] The user reviews the displayed recommendation information and chooses an action based on the information that interests them. In this step, the user checks the notification, and the decision of what action to take is the output.

[0417] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0418] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0419] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0420] [Third Embodiment]

[0421] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0422] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0423] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0424] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0425] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0426] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0427] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0428] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0429] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0430] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0431] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0432] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0433] This invention is a system for efficiently acquiring and analyzing payment history data and behavioral data via users' smartphones and mobile devices to provide users with optimal store information and coupons. This system generates highly convenient recommendations based on the data analysis results and provides them to users via push notifications.

[0434] System configuration for carrying out the invention

[0435] The server collects users' payment history and behavioral data. This includes purchase date and time, location, amount, purchased product category, travel route, and visit frequency. The data is collected using partner service providers and location-based services.

[0436] The server analyzes the collected data to identify the user's past purchasing behavior and movement patterns. This allows, for example, to reveal the frequency of use in a particular area and the product categories of interest.

[0437] The server extracts relevant stores based on the user's current location. This identifies stores the user is likely to visit and generates customized coupons based on their past history.

[0438] The server sends the generated coupon information to the user's smartphone or mobile device via push notification. This allows users to receive special offers in real time, motivating them to visit stores.

[0439] Specific usage examples

[0440] For example, suppose a user frequently visits a particular cafe in the afternoon. The server analyzes the user's frequency of visits to that cafe and issues a special discount coupon when the user is near the cafe. At this time, the device displays the coupon as a pop-up notification on the screen, prompting the user to use it. If the user uses the coupon and completes the payment, the record is sent back to the server, and the history data is updated.

[0441] In this way, the system of the present invention is expected to provide users with an optimal purchasing experience without them even realizing it, and also to increase the store's ability to attract customers.

[0442] The following describes the processing flow.

[0443] Step 1:

[0444] The server retrieves user payment history data from partner payment service providers. This includes purchase date and time, store information, payment amount, and purchase category.

[0445] Step 2:

[0446] The device uses a GPS sensor to obtain the user's current location information and transmits it to the server. This location information is updated in real time.

[0447] Step 3:

[0448] The server analyzes user behavior patterns and store visit frequency based on past behavioral data. In particular, it identifies visit patterns for specific areas and stores.

[0449] Step 4:

[0450] The server uses the analysis results to search the database for stores near the user's current location and extracts stores that are likely to interest the user.

[0451] Step 5:

[0452] The server generates coupons optimized for each user based on the extracted stores, referencing past usage history and analysis results. These coupons include discounts and special offers.

[0453] Step 6:

[0454] The server sends the generated coupon information to the device as a push notification. The push notification includes information such as the coupon's validity period and the stores where it can be used.

[0455] Step 7:

[0456] The device displays a push notification for the coupon on the screen, prompting the user to confirm. If the user is interested in the coupon, they can tap it to view more details.

[0457] Step 8:

[0458] When a user uses a coupon to purchase an item at a participating store, the payment information is sent back to the server. This allows the transaction history to be updated in real time.

[0459] Step 9:

[0460] The server updates its database based on newly acquired usage history and continues the analysis process to improve the accuracy of recommendations for future use.

[0461] (Example 1)

[0462] Next, we will describe Example 1. 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."

[0463] Modern consumers seek efficient and personalized shopping experiences from a wide range of choices, but traditional sales promotion methods struggle to provide information tailored to individual consumer preferences and needs. Furthermore, retailers face the challenge of finding effective ways to attract customers.

[0464] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0465] In this invention, the server includes data collection means for collecting the user's transaction history and movement data; analysis means for analyzing the collected data and identifying the user's past purchase behavior and movement patterns; and recommendation generation means for extracting relevant nearby commercial facilities based on the user's current location information and generating discount information according to the analysis results. This allows consumers to receive promotional information tailored to their preferences in real time, and enables stores to attract customers effectively.

[0466] "Users" refer to individuals or corporations that receive services from this system, and are particularly those who are the target of data collection and analysis.

[0467] "Transaction history" refers to a collection of data that records a user's past purchasing activities, including details such as date, time, location, and product category.

[0468] "Movement data" refers to data related to the user's location information, indicating the user's travel routes and visit frequency.

[0469] "Data collection methods" refer to systems that collect information from partner providers and devices in order to obtain users' transaction history and movement data.

[0470] "Analysis methods" refer to technologies and algorithms used to identify user behavior patterns and interests based on collected data.

[0471] "Recommendation generation method" refers to the process of creating the most suitable coupons and promotional information for users based on analyzed data.

[0472] A "commercial facility" refers to a place or business that provides goods or services to users.

[0473] "Discount information" refers to information that temporarily lowers the price of goods or services, and refers to discounts offered to users.

[0474] "Information transmission means" refers to the communication technologies and protocols used to deliver generated discount information to the user's mobile device.

[0475] "History update method" refers to a method of updating the database based on the user's coupon usage results to improve the accuracy of future analyses.

[0476] This invention is a system aimed at enabling users to obtain an optimal purchasing experience based on their individual preferences and behaviors. The system primarily involves data collection, analysis, and the provision of information tailored to specific conditions.

[0477] First, the server automatically collects user transaction history and movement data through partner data providers and location services. This includes purchase date and time, product category, and location information. Cloud-based storage and APIs are used for data collection as a secure and efficient method.

[0478] Next, the server uses a dedicated analytical tool to analyze the collected data. Specifically, it utilizes a programming language like Python and the scikit-learn library to employ machine learning algorithms to identify user purchasing patterns and interests. As a result of the analysis, behavioral trends in specific time periods and geographical areas are recognized, and a different profile is formed for each user.

[0479] Next, the server extracts relevant facilities from nearby commercial establishments based on the user's current location. This generates optimal discount information for the commercial establishments the user is likely to visit. During this generation process, the following prompts are input using a generation AI model to maximize the use of discount information tailored to the user's preferences:

[0480] "Generate a coupon to be offered to a specific user on their next visit, based on their purchase history and current location."

[0481] Finally, the generated discount information is sent to the user's device in real time using a push notification service such as Firebase Cloud Messaging. The device immediately displays this information as a notification, presenting it to the user. The results of each discount offer are sent back to the server, and the database is constantly updated. This improves the accuracy of future information provision and enables a more personalized purchasing approach for the user.

[0482] Through this system, users can enjoy a more attractive shopping experience, and commercial facilities can expect to attract more customers effectively.

[0483] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0484] Step 1:

[0485] The server collects data from partner service providers and location services. Specifically, it obtains user transaction history (purchase date and time, product category, etc.) and movement data (location information, visit frequency, etc.) via APIs. The input consists of transaction history and location information corresponding to each user's ID, which is securely stored in cloud storage to form the initial dataset.

[0486] Step 2:

[0487] The server analyzes the collected data. The analysis uses the Python scikit-learn library and applies machine learning algorithms. Specifically, it analyzes user purchasing and movement patterns using clustering techniques. The input is the data collected in step 1, and the output is profile data showing the interests and tendencies of specific users. This enables user-specific targeting.

[0488] Step 3:

[0489] The server extracts relevant commercial facilities using the user's current location information. It searches for nearby stores centered on the user's current location using a geospatial database. The inputs are the user's location information obtained in real time and the profile data generated in step 2. The output is a targeted store list, which will be used for coupon generation later.

[0490] Step 4:

[0491] The server generates discount information using a generative AI model based on a targeted list of stores. It generates coupons optimized for each user based on their purchase history and current location using prompts. Specifically, it uses the prompt, "Generate a coupon to offer on the next visit based on a specific user's purchase history and current location." The inputs are the store list from step 3 and the profile data from step 2, and the output is personalized discount information for each user.

[0492] Step 5:

[0493] The server sends the generated discount information to the user's device via push notification. The coupon is delivered to the user's smartphone via a push notification service such as Firebase Cloud Messaging. The input is the discount information generated in step 4, and the output is a notification displayed on the user's device.

[0494] Step 6:

[0495] When a user uses a coupon and makes a purchase, that information is sent back to the server. The server uses this information to update the database and refine the user's profile. This improves the accuracy of targeting for future purchases and enables more effective recommendations.

[0496] (Application Example 1)

[0497] Next, we will explain Application Example 1. In the following explanation, 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."

[0498] Currently, many electronic payment systems and location-based services only provide users with unpersonalized information and benefits, making it difficult to offer optimized suggestions that reflect users' purchasing trends and behavioral patterns. As a result, users often miss opportunities to receive information that is truly valuable to them. Furthermore, this presents a problem for businesses, as they are unable to improve their customer acquisition efficiency.

[0499] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0500] In this invention, the server includes information gathering means for collecting user transaction history data and behavioral data; data analysis means for analyzing the collected data and identifying the user's past purchasing trends and behavioral patterns; suggestion generation means for extracting relevant facilities based on the user's current location information and generating special offers corresponding to the analysis results; and prompt generation means for creating prompt messages related to the user's tendencies using a generation AI model. This enables users to receive valuable information tailored to their preferences, and allows companies to attract customers efficiently.

[0501] "Transaction history data" refers to information that shows records of past purchases and payments made by a user.

[0502] "Behavioral data" refers to information about a user's physical behavior, such as their location, movement patterns, and frequency of visits.

[0503] "Information gathering means" refers to devices or methods for collecting users' transaction history data and behavioral data.

[0504] "Data analysis means" refers to a device or method for analyzing collected data to identify users' purchasing trends and behavioral patterns.

[0505] "Purchasing trends" refer to the behavioral tendencies based on what products and services a user has purchased in the past, as well as the frequency and patterns of those purchases.

[0506] "Behavioral patterns" refer to the patterns of movement and visits that users typically follow on a daily basis, indicating how often they visit specific locations.

[0507] "Privileges" refer to the provision of special discounts or services that allow users to enjoy benefits.

[0508] "Proposal generation means" refers to a device or method for generating customized benefits for users.

[0509] "Prompt generation means" refers to a device or method that uses a generation AI model to create instructional or suggestive statements based on the user's behavioral tendencies.

[0510] A "facility" refers to places, shops, or service providers that users may visit.

[0511] In the system that realizes this invention, a server, a user terminal, and a data processing program using a generation AI model work in conjunction. The server first collects the user's transaction history data and behavioral data from various sources. This includes the user's past purchase history and behavioral history such as location information and store visit frequency. Information collection is performed in real time using a cloud-based database.

[0512] Next, the server analyzes the collected data using data analysis tools to identify users' purchasing trends and behavioral patterns. This analysis utilizes Python data analysis libraries and machine learning algorithms. Specifically, Pandas and Scikit-learn can be used to format and analyze the data.

[0513] Based on the user's current location, the server utilizes location services to extract relevant facilities. This identifies stores and facilities that the user is likely to visit and generates promotional information related to those facilities. The promotional information is then generated using an AI model to create benefits tailored to the user's behavior patterns.

[0514] The generated promotional information is sent from the server to the user's device via push notification. Push technologies such as Firebase Cloud Messaging are used for this notification. By receiving this promotional information, users can take advantage of benefits that are beneficial to their purchasing behavior in a timely manner.

[0515] As a concrete example, when a user approaches a cafe they frequent, a 10% discount coupon offered by that cafe is sent to the user's smartphone. This coupon is generated based on the server's analysis of the user's past purchase history and location information.

[0516] An example of a prompt for a generative AI model would be: "The user tends to buy coffee at a specific cafe every morning. Create a discount suggestion to offer the user the next time they visit that cafe." This allows the user to receive advantageous information tailored to their individual needs.

[0517] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0518] Step 1:

[0519] The server collects user transaction history and behavioral data. Inputs include purchase history, location information, and visit frequency, while output is an information database summarizing this data. The server retrieves data from partner service APIs and GPS devices and records it in the cloud database.

[0520] Step 2:

[0521] The server analyzes the collected data. The input is an information database, and the output is an analysis showing users' purchasing trends and behavioral patterns. The server uses Python's Pandas library to format the data and machine learning algorithms to predict behavioral patterns.

[0522] Step 3:

[0523] The server extracts relevant facilities based on the user's current location information. The input is the user's real-time location data and the analysis results from the previous step, and the output is a list of highly relevant facilities. The server retrieves current data from location information services and matches it with the level of interest information obtained from data analysis.

[0524] Step 4:

[0525] The server generates special offers based on the extracted information. The input is a list of facilities and the purchasing trends of users, and the output is customized special offer information. The server runs a generation AI model, creates prompt messages, and generates the most suitable special offer.

[0526] Step 5:

[0527] The server sends the generated special offer information as a push notification to the user's device. The input is the special offer information, and the output is the user's device that received the notification. The server uses Firebase Cloud Messaging to send the special offer information in real time.

[0528] Step 6:

[0529] The user checks the received discount information, visits the store as needed, and uses the coupon. The input is the discount information sent to the device, and the output is the history data of used coupons. The user checks the notification on the device and takes advantage of newly generated discounts.

[0530] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0531] This invention is an information provision system that takes into account the emotional state of users. By analyzing the user's payment history, behavioral data, and emotional state, the system provides the most suitable coupons and related information to the user. This system uses an emotion engine to identify the user's emotional state and generate customized recommendations based on that state.

[0532] System configuration for carrying out the invention

[0533] The server collects users' payment history and behavioral data from partner payment service providers and behavioral data providers. This includes information about stores visited in the past and the categories of products purchased.

[0534] The server uses an emotion engine to analyze the emotional state of the user's current situation. At this stage, it uses data obtained from voice input and facial imagery to identify multiple emotional states the person may be experiencing (e.g., joy, sadness, surprise, etc.).

[0535] The server selects appropriate store information and coupons based on the user's emotional state and past purchase history. By adjusting the information delivered according to the analysis results of the emotion engine, it presents benefits tailored to the user's current emotions.

[0536] The server sends the selected coupon information to the device as a push notification. The device receives the notification and displays it on the user's screen.

[0537] Specific usage examples

[0538] For example, consider a scenario where a user is walking through a shopping mall and joyful laughter is detected in the audio data. Based on this information, the server identifies the emotion of "joy." The server then generates a special coupon for an entertainment facility or amusement-related product that the user has previously enjoyed. This coupon is delivered to the user in real time via their device, and the user checks the notification and chooses to visit the facility.

[0539] In this way, this system responds sensitively to users' emotions, providing a more personalized shopping experience and contributing to increased user satisfaction. Furthermore, it enables stores to target customers based on their emotions, allowing for more efficient promotions.

[0540] The following describes the processing flow.

[0541] Step 1:

[0542] The server receives payment history data from the payment provider. This data includes information about the goods and services the user has purchased in the past.

[0543] Step 2:

[0544] The device uses built-in sensors (camera and microphone) to detect the user's facial expressions and voice tone, and transmits that data to the emotion engine.

[0545] Step 3:

[0546] The server activates an emotion engine to analyze the audio and image data sent by the user. This identifies the user's emotional state (joy, surprise, sadness, etc.).

[0547] Step 4:

[0548] The server combines collected payment history and emotional states to identify stores and products that best match the user's current interests and preferences.

[0549] Step 5:

[0550] The server generates the most suitable coupons or special offers based on the identified store or product. This includes messages tailored to the user's emotional state.

[0551] Step 6:

[0552] The server sends the generated coupon information or special offer to the device in the form of a push notification.

[0553] Step 7:

[0554] The device displays received notifications to the user and provides access to detailed information through an engaging interface.

[0555] Step 8:

[0556] When a user uses a coupon to purchase an item at a store, that information is sent back to the server and stored in the database as part of their usage history.

[0557] Step 9:

[0558] The server initiates an analysis process based on the new usage history stored in the database, contributing to improving the accuracy of the system for future recommendations.

[0559] (Example 2)

[0560] Next, we will describe Example 2. 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."

[0561] Conventional information provision systems are limited to providing information based on users' past purchase history and behavioral patterns, and have the challenge of not being able to provide appropriate recommendations that take into account the user's emotional state. In addition, delays and decreased accuracy in real-time information provision also affect user satisfaction.

[0562] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0563] In this invention, the server includes information gathering means for collecting the user's payment history and behavioral data, sentiment analysis means for analyzing the collected data and identifying the user's emotional state, and recommendation generation means for generating relevant information based on the emotional state and purchase history data. This enables the provision of personalized information that corresponds to the user's emotional state.

[0564] "Information gathering means" refers to functions or devices for effectively collecting users' payment history and behavioral data.

[0565] "Emotional analysis means" refers to a function or device that analyzes and identifies a user's emotional state using audio data and image data based on collected data.

[0566] "Recommendation generation means" refers to a function or device that generates information or coupons related to the user based on analyzed emotional state and purchase history data.

[0567] "Information transmission means" refers to a function or device for notifying a user device of the generated information.

[0568] "Location information acquisition means" refers to a function or device for acquiring location information from a user device and determining the user's current location.

[0569] This system is designed to provide information that takes into account the user's emotional state. Specifically, the server acts as the core, collecting and analyzing various data to provide customized recommendations.

[0570] First, the server uses information gathering methods to obtain users' payment history and behavioral data from payment service providers and data providers. This includes data collection via APIs, and a high-performance database server is one example of hardware used. This data may include previously visited stores and categories of products purchased.

[0571] Next, the server employs emotion analysis tools. Specifically, it uses deep learning models to process audio and image data to analyze the user's emotional state. This analysis utilizes an emotion AI engine, which can identify multiple emotional states, such as "joy" or "sadness."

[0572] Subsequently, the server uses recommendation generation tools to generate relevant information based on the analyzed emotional state and past purchase history data. For example, if the emotion of joy is detected, coupons for entertainment facilities can be generated.

[0573] Finally, the server uses an information transmission method to send the generated coupons and information to the device as a push notification. The device receives it and displays it to the user immediately. This allows the user to check available coupons and related information in real time.

[0574] As a concrete example, suppose a user is walking through a shopping mall and their smartphone's microphone picks up the sound of cheerful conversation. In this case, the server identifies the emotion of "joy," generates a discount coupon for the user's favorite amusement facility, and sends it to the device. The device displays a notification, and the user can use the coupon by tapping the notification.

[0575] An example of a prompt message would be, "Detect the emotions of users enjoying themselves from audio data within the shopping mall, and generate coupons tailored to those emotions." By inputting this prompt into the AI ​​generation model, it becomes possible to provide appropriate information.

[0576] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0577] Step 1:

[0578] The server uses information gathering tools to collect users' payment history and behavioral data from partner payment service providers and behavioral data providers. Data obtained via APIs as input includes store visit history and purchased product categories. This data is stored in a database and used as foundational information to identify users' past behavioral patterns.

[0579] Step 2:

[0580] The server uses emotion analysis tools to identify the user's emotional state by analyzing audio and image data. The input data consists of the user's voice and facial expressions, and the emotions are classified based on a deep learning model. This results in the output of labels such as "joy" or "sadness" as the emotional state.

[0581] Step 3:

[0582] The server uses a recommendation generation mechanism to match identified emotional states with past payment history and generate recommendations for the user. Inputs include analyzed emotional states and stored purchase history data, and relevant coupons and information are generated based on these. For example, if an emotional state is "joyful" and the user has frequently visited amusement facilities in the past, a coupon for a special offer at such facilities will be output.

[0583] Step 4:

[0584] The server sends the generated coupon information to the user's device as a push notification using the information transmission method. The input is the coupon information generated in step 3, which is immediately presented to the user when sent to the device. The device receives this information and displays it on the screen along with a notification sound.

[0585] Step 5:

[0586] Users can check notifications received on their devices and, if interested, tap on the notification to view more details. This allows them to activate and use available coupons. For example, a user could receive a coupon for an entertainment facility in a shopping mall, check it on the spot, and then visit the facility.

[0587] (Application Example 2)

[0588] Next, we will explain application example 2. In the following explanation, 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."

[0589] In today's urban environment, users are surrounded by a vast amount of information, making it difficult to find the most relevant information and benefits for them. In particular, the lack of information tailored to users' emotional states limits their experiences. Therefore, an information delivery system that takes users' emotional states into consideration is needed.

[0590] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0591] In this invention, the server includes information acquisition means, data processing means, and emotion analysis means. This enables the provision of personalized information based on the user's emotional state.

[0592] "Information acquisition means" refers to a medium that has the function of collecting users' economic transaction history data and behavioral pattern data.

[0593] "Data processing means" refers to a medium that has the function of analyzing acquired economic transaction history data and behavioral pattern data to identify the user's past purchasing behavior patterns and behavioral history patterns.

[0594] An "emotion analysis tool" is a medium that has the function of identifying the emotional state of a user and generating information corresponding to that state.

[0595] An "emotion-linked recommendation generation method" is a medium that has the function of generating information based on the emotional state of the user identified by an emotion analysis method.

[0596] A "notification means" is a medium that has the function of notifying the user's device of the generated recommendation information.

[0597] The system based on this invention is designed to provide personalized information tailored to the user's emotional state.

[0598] First, the server uses information acquisition methods to collect users' economic transaction history data and behavioral pattern data. This includes data acquired through smartphones and wearable devices.

[0599] Next, the server uses data processing tools to analyze the acquired data and identify the user's past purchasing behavior patterns and behavioral history patterns. This analysis utilizes data mining techniques and machine learning algorithms.

[0600] The server then uses emotion analysis tools to identify the user's emotional state from their voice and facial image. Emotion analysis libraries such as the Affectiva SDK are sometimes used for this purpose. This analysis makes it possible to recognize emotions such as "joy" and "surprise" in real time.

[0601] The user's device receives information notified from the server and displays it on the screen. Depending on the notification method, recommendation information and coupons tailored to the user's emotional state are presented in a timely manner.

[0602] For example, if a user experiences a feeling of "surprise" when visiting a tourist destination, information about special exhibitions or events within the facility will be recommended. By implementing such a system, users can have experiences they might not have otherwise noticed.

[0603] An example of a prompt message is: "Create a program that analyzes emotional states obtained from voice data in real time and provides the latest information on city events."

[0604] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0605] Step 1:

[0606] The server collects economic transaction history data and behavioral pattern data from the user's smartphone or wearable device via information acquisition means. In this step, the user's transaction history and location information are provided as input, and this data is processed to convert it into an appropriate format for storage in the database. The output is a structured dataset.

[0607] Step 2:

[0608] The server uses data processing tools to analyze the collected data and identify the user's past purchasing behavior patterns and behavioral history patterns. In this step, the stored dataset is used as input, and calculations are performed to identify patterns using data mining techniques. The output is an analytical report showing the user's behavioral characteristics.

[0609] Step 3:

[0610] The server uses emotion analysis tools to analyze audio and facial data acquired from the user's device to identify their current emotional state. Real-time audio and video data are provided as input, and an emotion score is calculated using the Affectiva SDK. The output is tag information indicating the user's emotional state.

[0611] Step 4:

[0612] The server uses an emotion-driven recommendation generation method to generate appropriate recommendation information based on the obtained emotional state and analysis report. The analysis report and emotional state tags are used as input, and a generation AI model is applied based on this to perform calculations that generate suggestions suitable for the user. The output is customized recommendation data.

[0613] Step 5:

[0614] The terminal receives recommendation information sent from the server and displays it as a notification on the user's screen. The received recommendation data is used as input, and the system formats it for display on the user interface. The output is the specific suggestions displayed on the user's terminal.

[0615] Step 6:

[0616] The user reviews the displayed recommendation information and chooses an action based on the information that interests them. In this step, the user checks the notification, and the decision of what action to take is the output.

[0617] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0618] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0619] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0620] [Fourth Embodiment]

[0621] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0622] As shown in Figure 7, the 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.

[0623] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0624] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0625] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0626] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0627] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0628] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0629] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0630] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0631] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0632] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0633] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0634] This invention is a system for efficiently acquiring and analyzing payment history data and behavioral data via users' smartphones and mobile devices to provide users with optimal store information and coupons. This system generates highly convenient recommendations based on the data analysis results and provides them to users via push notifications.

[0635] System configuration for carrying out the invention

[0636] The server collects users' payment history and behavioral data. This includes purchase date and time, location, amount, purchased product category, travel route, and visit frequency. The data is collected using partner service providers and location-based services.

[0637] The server analyzes the collected data to identify the user's past purchasing behavior and movement patterns. This allows, for example, to reveal the frequency of use in a particular area and the product categories of interest.

[0638] The server extracts relevant stores based on the user's current location. This identifies stores the user is likely to visit and generates customized coupons based on their past history.

[0639] The server sends the generated coupon information to the user's smartphone or mobile device via push notification. This allows users to receive special offers in real time, motivating them to visit stores.

[0640] Specific usage examples

[0641] For example, suppose a user frequently visits a particular cafe in the afternoon. The server analyzes the user's frequency of visits to that cafe and issues a special discount coupon when the user is near the cafe. At this time, the device displays the coupon as a pop-up notification on the screen, prompting the user to use it. If the user uses the coupon and completes the payment, the record is sent back to the server, and the history data is updated.

[0642] In this way, the system of the present invention is expected to provide users with an optimal purchasing experience without them even realizing it, and also to increase the store's ability to attract customers.

[0643] The following describes the processing flow.

[0644] Step 1:

[0645] The server retrieves user payment history data from partner payment service providers. This includes purchase date and time, store information, payment amount, and purchase category.

[0646] Step 2:

[0647] The device uses a GPS sensor to obtain the user's current location information and transmits it to the server. This location information is updated in real time.

[0648] Step 3:

[0649] The server analyzes user behavior patterns and store visit frequency based on past behavioral data. In particular, it identifies visit patterns for specific areas and stores.

[0650] Step 4:

[0651] The server uses the analysis results to search the database for stores near the user's current location and extracts stores that are likely to interest the user.

[0652] Step 5:

[0653] The server generates coupons optimized for each user based on the extracted stores, referencing past usage history and analysis results. These coupons include discounts and special offers.

[0654] Step 6:

[0655] The server sends the generated coupon information to the device as a push notification. The push notification includes information such as the coupon's validity period and the stores where it can be used.

[0656] Step 7:

[0657] The device displays a push notification for the coupon on the screen, prompting the user to confirm. If the user is interested in the coupon, they can tap it to view more details.

[0658] Step 8:

[0659] When a user uses a coupon to purchase an item at a participating store, the payment information is sent back to the server. This allows the transaction history to be updated in real time.

[0660] Step 9:

[0661] The server updates its database based on newly acquired usage history and continues the analysis process to improve the accuracy of recommendations for future use.

[0662] (Example 1)

[0663] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0664] Modern consumers seek efficient and personalized shopping experiences from a wide range of choices, but traditional sales promotion methods struggle to provide information tailored to individual consumer preferences and needs. Furthermore, retailers face the challenge of finding effective ways to attract customers.

[0665] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0666] In this invention, the server includes data collection means for collecting the user's transaction history and movement data; analysis means for analyzing the collected data and identifying the user's past purchase behavior and movement patterns; and recommendation generation means for extracting relevant nearby commercial facilities based on the user's current location information and generating discount information according to the analysis results. This allows consumers to receive promotional information tailored to their preferences in real time, and enables stores to attract customers effectively.

[0667] "Users" refer to individuals or corporations that receive services from this system, and are particularly those who are the target of data collection and analysis.

[0668] "Transaction history" refers to a collection of data that records a user's past purchasing activities, including details such as date, time, location, and product category.

[0669] "Movement data" refers to data related to the user's location information, indicating the user's travel routes and visit frequency.

[0670] "Data collection methods" refer to systems that collect information from partner providers and devices in order to obtain users' transaction history and movement data.

[0671] "Analysis methods" refer to technologies and algorithms used to identify user behavior patterns and interests based on collected data.

[0672] "Recommendation generation method" refers to the process of creating the most suitable coupons and promotional information for users based on analyzed data.

[0673] A "commercial facility" refers to a place or business that provides goods or services to users.

[0674] "Discount information" refers to information that temporarily lowers the price of goods or services, and refers to discounts offered to users.

[0675] "Information transmission means" refers to the communication technologies and protocols used to deliver generated discount information to the user's mobile device.

[0676] "History update method" refers to a method of updating the database based on the user's coupon usage results to improve the accuracy of future analyses.

[0677] This invention is a system aimed at enabling users to obtain an optimal purchasing experience based on their individual preferences and behaviors. The system primarily involves data collection, analysis, and the provision of information tailored to specific conditions.

[0678] First, the server automatically collects user transaction history and movement data through partner data providers and location services. This includes purchase date and time, product category, and location information. Cloud-based storage and APIs are used for data collection as a secure and efficient method.

[0679] Next, the server uses a dedicated analytical tool to analyze the collected data. Specifically, it utilizes a programming language like Python and the scikit-learn library to employ machine learning algorithms to identify user purchasing patterns and interests. As a result of the analysis, behavioral trends in specific time periods and geographical areas are recognized, and a different profile is formed for each user.

[0680] Next, the server extracts relevant facilities from nearby commercial establishments based on the user's current location. This generates optimal discount information for the commercial establishments the user is likely to visit. During this generation process, the following prompts are input using a generation AI model to maximize the use of discount information tailored to the user's preferences:

[0681] "Generate a coupon to be offered to a specific user on their next visit, based on their purchase history and current location."

[0682] Finally, the generated discount information is sent to the user's device in real time using a push notification service such as Firebase Cloud Messaging. The device immediately displays this information as a notification, presenting it to the user. The results of each discount offer are sent back to the server, and the database is constantly updated. This improves the accuracy of future information provision and enables a more personalized purchasing approach for the user.

[0683] Through this system, users can enjoy a more attractive shopping experience, and commercial facilities can expect to attract more customers effectively.

[0684] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0685] Step 1:

[0686] The server collects data from partner service providers and location services. Specifically, it obtains user transaction history (purchase date and time, product category, etc.) and movement data (location information, visit frequency, etc.) via APIs. The input consists of transaction history and location information corresponding to each user's ID, which is securely stored in cloud storage to form the initial dataset.

[0687] Step 2:

[0688] The server analyzes the collected data. The analysis uses the Python scikit-learn library and applies machine learning algorithms. Specifically, it analyzes user purchasing and movement patterns using clustering techniques. The input is the data collected in step 1, and the output is profile data showing the interests and tendencies of specific users. This enables user-specific targeting.

[0689] Step 3:

[0690] The server extracts relevant commercial facilities using the user's current location information. It searches for nearby stores centered on the user's current location using a geospatial database. The inputs are the user's location information obtained in real time and the profile data generated in step 2. The output is a targeted store list, which will be used for coupon generation later.

[0691] Step 4:

[0692] The server generates discount information using a generative AI model based on a targeted list of stores. It generates coupons optimized for each user based on their purchase history and current location using prompts. Specifically, it uses the prompt, "Generate a coupon to offer on the next visit based on a specific user's purchase history and current location." The inputs are the store list from step 3 and the profile data from step 2, and the output is personalized discount information for each user.

[0693] Step 5:

[0694] The server sends the generated discount information to the user's device via push notification. The coupon is delivered to the user's smartphone via a push notification service such as Firebase Cloud Messaging. The input is the discount information generated in step 4, and the output is a notification displayed on the user's device.

[0695] Step 6:

[0696] When a user uses a coupon and makes a purchase, that information is sent back to the server. The server uses this information to update the database and refine the user's profile. This improves the accuracy of targeting for future purchases and enables more effective recommendations.

[0697] (Application Example 1)

[0698] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0699] Currently, many electronic payment systems and location-based services only provide users with unpersonalized information and benefits, making it difficult to offer optimized suggestions that reflect users' purchasing trends and behavioral patterns. As a result, users often miss opportunities to receive information that is truly valuable to them. Furthermore, this presents a problem for businesses, as they are unable to improve their customer acquisition efficiency.

[0700] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0701] In this invention, the server includes information gathering means for collecting user transaction history data and behavioral data; data analysis means for analyzing the collected data and identifying the user's past purchasing trends and behavioral patterns; suggestion generation means for extracting relevant facilities based on the user's current location information and generating special offers corresponding to the analysis results; and prompt generation means for creating prompt messages related to the user's tendencies using a generation AI model. This enables users to receive valuable information tailored to their preferences, and allows companies to attract customers efficiently.

[0702] "Transaction history data" refers to information that shows records of past purchases and payments made by a user.

[0703] "Behavioral data" refers to information about a user's physical behavior, such as their location, movement patterns, and frequency of visits.

[0704] "Information gathering means" refers to devices or methods for collecting users' transaction history data and behavioral data.

[0705] "Data analysis means" refers to a device or method for analyzing collected data to identify users' purchasing trends and behavioral patterns.

[0706] "Purchasing trends" refer to the behavioral tendencies based on what products and services a user has purchased in the past, as well as the frequency and patterns of those purchases.

[0707] "Behavioral patterns" refer to the patterns of movement and visits that users typically follow on a daily basis, indicating how often they visit specific locations.

[0708] "Privileges" refer to the provision of special discounts or services that allow users to enjoy benefits.

[0709] "Proposal generation means" refers to a device or method for generating customized benefits for users.

[0710] "Prompt generation means" refers to a device or method that uses a generation AI model to create instructional or suggestive statements based on the user's behavioral tendencies.

[0711] A "facility" refers to places, shops, or service providers that users may visit.

[0712] In the system that realizes this invention, a server, a user terminal, and a data processing program using a generation AI model work in conjunction. The server first collects the user's transaction history data and behavioral data from various sources. This includes the user's past purchase history and behavioral history such as location information and store visit frequency. Information collection is performed in real time using a cloud-based database.

[0713] Next, the server analyzes the collected data using data analysis tools to identify users' purchasing trends and behavioral patterns. This analysis utilizes Python data analysis libraries and machine learning algorithms. Specifically, Pandas and Scikit-learn can be used to format and analyze the data.

[0714] Based on the user's current location, the server utilizes location services to extract relevant facilities. This identifies stores and facilities that the user is likely to visit and generates promotional information related to those facilities. The promotional information is then generated using an AI model to create benefits tailored to the user's behavior patterns.

[0715] The generated promotional information is sent from the server to the user's device via push notification. Push technologies such as Firebase Cloud Messaging are used for this notification. By receiving this promotional information, users can take advantage of benefits that are beneficial to their purchasing behavior in a timely manner.

[0716] As a concrete example, when a user approaches a cafe they frequent, a 10% discount coupon offered by that cafe is sent to the user's smartphone. This coupon is generated based on the server's analysis of the user's past purchase history and location information.

[0717] An example of a prompt for a generative AI model would be: "The user tends to buy coffee at a specific cafe every morning. Create a discount suggestion to offer the user the next time they visit that cafe." This allows the user to receive advantageous information tailored to their individual needs.

[0718] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0719] Step 1:

[0720] The server collects user transaction history and behavioral data. Inputs include purchase history, location information, and visit frequency, while output is an information database summarizing this data. The server retrieves data from partner service APIs and GPS devices and records it in the cloud database.

[0721] Step 2:

[0722] The server analyzes the collected data. The input is an information database, and the output is an analysis showing users' purchasing trends and behavioral patterns. The server uses Python's Pandas library to format the data and machine learning algorithms to predict behavioral patterns.

[0723] Step 3:

[0724] The server extracts relevant facilities based on the user's current location information. The input is the user's real-time location data and the analysis results from the previous step, and the output is a list of highly relevant facilities. The server retrieves current data from location information services and matches it with the level of interest information obtained from data analysis.

[0725] Step 4:

[0726] The server generates special offers based on the extracted information. The input is a list of facilities and the purchasing trends of users, and the output is customized special offer information. The server runs a generation AI model, creates prompt messages, and generates the most suitable special offer.

[0727] Step 5:

[0728] The server sends the generated special offer information as a push notification to the user's device. The input is the special offer information, and the output is the user's device that received the notification. The server uses Firebase Cloud Messaging to send the special offer information in real time.

[0729] Step 6:

[0730] The user checks the received discount information, visits the store as needed, and uses the coupon. The input is the discount information sent to the device, and the output is the history data of used coupons. The user checks the notification on the device and takes advantage of newly generated discounts.

[0731] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0732] This invention is an information provision system that takes into account the emotional state of users. By analyzing the user's payment history, behavioral data, and emotional state, the system provides the most suitable coupons and related information to the user. This system uses an emotion engine to identify the user's emotional state and generate customized recommendations based on that state.

[0733] System configuration for carrying out the invention

[0734] The server collects users' payment history and behavioral data from partner payment service providers and behavioral data providers. This includes information about stores visited in the past and the categories of products purchased.

[0735] The server uses an emotion engine to analyze the emotional state of the user's current situation. At this stage, it uses data obtained from voice input and facial imagery to identify multiple emotional states the person may be experiencing (e.g., joy, sadness, surprise, etc.).

[0736] The server selects appropriate store information and coupons based on the user's emotional state and past purchase history. By adjusting the information delivered according to the analysis results of the emotion engine, it presents benefits tailored to the user's current emotions.

[0737] The server sends the selected coupon information to the device as a push notification. The device receives the notification and displays it on the user's screen.

[0738] Specific usage examples

[0739] For example, consider a scenario where a user is walking through a shopping mall and joyful laughter is detected in the audio data. Based on this information, the server identifies the emotion of "joy." The server then generates a special coupon for an entertainment facility or amusement-related product that the user has previously enjoyed. This coupon is delivered to the user in real time via their device, and the user checks the notification and chooses to visit the facility.

[0740] In this way, this system responds sensitively to users' emotions, providing a more personalized shopping experience and contributing to increased user satisfaction. Furthermore, it enables stores to target customers based on their emotions, allowing for more efficient promotions.

[0741] The following describes the processing flow.

[0742] Step 1:

[0743] The server receives payment history data from the payment provider. This data includes information about the goods and services the user has purchased in the past.

[0744] Step 2:

[0745] The device uses built-in sensors (camera and microphone) to detect the user's facial expressions and voice tone, and transmits that data to the emotion engine.

[0746] Step 3:

[0747] The server activates an emotion engine to analyze the audio and image data sent by the user. This identifies the user's emotional state (joy, surprise, sadness, etc.).

[0748] Step 4:

[0749] The server combines collected payment history and emotional states to identify stores and products that best match the user's current interests and preferences.

[0750] Step 5:

[0751] The server generates the most suitable coupons or special offers based on the identified store or product. This includes messages tailored to the user's emotional state.

[0752] Step 6:

[0753] The server sends the generated coupon information or special offer to the device in the form of a push notification.

[0754] Step 7:

[0755] The device displays received notifications to the user and provides access to detailed information through an engaging interface.

[0756] Step 8:

[0757] When a user uses a coupon to purchase an item at a store, that information is sent back to the server and stored in the database as part of their usage history.

[0758] Step 9:

[0759] The server initiates an analysis process based on the new usage history stored in the database, contributing to improving the accuracy of the system for future recommendations.

[0760] (Example 2)

[0761] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0762] Conventional information provision systems are limited to providing information based on users' past purchase history and behavioral patterns, and have the challenge of not being able to provide appropriate recommendations that take into account the user's emotional state. In addition, delays and decreased accuracy in real-time information provision also affect user satisfaction.

[0763] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0764] In this invention, the server includes information gathering means for collecting the user's payment history and behavioral data, sentiment analysis means for analyzing the collected data and identifying the user's emotional state, and recommendation generation means for generating relevant information based on the emotional state and purchase history data. This enables the provision of personalized information that corresponds to the user's emotional state.

[0765] "Information gathering means" refers to functions or devices for effectively collecting users' payment history and behavioral data.

[0766] "Emotional analysis means" refers to a function or device that analyzes and identifies a user's emotional state using audio data and image data based on collected data.

[0767] "Recommendation generation means" refers to a function or device that generates information or coupons related to the user based on analyzed emotional state and purchase history data.

[0768] "Information transmission means" refers to a function or device for notifying a user device of the generated information.

[0769] "Location information acquisition means" refers to a function or device for acquiring location information from a user device and determining the user's current location.

[0770] This system is designed to provide information that takes into account the user's emotional state. Specifically, the server acts as the core, collecting and analyzing various data to provide customized recommendations.

[0771] First, the server uses information gathering methods to obtain users' payment history and behavioral data from payment service providers and data providers. This includes data collection via APIs, and a high-performance database server is one example of hardware used. This data may include previously visited stores and categories of products purchased.

[0772] Next, the server employs emotion analysis tools. Specifically, it uses deep learning models to process audio and image data to analyze the user's emotional state. This analysis utilizes an emotion AI engine, which can identify multiple emotional states, such as "joy" or "sadness."

[0773] Subsequently, the server uses recommendation generation tools to generate relevant information based on the analyzed emotional state and past purchase history data. For example, if the emotion of joy is detected, coupons for entertainment facilities can be generated.

[0774] Finally, the server uses an information transmission method to send the generated coupons and information to the device as a push notification. The device receives it and displays it to the user immediately. This allows the user to check available coupons and related information in real time.

[0775] As a concrete example, suppose a user is walking through a shopping mall and their smartphone's microphone picks up the sound of cheerful conversation. In this case, the server identifies the emotion of "joy," generates a discount coupon for the user's favorite amusement facility, and sends it to the device. The device displays a notification, and the user can use the coupon by tapping the notification.

[0776] An example of a prompt message would be, "Detect the emotions of users enjoying themselves from audio data within the shopping mall, and generate coupons tailored to those emotions." By inputting this prompt into the AI ​​generation model, it becomes possible to provide appropriate information.

[0777] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0778] Step 1:

[0779] The server uses information gathering tools to collect users' payment history and behavioral data from partner payment service providers and behavioral data providers. Data obtained via APIs as input includes store visit history and purchased product categories. This data is stored in a database and used as foundational information to identify users' past behavioral patterns.

[0780] Step 2:

[0781] The server uses emotion analysis tools to identify the user's emotional state by analyzing audio and image data. The input data consists of the user's voice and facial expressions, and the emotions are classified based on a deep learning model. This results in the output of labels such as "joy" or "sadness" as the emotional state.

[0782] Step 3:

[0783] The server uses a recommendation generation mechanism to match identified emotional states with past payment history and generate recommendations for the user. Inputs include analyzed emotional states and stored purchase history data, and relevant coupons and information are generated based on these. For example, if an emotional state is "joyful" and the user has frequently visited amusement facilities in the past, a coupon for a special offer at such facilities will be output.

[0784] Step 4:

[0785] The server sends the generated coupon information to the user's device as a push notification using the information transmission method. The input is the coupon information generated in step 3, which is immediately presented to the user when sent to the device. The device receives this information and displays it on the screen along with a notification sound.

[0786] Step 5:

[0787] Users can check notifications received on their devices and, if interested, tap on the notification to view more details. This allows them to activate and use available coupons. For example, a user could receive a coupon for an entertainment facility in a shopping mall, check it on the spot, and then visit the facility.

[0788] (Application Example 2)

[0789] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0790] In today's urban environment, users are surrounded by a vast amount of information, making it difficult to find the most relevant information and benefits for them. In particular, the lack of information tailored to users' emotional states limits their experiences. Therefore, an information delivery system that takes users' emotional states into consideration is needed.

[0791] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0792] In this invention, the server includes information acquisition means, data processing means, and emotion analysis means. This enables the provision of personalized information based on the user's emotional state.

[0793] "Information acquisition means" refers to a medium that has the function of collecting users' economic transaction history data and behavioral pattern data.

[0794] "Data processing means" refers to a medium that has the function of analyzing acquired economic transaction history data and behavioral pattern data to identify the user's past purchasing behavior patterns and behavioral history patterns.

[0795] An "emotion analysis tool" is a medium that has the function of identifying the emotional state of a user and generating information corresponding to that state.

[0796] An "emotion-linked recommendation generation method" is a medium that has the function of generating information based on the emotional state of the user identified by an emotion analysis method.

[0797] A "notification means" is a medium that has the function of notifying the user's device of the generated recommendation information.

[0798] The system based on this invention is designed to provide personalized information tailored to the user's emotional state.

[0799] First, the server uses information acquisition methods to collect users' economic transaction history data and behavioral pattern data. This includes data acquired through smartphones and wearable devices.

[0800] Next, the server uses data processing tools to analyze the acquired data and identify the user's past purchasing behavior patterns and behavioral history patterns. This analysis utilizes data mining techniques and machine learning algorithms.

[0801] The server then uses emotion analysis tools to identify the user's emotional state from their voice and facial image. Emotion analysis libraries such as the Affectiva SDK are sometimes used for this purpose. This analysis makes it possible to recognize emotions such as "joy" and "surprise" in real time.

[0802] The user's device receives information notified from the server and displays it on the screen. Depending on the notification method, recommendation information and coupons tailored to the user's emotional state are presented in a timely manner.

[0803] For example, if a user experiences a feeling of "surprise" when visiting a tourist destination, information about special exhibitions or events within the facility will be recommended. By implementing such a system, users can have experiences they might not have otherwise noticed.

[0804] An example of a prompt message is: "Create a program that analyzes emotional states obtained from voice data in real time and provides the latest information on city events."

[0805] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0806] Step 1:

[0807] The server collects economic transaction history data and behavioral pattern data from the user's smartphone or wearable device via information acquisition means. In this step, the user's transaction history and location information are provided as input, and this data is processed to convert it into an appropriate format for storage in the database. The output is a structured dataset.

[0808] Step 2:

[0809] The server uses data processing tools to analyze the collected data and identify the user's past purchasing behavior patterns and behavioral history patterns. In this step, the stored dataset is used as input, and calculations are performed to identify patterns using data mining techniques. The output is an analytical report showing the user's behavioral characteristics.

[0810] Step 3:

[0811] The server uses emotion analysis tools to analyze audio and facial data acquired from the user's device to identify their current emotional state. Real-time audio and video data are provided as input, and an emotion score is calculated using the Affectiva SDK. The output is tag information indicating the user's emotional state.

[0812] Step 4:

[0813] The server uses an emotion-driven recommendation generation method to generate appropriate recommendation information based on the obtained emotional state and analysis report. The analysis report and emotional state tags are used as input, and a generation AI model is applied based on this to perform calculations that generate suggestions suitable for the user. The output is customized recommendation data.

[0814] Step 5:

[0815] The terminal receives recommendation information sent from the server and displays it as a notification on the user's screen. The received recommendation data is used as input, and the system formats it for display on the user interface. The output is the specific suggestions displayed on the user's terminal.

[0816] Step 6:

[0817] The user reviews the displayed recommendation information and chooses an action based on the information that interests them. In this step, the user checks the notification, and the decision of what action to take is the output.

[0818] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0819] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0820] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0821] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0822] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0823] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0824] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0825] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0826] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0827] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0828] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0829] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0830] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0831] 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.

[0832] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0833] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0834] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0835] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0836] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0837] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0838] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0839] The following is further disclosed regarding the embodiments described above.

[0840] (Claim 1)

[0841] Information collection means for collecting user payment history data and behavioral data,

[0842] A data analysis means for analyzing the collected data and identifying the user's past purchasing and behavioral patterns,

[0843] A recommendation generation means for extracting relevant stores based on the user's current location information and generating coupons according to the analysis results,

[0844] A coupon transmission means for notifying the user terminal of the generated coupon information,

[0845] A system that includes this.

[0846] (Claim 2)

[0847] The system according to claim 1, wherein the data analysis means includes an evaluation means for evaluating the user's level of interest in the store based on the user's visit frequency and purchased items.

[0848] (Claim 3)

[0849] The system according to claim 1, wherein the information gathering means includes a location information acquisition means for periodically acquiring location information from a user terminal.

[0850] "Example 1"

[0851] (Claim 1)

[0852] A data collection means for collecting user transaction history and movement data,

[0853] The aforementioned collected data is analyzed to identify the user's past purchasing behavior and movement patterns, and

[0854] A recommendation generation means for extracting relevant nearby commercial facilities based on the user's current location information and generating discount information according to the analysis results,

[0855] Information transmission means for notifying the user's mobile device of the generated discount information,

[0856] A history update means for collecting the results of using the aforementioned discount information and updating the database,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, wherein the analysis means includes an evaluation means for evaluating the user's level of interest in a commercial facility based on the user's visit frequency and purchased items.

[0860] (Claim 3)

[0861] The system according to claim 1, wherein the data collection means includes location information acquisition means for periodically acquiring geographic information from a user's mobile terminal.

[0862] "Application Example 1"

[0863] (Claim 1)

[0864] Information collection means for collecting user transaction history data and behavioral data,

[0865] A data analysis means for analyzing the collected data and identifying the user's past purchasing trends and behavioral patterns,

[0866] A proposal generation means for extracting relevant facilities based on the user's current location information and generating preferential treatment according to the analysis results,

[0867] A means for sending the generated discount information to the user's terminal,

[0868] A prompt generation means that uses a generative AI model to create prompt sentences related to user trends,

[0869] A system that includes this.

[0870] (Claim 2)

[0871] The system according to claim 1, wherein the data analysis means includes an evaluation means for evaluating the user's level of interest in the facility based on the user's visit frequency and purchased products.

[0872] (Claim 3)

[0873] The system according to claim 1, wherein the information gathering means includes a location information acquisition means for periodically acquiring location information from a user terminal.

[0874] "Example 2 of combining an emotion engine"

[0875] (Claim 1)

[0876] Information collection means for collecting users' payment history and behavioral data,

[0877] An emotion analysis means for analyzing the aforementioned collected data and identifying the user's emotional state,

[0878] A recommendation generation means for generating relevant information based on the aforementioned emotional state and purchase history data,

[0879] Information transmission means for notifying the user device of the generated information,

[0880] A system that includes this.

[0881] (Claim 2)

[0882] The system according to claim 1, wherein the emotion analysis means includes means for identifying multiple emotional states of a user using voice data and image data.

[0883] (Claim 3)

[0884] The system according to claim 1, wherein the information gathering means includes a location information acquisition means for acquiring location information from a user device.

[0885] "Application example 2 when combining with an emotional engine"

[0886] (Claim 1)

[0887] Information acquisition means for collecting users' economic transaction history data and behavioral pattern data,

[0888] A data processing means for analyzing the acquired data and identifying the user's past purchasing behavior patterns and behavioral history patterns,

[0889] The system includes emotion analysis means for identifying the user's emotional state, and emotion-linked recommendation generation means for generating information corresponding to the emotional state,

[0890] Notification means for notifying the user device of the generated recommendation information,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, wherein the data processing means includes an evaluation means for evaluating the user's level of interest in a sales facility based on the user's visit frequency and purchased items.

[0894] (Claim 3)

[0895] The information acquisition means includes a location information acquisition means for periodically acquiring location information from a user device, and provides city information corresponding to the user's emotions based on the analysis results of the emotion analysis means, according to claim 1. [Explanation of Symbols]

[0896] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Information collection means for collecting user transaction history data and behavioral data, A data analysis means for analyzing the collected data and identifying the user's past purchasing trends and behavioral patterns, A proposal generation means for extracting relevant facilities based on the user's current location information and generating preferential treatment according to the analysis results, A means for sending the generated discount information to the user's terminal, A prompt generation means that uses a generative AI model to create prompt sentences related to user trends, A system that includes this.

2. The system according to claim 1, wherein the data analysis means includes an evaluation means for evaluating the user's level of interest in the facility based on the user's visit frequency and purchased products.

3. The system according to claim 1, wherein the information gathering means includes a location information acquisition means for periodically acquiring location information from a user terminal.

Images