system

Abstract

We provide a system that offers optimal shopping suggestions to consumers and enables businesses to efficiently attract customers. [Solution] A system including: a user authentication means that grants access to the system when the user logs in for the first time; an external account linking means that links an external service account to the system and obtains data from that service; a purchase history acquisition means that obtains purchase history data from external services used by the user and utilizes it within the system; a means that acquires location information of the user's terminal; an SNS information collection means that collects real-time information from social networking services and utilizes it within the system; an analysis means that uses an artificial intelligence model; a suggestion information generation means that analyzes the user's preferences and behavior patterns based on the acquired data and utilizes artificial intelligence technology to generate optimal suggestion information; and a suggestion information notification means that notifies the user's terminal of the suggestion information and provides it to the user at an appropriate time.

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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] [[ID=3...]] Currently, many consumers do not have a means to efficiently obtain suitable shopping information recommendations, and there is a problem that it is difficult to make an optimal choice in shopping. Furthermore, since companies cannot fully utilize consumers' purchase histories and location information, targeted marketing and effective customer acquisition are difficult. Based on such a background, there is a need to provide a system that can make optimal shopping proposals to consumers and enable companies to efficiently acquire customers.

Means for Solving the Problems

[0005] The present invention solves the above problems with a system that includes user authentication means, external account linking means, purchase history acquisition means, location information acquisition means, SNS information collection means, analysis means using an artificial intelligence model, suggestion information generation means, and suggestion information notification means.

[0006] Specifically, users register with the system for the first time and link their external accounts to obtain purchase history data from external services. The system also obtains the user's location information in real time via their device and collects real-time information from social media. The acquired data is analyzed using an artificial intelligence model to generate optimal shopping recommendations based on the user's preferences. These recommendations are sent to the user's device and delivered to the consumer at the appropriate time. Furthermore, recommendations provided by companies are filtered based on the user's preferences, enabling highly accurate marketing.

[0007] "User authentication means" refers to the means used to verify a user's authentication information and grant them access to the system when they log in to the system for the first time.

[0008] "External account linking means" refers to a method by which a user links their external service account (e.g., electronic payment service or social media account) to the system and retrieves data from that service.

[0009] A "purchase history acquisition method" is a means of acquiring purchase history data from external services used by users and utilizing this data within the system.

[0010] A "location information acquisition method" is a means of acquiring real-time location information using the user's terminal and transmitting that data to the system.

[0011] "SNS information gathering methods" refer to means of collecting real-time information (e.g., trends, campaign information) from social networking services and utilizing it within the system.

[0012] "Analysis methods using artificial intelligence models" refer to methods that utilize artificial intelligence technology to analyze user preferences and behavioral patterns based on acquired data and generate optimal suggestion information.

[0013] The "proposal information generation means" is a means for generating shopping suggestion information suitable for the user based on the results obtained from the analysis means.

[0014] A "proposal information notification means" is a means of notifying the user's terminal of the generated proposal information and providing it to the user at an appropriate time. [Brief explanation of the drawing]

[0015] [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 the data processing device and smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This 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] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This 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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 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 Embodiment 2 when combined with an emotion engine. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when combined with an emotion engine.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0018] In the following embodiments, the labeled 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.

[0019] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor. <00​In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] 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."

[0023] [First Embodiment]

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

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0030] 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.

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

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] Modes for carrying out the invention

[0037] System Overview

[0038] This invention relates to a system that utilizes a user's purchase history, current location information, real-time information from social media, etc., and uses a generated AI model to provide personalized shopping suggestions. Specifically, the system consists of a user authentication means, an external account linking means, a purchase history acquisition means, a location information acquisition means, a social media information collection means, an analysis means using an artificial intelligence model, a suggestion information generation means, and a suggestion information notification means.

[0039] Program processing

[0040] The system program performs the following operations:

[0041] 1. User authentication and data integration

[0042] When a user logs into the app for the first time, the user authentication method verifies the user's credentials and grants access to the system. At this time, the user can link external accounts (e.g., electronic payment services or social media accounts).

[0043] After successful user authentication, the server retrieves the user's purchase history from an external service. The retrieved data is stored in a database to analyze the user's consumption patterns.

[0044] 2. Customization settings and information gathering

[0045] Users can customize settings based on their interests in the app's settings screen. For example, they can specify that they are interested in a particular category (fashion, groceries, electronics, etc.).

[0046] The device acquires the user's location information in real time and sends it to the server. Additionally, the SNS information gathering mechanism collects real-time information (e.g., trends, campaign information) from social media.

[0047] 3. Data Analysis and Proposal Generation

[0048] The server integrates and analyzes the user's purchase history, customization settings, current location information, and real-time information from social media. Using an artificial intelligence model, it analyzes the user's preferences and behavioral patterns to generate optimal shopping recommendations.

[0049] The server also collects recommendations from companies and selects those that match the user's preferences. This ensures that marketing information provided by companies is also suggested to users with high accuracy.

[0050] 4. Information Distribution and User Interaction

[0051] The server notifies the user's device of the generated shopping recommendations. These notifications include coupon information and special offer details.

[0052] The device displays recommended information to the user as a notification. If the user shows interest in the suggestion, it provides a link to access detailed store and product information.

[0053] Specific example

[0054] Example 1: User's first use

[0055] 1. The user launches the app for the first time, enters their ID and password on the authentication screen, and logs in. Afterward, they link their electronic payment service and social media account.

[0056] 2. The server retrieves the user's past purchase history from external services and stores it in a database. It analyzes consumption trends and builds a user profile.

[0057] Example 2: Real-time information suggestion

[0058] 1. The device detects that the user is in a shopping mall using GPS.

[0059] 2. The server checks the purchase history to confirm that the user has previously purchased items from a specific brand within that mall.

[0060] 3. The server retrieves sales information for the brand from social media and uses a generative AI model to generate optimal suggestions for the user.

[0061] 4. The device sends a push notification to the user saying, "20% off sale at your nearest [brand name]!" and provides a link to more information. When the user clicks the notification, the store's map information and sale details are displayed.

[0062] In this way, the system combines users' purchase history with real-time information to provide optimal shopping suggestions to individual users. This allows users to enjoy shopping efficiently and conveniently. Companies can also improve the accuracy of their targeted marketing, enabling them to attract customers effectively.

[0063] The following describes the processing flow.

[0064] Step 1:

[0065] The user launches the app for the first time and authenticates with their Yahoo! ID. The user enters their ID and password on the login screen and clicks the "Login" button.

[0066] Step 2:

[0067] The server authenticates the user's ID and password, and if authentication is successful, creates a user profile in the database. The server uses an authentication API to verify the user's authentication information.

[0068] Step 3:

[0069] Users perform operations within the app to link their electronic payment services or social media accounts. Users select "Electronic Payment Linkage" or "Social Media Linkage" from the settings menu.

[0070] Step 4:

[0071] The server obtains purchase history data from the electronic payment service with the user's consent. The server uses the electronic payment service's API to retrieve the user's past transaction data and stores it in the database.

[0072] Step 5:

[0073] Users can customize settings based on their interests in the app's settings screen. They can select categories such as fashion, groceries, and electronics, and configure notification frequency and preferred store lists.

[0074] Step 6:

[0075] The device periodically acquires the user's current location information and sends it to the server. The device uses a GPS sensor to collect location information and sends it to the server at regular intervals.

[0076] Step 7:

[0077] The server uses social media information gathering methods to collect real-time information related to users from social media (e.g., trends, campaign information).

[0078] Step 8:

[0079] The server integrates and analyzes the user's purchase history, customization settings, current location information, and social media information. Using artificial intelligence models, it analyzes the user's preferences and behavioral patterns to generate optimal recommendation information.

[0080] Step 9:

[0081] The server collects recommendation information provided by companies and filters it based on user preferences. This ensures that companies' marketing information is also presented to users with high accuracy.

[0082] Step 10:

[0083] The server notifies the user's device of the generated shopping recommendations. These notifications include coupon information and special offer details.

[0084] Step 11:

[0085] The device displays recommended information to the user as a notification. The notification includes a link, which the user can click to view more details. The user taps the notification to access the details page.

[0086] Step 12:

[0087] Users check notifications and click on information that interests them. Clicking displays detailed store and product information, improving the user's shopping experience.

[0088] (Example 1)

[0089] 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."

[0090] Conventional shopping suggestion systems are limited to suggestions based on the user's purchase history and lack the ability to provide dynamic suggestions that utilize real-time location information and the latest trend information obtained from social media. Furthermore, they struggle to provide highly accurate suggestions that integrate user preferences and marketing information from companies. In addition, conventional systems are unable to properly analyze and reflect users' specific interests and behavioral patterns, making it difficult to increase user satisfaction.

[0091] 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.

[0092] In this invention, the server includes user authentication means, external account linking means, purchase history acquisition means, location information acquisition means, SNS information collection means, analysis means using a generation AI model, suggestion information generation means, and suggestion information notification means. This enables highly accurate shopping suggestions tailored to the user's preferences by utilizing real-time location information and the latest trend information.

[0093] "User authentication means" refers to the means used to verify and authenticate a user's identity when they access a system.

[0094] "External account linking methods" refer to methods for linking external service accounts, such as electronic payment services and social media accounts, with the system.

[0095] A "purchase history acquisition method" is a means of acquiring a user's past purchase history from an external service and making it available within the system.

[0096] "Location information acquisition means" refers to a means for acquiring the user's current location in real time and transmitting it to the system.

[0097] "SNS information gathering methods" refer to methods for collecting real-time trend information and campaign information from social media.

[0098] "Analysis methods using generative AI models" refer to methods that use generative AI models to analyze users' purchase history, location information, social media information, etc., in order to analyze users' preferences and behavioral patterns.

[0099] The "proposal information generation means" is a means for generating optimal shopping suggestion information for the user based on the analysis results.

[0100] A "suggestion information notification means" is a means for notifying the user's terminal of the generated shopping suggestion information.

[0101] "Customization settings" are items that users configure based on their interests and preferences, and they serve as the basic data for the system to generate personalized suggestions.

[0102] "Company-provided information" refers to information collected for marketing purposes, such as sales information and recommended product information provided by companies.

[0103] This invention relates to a system that utilizes a user's purchase history, current location information, real-time information from social media, etc., and uses a generated AI model to provide personalized shopping suggestions. The specific system configuration and operation are described below.

[0104] System Configuration

[0105] This system includes the following means:

[0106] User authentication method: A function that verifies and authenticates a user's identity when they access a system.

[0107] External account integration method: A function that allows integration of external service accounts, such as electronic payment services and social media accounts, with the system.

[0108] Purchase history acquisition method: A function that retrieves the user's past purchase history from an external service.

[0109] Location information acquisition method: A function that acquires the user's current location in real time.

[0110] SNS information gathering method: A function that collects real-time trend information and campaign information from social media.

[0111] Analysis method using generative AI models: A function that uses generative AI models to analyze users' purchase history, location information, social media information, etc., and analyzes users' preferences and behavioral patterns.

[0112] Suggestion information generation means: A function that generates optimal shopping suggestion information for the user based on the analysis results.

[0113] Suggestion information notification means: A function that notifies the user's device of the generated shopping suggestion information.

[0114] Operation Description

[0115] The main functions of the system are as follows:

[0116] User authentication and external account integration

[0117] The user launches the app and enters their ID and password on the login screen. The server uses this information to verify the user's identity, and if authentication is successful, grants access to the system. The user then provides more data to the system by linking external accounts (e.g., electronic payment services or social media accounts). At this point, the server receives the information from the linked external accounts and stores it in a database. This makes it possible to understand the user's spending trends.

[0118] Acquisition of purchase history and social media information

[0119] The server retrieves user purchase history using APIs from integrated external services. This data is stored in a database and used for later analysis. Similarly, the server retrieves real-time trend and campaign information using social media APIs. This information is also stored in the database.

[0120] Customization settings and location information acquisition

[0121] Users can customize their interests and preferences in the app's settings screen. For example, setting interests in specific categories (fashion, groceries, electronics, etc.) provides the system with the basis for generating personalized recommendations. The device also acquires the user's location information (GPS information) in real time and sends it to the server.

[0122] Data analysis and shopping suggestion generation

[0123] The server integrates purchase history, customization settings, location information, and real-time information from social media, and inputs it into a generative AI model. Based on this data, the generative AI model generates optimal shopping suggestions for the user. Examples of specific prompts include: "What products did user A recently purchase?", "What categories is user B interested in?", and "What sales information would you recommend for user C, who is currently located in Tokyo?".

[0124] Proposal information notification

[0125] The server notifies the user's device of the shopping suggestion information it has generated. The device displays this notification to the user and provides a link to more detailed information, thereby enhancing the user's convenience in taking action based on the suggestion.

[0126] In this way, the system comprehensively analyzes users' purchase history, location information, and social media information, and uses a generated AI model to provide individually optimized shopping suggestions in real time. This allows users to enjoy efficient and convenient shopping, while also enabling companies to achieve effective marketing.

[0127] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0128] Step 1:

[0129] The user launches the app and enters their ID and password on the login screen.

[0130] Input: User-entered ID and password

[0131] Specific action: The user enters their ID and password on the login screen and presses the "Login" button.

[0132] Output: An authentication request is sent to the server.

[0133] Step 2:

[0134] The server verifies the user's authentication credentials, and if authentication is successful, it grants access to the system.

[0135] Input: Authentication request, database user information

[0136] Specific operation: The server compares the ID and password with the database, and if they match, it returns a response indicating successful authentication.

[0137] Output: Authentication success message and user profile retrieved.

[0138] Step 3:

[0139] Users can add and link electronic payment services and social media accounts on the external account linking screen.

[0140] Input: External account information (e.g., social media account)

[0141] Specific action: The user enters their external account information and presses the "Link" button.

[0142] Output: A connection request is sent to the external service.

[0143] Step 4:

[0144] The server receives information from linked external accounts and adds it to the user profile.

[0145] Input: Account information from an external service

[0146] Specific operation: The server uses the SNS API to retrieve information about linked accounts and saves it to the database.

[0147] Output: Stored in the database as a complete profile.

[0148] Step 5:

[0149] The server retrieves the user's purchase history from an external service.

[0150] Input: Request to the electronic payment service API

[0151] Specific operation: The server uses the API of the electronic payment service to retrieve past purchase history data and store it in the database.

[0152] Output: Purchase history data is saved to the database.

[0153] Step 6:

[0154] The server uses SNS APIs to retrieve real-time trend information and campaign information.

[0155] Input: Request to SNS API

[0156] Specific operation: The server uses the SNS API to retrieve the latest information related to the specified keywords and hashtags.

[0157] Output: The latest information from social media is saved to the database.

[0158] Step 7:

[0159] Users can customize their interests and preferences in the app's settings screen.

[0160] Input: User's interest category information

[0161] Specific operation: The user opens the settings menu, selects categories of interest using checkboxes, and presses the save button.

[0162] Output: The user's interest settings are stored in the database.

[0163] Step 8:

[0164] The device acquires the user's location information (GPS information) in real time and sends it to the server.

[0165] Input: Location information from GPS sensor

[0166] Specific operation: The device periodically acquires location information and sends it to the server.

[0167] Output: Location information is sent to the server and stored in the database.

[0168] Step 9:

[0169] The server integrates purchase history, customization settings, location information, and real-time information from social media, and inputs it into the generating AI model.

[0170] Input: Purchase history, customization settings, location information, social media information

[0171] Specific operation: The server generates various data as a single dataset and inputs prompt statements into the AI ​​model.

[0172] Output: Input dataset for the generative AI model

[0173] Step 10:

[0174] The generative AI model generates optimal shopping suggestions for the user.

[0175] Input: Integrated dataset and prompt statement

[0176] Specific operation: The generating AI model analyzes historical data and trend information based on the prompt text and outputs shopping suggestions.

[0177] Output: Suggested shopping information

[0178] Step 11:

[0179] The server notifies the user's terminal of the generated suggestion information.

[0180] Input: Suggestion information from the generated AI model

[0181] Specific operation: The server sends a push notification to the user's device, sending a message such as "Sale happening at your local [store name]!"

[0182] Output: Push notification message

[0183] Step 12:

[0184] The device displays notifications received by the user and provides a link to more detailed information.

[0185] Input: Push notification from server

[0186] Specific operation: The device displays a notification as a pop-up message, and when the user clicks it, a detailed information page opens.

[0187] Output: Shopping suggestions displayed to the user

[0188] (Application Example 1)

[0189] 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."

[0190] Traditional shopping suggestion systems struggled to fully utilize users' purchase history and location information to provide personalized recommendations, thus failing to improve the in-store shopping experience. Furthermore, the lack of a real-time means for users to receive suggested information while in a physical store led to delays in providing timely information, hindering effective marketing.

[0191] 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.

[0192] In this invention, the server includes a user authentication means, an external account linking means, a purchase history acquisition means, a location information acquisition means, an SNS information collection means, an analysis means using an artificial intelligence model, a suggestion information generation means, a suggestion information notification means, a means for making shopping suggestions in real time when the user approaches a physical store, and a means for providing detailed information and maps based on the notified suggestion information. This makes it possible to provide users with immediate and optimal shopping suggestions by comprehensively utilizing the user's purchase history, location information, real-time information from SNS, etc.

[0193] "User authentication means" refers to the means of verifying that a user is a legitimate user when accessing a system.

[0194] "External account linking method" refers to a method by which a system links with a user's external service accounts (such as electronic payment services or social media accounts).

[0195] A "purchase history acquisition method" is a means of acquiring records of products and services that a user has purchased in the past.

[0196] "Location information acquisition means" refers to methods for acquiring location information using technologies such as GPS in order to determine the user's current location.

[0197] "SNS information gathering methods" refer to methods for collecting real-time information about users and trends from social media.

[0198] "Analysis methods using artificial intelligence models" refer to methods that use artificial intelligence models based on collected data to analyze user preferences and behavioral patterns.

[0199] The "proposal information generation method" is a method for generating optimal shopping information and coupon information for users based on analysis results.

[0200] A "proposal information notification means" is a means of notifying the user's terminal of the generated proposal information.

[0201] "A means of providing shopping suggestions in real time" refers to a method of immediately providing appropriate shopping suggestions to users when they approach a physical store.

[0202] "Means of providing detailed information and maps" refers to means of providing users with links or maps to check more detailed information and store locations based on the suggested shopping information.

[0203] This invention relates to a system that utilizes a user's purchase history, location information, real-time information from social media, etc., and uses a generated AI model to provide personalized shopping suggestions. The system includes means for user authentication, means for linking external accounts, means for acquiring purchase history, means for acquiring location information, means for collecting social media information, means for analysis using an artificial intelligence model, means for generating suggestion information, means for notifying suggestion information, means for providing shopping suggestions in real time, and means for providing detailed information and maps.

[0204] System Configuration

[0205] The system primarily consists of a server and user terminals. The server is responsible for data analysis and generating suggestion information, while the user terminals are responsible for collecting information and displaying the suggested information.

[0206] Specific examples of hardware and software

[0207] Servers: High-performance servers are used for data processing. For example, cloud servers such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) can be used.

[0208] User devices: Smartphones are primarily used. This includes devices with mobile operating systems such as Android and iOS installed.

[0209] Generative AI models: Models using AI frameworks such as PyTorch and TensorFlow are used.

[0210] Feature details

[0211] 1. User Authentication Methods

[0212] When a user logs into the app for the first time, their authentication information is verified and permission to access the system is granted. At this time, the user can link external accounts (for example, electronic payment services or social media accounts).

[0213] 2. External account linking methods

[0214] After successful authentication, the system retrieves the user's purchase history from an external service and stores it in a database. This allows the system to understand the user's spending habits.

[0215] 3. Means of acquiring purchase history

[0216] Purchase history will be collected from electronic payment services and online shops to serve as basic data for analyzing user consumption behavior.

[0217] 4. Location information acquisition means

[0218] Using GPS technology, the system obtains the user's current location in real time. This allows it to identify which physical store the user is approaching.

[0219] 5. Means of gathering information from social media

[0220] It can collect trending and campaign information from social media and analyze user interests in real time.

[0221] 6. Analysis methods using artificial intelligence models

[0222] It integrates purchase history, location information, and social media data to analyze user preferences and behavioral patterns. By using generative AI models such as PyTorch, it generates highly accurate recommendation information.

[0223] 7. Proposal information generation means

[0224] Based on the analysis results, the system generates optimal shopping and coupon information for users. This also takes into account marketing information provided by companies.

[0225] 8. Proposal information notification means

[0226] The generated suggestion information is sent as a push notification to the user's smartphone. The notification includes information on special offers and coupons.

[0227] 9. Means of providing shopping suggestions in real time

[0228] When a user approaches a physical store, the system provides appropriate shopping suggestions on the spot. For example, it might send a notification like, "20% off sale at your nearest [brand name]!"

[0229] 10. Means of providing detailed information and maps

[0230] Based on the suggested information, provide users with links to access more detailed product information and store maps.

[0231] Specific example

[0232] For example, when a user arrives at a shopping mall, the system works as follows: First, a location information acquisition system identifies the user's location, and an AI model analyzes products and stores that the user might be interested in based on their purchase history and social media information. Then, a notification system sends a push notification saying, "There's a 30% off sale at your nearest electronics store!", along with more detailed information and a map.

[0233] Example of a prompt

[0234] Examples of prompt messages that provide suggestions based on the user's purchase history, current location, and social media trends are as follows:

[0235] "The user's purchase history includes electronics products, and their current location is within a shopping mall. According to social media trends, there is a sale on electronics products. Based on this information, we generate optimal shopping suggestions."

[0236] This allows users to enjoy shopping more efficiently, and enables companies to improve the accuracy of their targeted marketing.

[0237] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0238] Step 1: User authentication and external account linking

[0239] Input: User authentication information (User ID, password), external account information (electronic payment service or social media account)

[0240] Processing: The server authenticates the user based on the entered authentication information. After successful authentication, it links with an external account and obtains an authentication token from an external service (electronic payment service or social networking service).

[0241] Output: Authentication token and user profile information

[0242] Specific operation: When a user logs into the app, the server verifies the authentication information, and if successful, displays a pop-up prompting the user to link with an electronic payment service or social media.

[0243] Step 2: Obtain purchase history

[0244] Input: Authentication token, external account information

[0245] Processing: The server retrieves purchase history from electronic payment services and online shops using external account information. The retrieved data is then added to the user's profile.

[0246] Output: Purchase history data

[0247] Specific operation: Upon successful authentication, the server uses the authentication token to retrieve purchase history data from an external service's API and saves it to the database.

[0248] Step 3: Obtaining location information

[0249] Input: GPS data from the user's device

[0250] Process: The device acquires GPS data and sends its current location information to the server. The server uses this location information to determine the place the user is visiting.

[0251] Output: Current location information

[0252] Specific operation: The device obtains the user's current location via GPS and sends it to the server in real time. The server uses this data to determine which physical store the user is in.

[0253] Step 4: Gathering SNS information

[0254] Input: Authentication token, social media account information

[0255] Processing: The server uses social media account information to collect current trend and campaign information. This allows it to obtain real-time information related to the user's interests.

[0256] Output: SNS trend information, campaign information

[0257] Specific operation: The server periodically retrieves trending and campaign information using SNS APIs and stores it in a database.

[0258] Step 5: Data Integration and Analysis

[0259] Input: Purchase history data, current location information, social media trend information

[0260] Processing: The server integrates this data and uses a generative AI model to analyze user preferences and behavioral patterns. This generates foundational data for providing users with optimal shopping recommendations.

[0261] Output: Analysis results (user preference data, behavioral pattern data)

[0262] Specific operation: The server collects data, inputs that data into a generating AI model for analysis, and uses frameworks such as PyTorch to obtain highly accurate results.

[0263] Step 6: Generating Proposal Information

[0264] Input: Analysis results (user preference data, behavioral pattern data)

[0265] Processing: The server generates optimal shopping recommendations for the user based on the analysis results. These recommendations also incorporate marketing information provided by companies.

[0266] Output: Proposal Information

[0267] Specific operation: The server integrates analysis results with marketing information from companies and generates shopping suggestions tailored to the user.

[0268] Step 7: Notification of proposed information

[0269] Input: Proposal Information

[0270] Processing: The server pushes the generated suggestion information to the user's device. The notification may also include information on special offers and coupons.

[0271] Output: Push notification to user's device

[0272] Specific operation: The server sends the suggestion information to the user's smartphone, and a notification is displayed.

[0273] Step 8: Provide detailed information and maps.

[0274] Input: User action upon receiving the push notification (e.g., clicking a link)

[0275] Processing: The device displays more detailed product information and store locations to users who click the link in the push notification.

[0276] Output: Detailed information screen, map display

[0277] Specific operation: When the user clicks the notification, the device retrieves detailed information and map data from the server and displays it.

[0278] 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.

[0279] Modes for carrying out the invention

[0280] System Overview

[0281] This invention relates to a system that utilizes a user's purchase history, current location information, real-time information from social media, and an emotion engine that recognizes the user's emotions, and uses a generative AI model to provide personalized shopping suggestions. Specifically, the system consists of a user authentication means, an external account linking means, a purchase history acquisition means, a location information acquisition means, a social media information collection means, an analysis means using an artificial intelligence model, a suggestion information generation means, an emotion engine, and a suggestion information notification means.

[0282] Program Processing

[0283] The system program performs the following processing.

[0284] 1. User Authentication and Data Linkage

[0285] When a user logs in to the app for the first time, the user authentication means checks the user's authentication information and permits access to the system. At this time, the user can link an external account (e.g., e-payment service or SNS account).

[0286] After the user's authentication is successful, the server obtains the user's purchase history from an external service. The obtained data is saved in a database to analyze the user's consumption tendency.

[0287] 2. Customization Settings and Information Collection

[0288] The user makes customization settings based on their interests on the app's settings screen. For example, the user specifies an interest in a particular category (fashion, food, electronics, etc.).

[0289] The terminal obtains the user's location information in real time and sends it to the server. Also, the SNS information collection means collects real-time information (e.g., trends, campaign information) from SNS.

[0290] 3. Emotion Recognition and Data Integration

[0291] The emotion engine installed on the terminal recognizes the user's emotion in real time and sends the data to the server. The emotion engine analyzes the user's facial expressions, voice tones, etc. to identify the emotion.

[0292] The server integrates and analyzes emotional data, purchase history, customization settings, current location information, and social media information. Using an artificial intelligence model, it analyzes user preferences and behavioral patterns, and generates optimal suggestion information that also takes emotional states into account.

[0293] 4. Proposal information generation and notification

[0294] The server also collects recommendations provided by companies and filters them based on the user's preferences and emotions. This ensures that companies' marketing information is also presented to users with high accuracy.

[0295] The server notifies the user's device of the generated shopping recommendations. These notifications include coupon information and special offer details.

[0296] The device displays recommended information to the user as a notification. If the user shows interest in the suggestion, it provides a link to access detailed store and product information.

[0297] Specific example

[0298] Example 1: User's first use

[0299] 1. The user launches the app for the first time, enters their ID and password on the authentication screen, and logs in. Afterward, they link their electronic payment service and social media account.

[0300] 2. The server retrieves the user's past purchase history from external services and stores it in a database. It analyzes consumption trends and builds a user profile.

[0301] Example 2: Suggestions based on emotions and real-time information

[0302] 1. The device detects the user's location in a shopping mall using GPS. Simultaneously, the emotion engine recognizes the user's state of excitement from their facial expressions.

[0303] 2. The server checks from the purchase history that the user has purchased items of a specific brand within the mall in the past.

[0304] 3. The server obtains the sale information of the brand from the SNS and generates an optimal proposal for the user using the generated AI model and sentiment data.

[0305] 4. The terminal sends a push notification to the user saying "There is a 20% off sale on the ○○ brand near you!" and provides a link to the detailed information. When the user clicks on the notification, the map information of the store and the sale details are displayed.

[0306] In this way, in addition to the user's purchase history and current location information, this system combines real-time sentiment information to provide an optimal shopping proposal for each individual user. As a result, the user can obtain a more personalized and efficient shopping experience. On the enterprise side, it is also possible to improve the accuracy of target marketing considering the user's emotional state, enabling effective customer acquisition.

[0307] The following explains the processing flow. <{id:0000969}>

[0308] Step 1:

[0309] The user launches the app for the first time and authenticates using their Yahoo!-ID. The user enters their ID and password on the login screen and clicks the "Login" button.

[0310] Step 2:

[0311] The server authenticates the user's ID and password and creates a user profile in the database if the authentication is successful. The server uses an authentication API to verify the user's authentication information.

[0312] Step 3:

[0313] <000098Users link their electronic payment services and social media accounts within the app. Users select "Electronic Payment Linkage" or "Social Media Linkage" from the settings menu.

[0314] Step 4:

[0315] The server obtains purchase history data from the electronic payment service with the user's consent. The server uses the electronic payment service's API to retrieve the user's past transaction data and stores it in the database.

[0316] Step 5:

[0317] Users can customize settings based on their interests in the app's settings screen. They can select categories such as fashion, groceries, and electronics, and configure notification frequency and preferred store lists.

[0318] Step 6:

[0319] The device periodically acquires the user's current location information and sends it to the server. The device uses a GPS sensor to collect location information and sends it to the server at regular intervals.

[0320] Step 7:

[0321] The emotion engine installed in the device recognizes the user's emotions in real time and sends that data to the server. The emotion engine identifies emotions by analyzing the user's facial expressions, voice tone, etc.

[0322] Step 8:

[0323] The server uses social media information gathering methods to collect real-time information related to users from social media (e.g., trends, campaign information).

[0324] Step 9:

[0325] The server integrates and analyzes the user's purchase history, customization settings, current location information, sentiment data, and social media information. Using artificial intelligence models, it analyzes the user's preferences and behavioral patterns to generate optimal recommendation information.

[0326] Step 10:

[0327] The server collects recommendation information provided by companies and filters it based on user preferences and sentiment data. This ensures that companies' marketing information is also suggested to users with high accuracy.

[0328] Step 11:

[0329] The server notifies the user's device of the generated shopping recommendations. These notifications include coupon information and special offer details.

[0330] Step 12:

[0331] The device displays recommended information to the user as a notification. The notification includes a link, which the user can click to view more details. The user taps the notification to access the details page.

[0332] Step 13:

[0333] Users check notifications and click on information that interests them. Clicking displays detailed store and product information, improving the user's shopping experience.

[0334] (Example 2)

[0335] 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 as the "terminal".

[0336] In today's shopping landscape, providing personalized purchase suggestions to users is crucial for maintaining high user satisfaction. However, traditional systems typically rely solely on purchase history and location data for suggestions, failing to consider users' momentary emotions or real-time social media information. As a result, providing optimal suggestions for users has been difficult, and the marketing effectiveness for companies has been limited.

[0337] 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.

[0338] In this invention, the server includes user authentication means, external account linking means, purchase history acquisition means, location information acquisition means, SNS information collection means, emotion recognition means, analysis means using an artificial intelligence model, suggestion information generation means, and suggestion information notification means. This enables comprehensive analysis of the user's purchase history, current location information, real-time emotion information, and SNS information to provide optimal shopping suggestions to individual users.

[0339] "User authentication means" refers to the means used to verify the identity of a user when they access a system.

[0340] "External account linking methods" refer to methods for linking a system with external services (e.g., electronic payment services or social networking services).

[0341] A "purchase history acquisition method" is a means of acquiring a user's past purchase history and importing it into the system.

[0342] "Location information acquisition means" refers to methods for acquiring the user's current location information using GPS or similar technologies.

[0343] "SNS information gathering methods" refer to methods for collecting information from social media in real time.

[0344] "Means of recognizing emotions" refers to methods for identifying emotions from a user's facial expressions, voice, etc.

[0345] "Analysis methods using artificial intelligence models" refer to methods for analyzing data acquired using artificial intelligence models to analyze user preferences and behavioral patterns.

[0346] The "proposal information generation means" is a means of generating optimal shopping suggestions for the user based on the analysis results.

[0347] A "proposal information notification means" is a means of notifying the user's terminal of the generated proposal information.

[0348] Modes for carrying out the invention

[0349] System Program Overview

[0350] This invention relates to a system that utilizes a user's purchase history, current location information, real-time information from social media, and an emotion engine that recognizes the user's emotions, and uses a generative AI model to provide personalized shopping suggestions. This system includes user authentication means, external account linking means, purchase history acquisition means, location information acquisition means, social media information collection means, emotion recognition means, analysis means using an artificial intelligence model, suggestion information generation means, and suggestion information notification means.

[0351] Hardware and software to use

[0352] Server: Performs database management, API integration, and data analysis using artificial intelligence models.

[0353] Device: Smartphones, tablets, etc. It receives user input and activates the emotion engine.

[0354] Emotion engine: Software that analyzes the user's facial expressions and voice tone to identify their emotions.

[0355] GPS function: Obtains the user's location information.

[0356] SNS information gathering tools: Scraping tools and APIs for collecting real-time information from social media.

[0357] Explanation of the program's processing

[0358] 1. User Authentication

[0359] The user logs into the app for the first time, and their identity is verified through an authentication method. The authentication information is securely transmitted to the server.

[0360] The server verifies the received authentication information and initiates external account linking upon successful authentication.

[0361] 2. External account integration and data acquisition

[0362] The user links their account with an electronic payment service or social media account. Authentication information for the linking service is entered.

[0363] The server uses APIs from external services to retrieve purchase history and social media activity data, and stores it in a database.

[0364] 3. Customization settings

[0365] Users can customize their settings within the app based on their interests. For example, they can select specific categories or brands.

[0366] The device sends the configured information to the server, which then stores it in the database.

[0367] 4. Obtaining location information

[0368] The device periodically obtains the user's current location using its GPS function and sends it to the server.

[0369] The server stores location information in a database and integrates it with related data.

[0370] 5. Obtaining SNS information

[0371] The device uses a social networking information gathering tool to acquire real-time information related to the specified keywords.

[0372] The server analyzes the collected information and stores it in a database.

[0373] 6. Emotion recognition

[0374] The device uses its camera and microphone to identify emotions from the user's facial expressions and voice, and acquires emotion data.

[0375] The device sends emotional data to the server.

[0376] 7. Data Integration and Analysis

[0377] The server integrates emotional data, purchase history, customization settings, current location information, and social media information, and analyzes the data using an artificial intelligence model.

[0378] Artificial intelligence models analyze user preferences and behavioral patterns.

[0379] 8. Generation of proposed information

[0380] The server collects marketing information provided by companies and filters it based on the user's preferences and emotions.

[0381] We use an artificial intelligence model to generate optimal shopping suggestions.

[0382] 9. Notification of proposed information

[0383] The server notifies the terminal of the shopping suggestions it has generated. The notification includes coupon information and special offer information.

[0384] The device displays a notification to the user and provides a link to more information.

[0385] Specific example

[0386] 1. The user logs in for the first time and links their electronic payment service with their social media account.

[0387] 2. The server retrieves purchase history from an external service and saves it to the database.

[0388] 3. The GPS detects that the user is in a shopping mall, and the emotion engine recognizes the user's state of excitement.

[0389] 4. The server generates optimal suggestions using purchase history and sales information from social media.

[0390] 5. The device sends a push notification saying, "20% off sale at your nearest [brand name] store."

[0391] Examples of prompts to input into a generative AI model

[0392] "This user has a history of frequently purchasing fashion items. They are currently in a shopping mall. Their facial expression indicates excitement. Please generate effective shopping suggestions for this user."

[0393] "This user is interested in electronics and is currently located in central Tokyo. They have sales information for electronics brands on social media. Please create the best possible suggestions for this user."

[0394] In this way, the system continuously collects data from multiple sources and provides personalized shopping suggestions to each user, thereby improving the user experience and maximizing the marketing effectiveness of companies.

[0395] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0396] Step 1:

[0397] User Authentication

[0398] Operation:

[0399] The user launches the app for the first time and enters their ID and password on the authentication screen.

[0400] The server compares the received authentication information with the user information in the database, and if authentication is successful, it starts a session.

[0401] Input: User ID, Password

[0402] Output: Session started based on authentication success / failure result.

[0403] Specific processing:

[0404] The server receives the authentication information and compares it with the information in the database. If authentication is successful, it generates session information and grants the user access.

[0405] Step 2:

[0406] External account integration and data retrieval

[0407] Operation:

[0408] Users enter authentication information for linking their electronic payment service or social media account within the app.

[0409] The server sends API requests to linked external services to retrieve user purchase history and social media activity data. This data is stored in a database.

[0410] Input: External account credentials

[0411] Output: Purchase history data, social media activity data

[0412] Specific processing:

[0413] The server calls an external API to retrieve the user's purchase history and social media data. The retrieved data is stored in the database as the user's profile.

[0414] Step 3:

[0415] Customization settings

[0416] Operation:

[0417] Users can customize settings based on their interests in the app's settings screen. For example, they can select specific categories or brands.

[0418] The terminal sends the entered configuration information to the server and stores it in the database.

[0419] Input: User customization settings information

[0420] Output: Configuration information stored in the database

[0421] Specific processing:

[0422] The user sends their selected customization settings from the terminal to the server, which stores this information in a database for use in subsequent analysis processes.

[0423] Step 4:

[0424] Location information acquisition

[0425] Operation:

[0426] The device periodically obtains the user's current location using its GPS function and sends it to the server.

[0427] The server stores the received location information in a database.

[0428] Input: Location information obtained from GPS

[0429] Output: Location information stored in the database

[0430] Specific processing:

[0431] The device periodically uses GPS to obtain the user's current location and sends it to the server. The server stores the received location information in a database and updates the location information in real time.

[0432] Step 5:

[0433] Acquisition of SNS information

[0434] Operation:

[0435] The device retrieves real-time information from social media information gathering tools based on specified keywords.

[0436] The server stores the collected SNS information in a database and integrates it into the user's profile.

[0437] Input: Collected SNS information

[0438] Output: SNS information stored in the database

[0439] Specific processing:

[0440] The device uses an SNS collection tool to acquire information related to specified keywords and sends it to the server. The server stores the collected SNS information in a database.

[0441] Step 6:

[0442] emotion recognition

[0443] Operation:

[0444] The device uses its camera and microphone to analyze the user's facial expressions and voice in real time and identify their emotions.

[0445] The device sends the identified emotion data to the server.

[0446] Input: Facial expression, voice tone

[0447] Output: Identified sentiment data

[0448] Specific processing:

[0449] The emotion engine uses information acquired from the device's camera and microphone to recognize the user's emotions and sends the results to the server. The server stores the emotion data in a database.

[0450] Step 7:

[0451] Data Integration and Analysis

[0452] Operation:

[0453] The server integrates and analyzes emotional data, purchase history, customization settings, current location information, and social media information.

[0454] Using artificial intelligence models, we analyze user preferences and behavioral patterns to generate optimal shopping recommendations.

[0455] Input: Sentimental data, purchase history, customization settings, current location information, social media information

[0456] Output: Analysis results, proposed information

[0457] Specific processing:

[0458] The server uses integrated data to perform analysis using an artificial intelligence model, analyzing user preferences and behavioral patterns. Based on these results, it generates optimal shopping recommendations.

[0459] Step 8:

[0460] Generation of proposed information

[0461] Operation:

[0462] The server collects marketing information provided by companies (e.g., coupon information, special offer information) and filters it based on the user's preferences and emotions.

[0463] We use a generative AI model to generate optimal shopping suggestions for the user.

[0464] Input: Marketing information and analysis results from companies.

[0465] Output: Optimal shopping suggestions

[0466] Specific processing:

[0467] The system filters information provided by companies and uses a generative AI model to create optimal suggestions that take into account the user's preferences and emotional state.

[0468] Step 9:

[0469] Notification of proposed information

[0470] Operation:

[0471] The server notifies the user's device of the shopping suggestions it has generated. These notifications include coupon information and special offer information.

[0472] The device will display this notification to the user as a push notification, providing a link to more information.

[0473] Input: Generated shopping suggestions

[0474] Output: Notification to user terminal

[0475] Specific processing:

[0476] The server sends the generated suggestion information to the user's device, which then displays it to the user as a push notification. The notification includes a link to more information, which, when tapped by the user, displays information about the relevant store or product.

[0477] In this way, each step works together to create a system that can efficiently provide personalized suggestions to users.

[0478] (Application Example 2)

[0479] 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".

[0480] Traditional online shopping systems offered recommendations based on user preferences, but they did not provide personalized suggestions that took into account real-time emotional states or location information. This made it difficult to provide a shopping experience that aligned with users' actual interests and desires, resulting in many users spending a considerable amount of time finding suitable products. Furthermore, companies faced the challenge of being unable to conduct effective marketing based on users' real-time emotions and behavior.

[0481] 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.

[0482] In this invention, the server includes user authentication means, external account linking means, purchase history acquisition means, location information acquisition means, SNS information collection means, emotion recognition engine, analysis means using an artificial intelligence model, suggestion information generation means, and suggestion information notification means. This enables integrated analysis of the user's purchase history, current location information, SNS information, and emotional state, and allows for optimal shopping suggestions for each individual user using a generated AI model.

[0483] "User authentication means" refers to a method of verifying a user's authentication information and granting them access to the system.

[0484] "External account linking methods" refer to methods for linking with external services such as electronic payment services and social media accounts.

[0485] "Purchase history acquisition method" refers to a method for acquiring a user's past purchase history and storing it in the system.

[0486] "Location information acquisition means" refers to means of collecting information about the user's current location.

[0487] "SNS information gathering methods" refer to methods for collecting data such as trend information and campaign information from social networking services.

[0488] An "emotion engine" is a method of identifying emotions by analyzing the user's facial expressions and voice tone.

[0489] "Analysis methods using artificial intelligence models" refer to methods that use artificial intelligence to analyze user preferences and behavioral patterns.

[0490] The "proposal information generation means" is a means of generating shopping suggestions that are optimal for each individual user based on user data.

[0491] A "proposal information notification means" is a means of notifying the user's terminal of the generated proposal information.

[0492] "Custom settings" refers to the ability for users to adjust application settings based on their own interests.

[0493] "Company-provided information" refers to recommended information and campaign information offered by companies.

[0494] System Overview

[0495] This invention is a system that collects user purchase history, current location information, real-time information from social media, and sentiment information, and analyzes and integrates them to provide optimal shopping suggestions for individual users. Specifically, it provides a series of systems that generate and notify suggestion information using an artificial intelligence model for analyzing various types of information and an sentiment engine that recognizes user sentiment in real time. This system includes the following main means:

[0496] 1. User authentication method: Verify the user's authentication information and grant access to the system.

[0497] 2. External account linking methods: Methods for linking with electronic payment services and social media accounts.

[0498] 3. Purchase history acquisition method: Acquire the user's past purchase history and save it in the system.

[0499] 4. Means of acquiring location information: Collect the user's current location information.

[0500] 5. Social media information gathering methods: Gather trend information and campaign information from social networking services.

[0501] 6. Emotion Engine: Analyzes the user's facial expressions and voice tone to identify emotions.

[0502] 7. Analysis methods using artificial intelligence models: Use artificial intelligence to analyze user preferences and behavioral patterns.

[0503] 8. Suggestion information generation means: Based on user data, it generates shopping suggestions that are optimal for each individual user.

[0504] 9. Proposal Information Notification Means: Generated proposal information is notified to the user's terminal.

[0505] Program processing

[0506] The server collects and analyzes various data, generates personalized recommendations for each user, and notifies the user's device. This allows users to have a more efficient and personalized shopping experience. Specifically, the following data processing or calculations are performed:

[0507] 1. Use of hardware and software:

[0508] Smartphones: Used for user authentication, location information acquisition, emotion recognition, etc.

[0509] Emotion Engine: A library for recognizing user emotions in real time.

[0510] Artificial intelligence model: Data analysis and proposal information are generated using the GenerativeAIModel library.

[0511] 2. Data collection and analysis:

[0512] The server collects purchase history from external accounts and stores it in a database.

[0513] Real-time location information is collected using a GPS module, and social media information is obtained via an API.

[0514] User sentiment data is collected by the sentiment engine and sent to the server.

[0515] 3. Proposal generation using artificial intelligence models:

[0516] The server integrates all collected data and generates optimal shopping suggestions using a generative AI model. This generative AI model operates based on the following prompts:

[0517] "User ID: 1234, Location: Tokyo, Emotion: Excited, Purchase History: Fashion, Social Media Trend: Autumn Sale. Please generate the best suggestions for this user."

[0518] Specific example

[0519] 1. First-time use case:

[0520] The user launches the app for the first time, enters their ID and password on the authentication screen to log in, and then links their electronic payment service and social media account.

[0521] The server retrieves the user's past purchase history from external services and stores it in a database. It then analyzes consumption trends and builds user profiles.

[0522] 2. Case of real-time proposals:

[0523] The system uses GPS to detect that the user is in a shopping mall. Simultaneously, an emotion engine recognizes the user's level of excitement from their facial expressions.

[0524] The server checks the purchase history to confirm that the user has previously purchased items from a specific brand within that mall.

[0525] The server retrieves sales information for a brand from social media, and uses a generative AI model and sentiment data to generate optimal suggestions for the user.

[0526] A push notification is sent to the user's device stating, "20% off sale at your nearest [brand name]!" and providing a link to more information. When the user clicks the notification, store map information and sale details are displayed.

[0527] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0528] Step 1:

[0529] User authentication and external integration

[0530] Input: User authentication information (ID, password), external account information (electronic payment account, social media account)

[0531] Specific operation: When a user logs into the smartphone app for the first time, they enter authentication information and authenticate using the authentication method. Additionally, users can link their accounts with electronic payment services and social media accounts using external account linking methods.

[0532] Output: Authentication success and the status of the external account linkage are sent to the server.

[0533] Step 2:

[0534] Retrieving purchase history

[0535] Input: User ID

[0536] Specific operation: The server collects the user's past purchase history using a purchase history acquisition method from an external service. The acquired purchase history is stored in a database and used to analyze the user's consumption trends.

[0537] Output: Purchase history data is saved to the server's database.

[0538] Step 3:

[0539] Retrieve custom settings

[0540] Input: User's interests and settings information

[0541] Specific operation: The user selects a category of interest (e.g., fashion, groceries, electronics, etc.) from the app's settings screen.

[0542] Output: Configuration information is sent to the server.

[0543] Step 4:

[0544] Real-time information gathering

[0545] Input: Location information, social media information

[0546] Specific operation: The device's GPS module acquires the user's location information in real time and sends it to the server. In addition, the SNS information collection method collects real-time trend information and campaign information from SNS.

[0547] Output: Location information and SNS information are sent to the server.

[0548] Step 5:

[0549] emotion recognition

[0550] Input: User's facial expression, voice tone

[0551] Specific operation: The emotion engine uses the camera and microphone built into the device to recognize the user's emotions in real time. The acquired emotion data is sent to the server.

[0552] Output: Emotional data is sent to the server.

[0553] Step 6:

[0554] Data integration and analysis

[0555] Input: Purchase history data, settings information, location information, social media information, sentiment data

[0556] Specific operation: The server integrates all collected data and analyzes it using an artificial intelligence model. The generative AI model generates optimal suggestion information based on the user's preferences, behavioral patterns, and emotional state. Instructions are given to the AI ​​model using prompts. Example of a prompt: "User ID: 1234, Location: Tokyo, Emotion: Excited, Purchase History: Fashion, SNS Trend: Autumn Sale, Please generate optimal suggestions for the user."

[0557] Output: Generated suggestion information is obtained.

[0558] Step 7:

[0559] Notification of proposed information

[0560] Input: Generated suggestion information

[0561] Specific operation: The server sends generated shopping suggestion information to the user's terminal via push notifications through the suggestion information notification system. The notification also includes a link to detailed information.

[0562] Output: The suggested information is displayed as a notification on the user's device.

[0563] Step 8:

[0564] Providing detailed information

[0565] Input: User action (notification click)

[0566] Specific operation: When the user clicks the notification, the app displays detailed information (store map, sale details, etc.).

[0567] Output: The detailed information screen is displayed on the user's device.

[0568] 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.

[0569] 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.

[0570] 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.

[0571] [Second Embodiment]

[0572] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0573] 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.

[0574] 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).

[0575] 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.

[0576] 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.

[0577] 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).

[0578] 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.

[0579] 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.

[0580] 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.

[0581] 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.

[0582] 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.

[0583] 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".

[0584] Modes for carrying out the invention

[0585] System Overview

[0586] This invention relates to a system that utilizes a user's purchase history, current location information, real-time information from social media, etc., and uses a generated AI model to provide personalized shopping suggestions. Specifically, the system consists of a user authentication means, an external account linking means, a purchase history acquisition means, a location information acquisition means, a social media information collection means, an analysis means using an artificial intelligence model, a suggestion information generation means, and a suggestion information notification means.

[0587] Program processing

[0588] The system program performs the following operations:

[0589] 1. User authentication and data integration

[0590] When a user logs into the app for the first time, the user authentication method verifies the user's credentials and grants access to the system. At this time, the user can link external accounts (e.g., electronic payment services or social media accounts).

[0591] After successful user authentication, the server retrieves the user's purchase history from an external service. The retrieved data is stored in a database to analyze the user's consumption patterns.

[0592] 2. Customization settings and information gathering

[0593] Users can customize settings based on their interests in the app's settings screen. For example, they can specify that they are interested in a particular category (fashion, groceries, electronics, etc.).

[0594] The device acquires the user's location information in real time and sends it to the server. Additionally, the SNS information gathering mechanism collects real-time information (e.g., trends, campaign information) from social media.

[0595] 3. Data Analysis and Proposal Generation

[0596] The server integrates and analyzes the user's purchase history, customization settings, current location information, and real-time information from social media. Using an artificial intelligence model, it analyzes the user's preferences and behavioral patterns to generate optimal shopping recommendations.

[0597] The server also collects recommendations from companies and selects those that match the user's preferences. This ensures that marketing information provided by companies is also suggested to users with high accuracy.

[0598] 4. Information Distribution and User Interaction

[0599] The server notifies the user's device of the generated shopping recommendations. These notifications include coupon information and special offer details.

[0600] The device displays recommended information to the user as a notification. If the user shows interest in the suggestion, it provides a link to access detailed store and product information.

[0601] Specific example

[0602] Example 1: User's first use

[0603] 1. The user launches the app for the first time, enters their ID and password on the authentication screen, and logs in. Afterward, they link their electronic payment service and social media account.

[0604] 2. The server retrieves the user's past purchase history from external services and stores it in a database. It analyzes consumption trends and builds a user profile.

[0605] Example 2: Real-time information suggestion

[0606] 1. The device detects that the user is in a shopping mall using GPS.

[0607] 2. The server checks the purchase history to confirm that the user has previously purchased items from a specific brand within that mall.

[0608] 3. The server retrieves sales information for the brand from social media and uses a generative AI model to generate optimal suggestions for the user.

[0609] 4. The device sends a push notification to the user saying, "20% off sale at your nearest [brand name]!" and provides a link to more information. When the user clicks the notification, the store's map information and sale details are displayed.

[0610] In this way, the system combines users' purchase history with real-time information to provide optimal shopping suggestions to individual users. This allows users to enjoy shopping efficiently and conveniently. Companies can also improve the accuracy of their targeted marketing, enabling them to attract customers effectively.

[0611] The following describes the processing flow.

[0612] Step 1:

[0613] The user launches the app for the first time and authenticates with their Yahoo! ID. The user enters their ID and password on the login screen and clicks the "Login" button.

[0614] Step 2:

[0615] The server authenticates the user's ID and password, and if authentication is successful, creates a user profile in the database. The server uses an authentication API to verify the user's authentication information.

[0616] Step 3:

[0617] Users perform operations within the app to link their electronic payment services or social media accounts. Users select "Electronic Payment Linkage" or "Social Media Linkage" from the settings menu.

[0618] Step 4:

[0619] The server obtains purchase history data from the electronic payment service with the user's consent. The server uses the electronic payment service's API to retrieve the user's past transaction data and stores it in the database.

[0620] Step 5:

[0621] Users can customize settings based on their interests in the app's settings screen. They can select categories such as fashion, groceries, and electronics, and configure notification frequency and preferred store lists.

[0622] Step 6:

[0623] The device periodically acquires the user's current location information and sends it to the server. The device uses a GPS sensor to collect location information and sends it to the server at regular intervals.

[0624] Step 7:

[0625] The server uses social media information gathering methods to collect real-time information related to users from social media (e.g., trends, campaign information).

[0626] Step 8:

[0627] The server integrates and analyzes the user's purchase history, customization settings, current location information, and social media information. Using artificial intelligence models, it analyzes the user's preferences and behavioral patterns to generate optimal recommendation information.

[0628] Step 9:

[0629] The server collects recommendation information provided by companies and filters it based on user preferences. This ensures that companies' marketing information is also presented to users with high accuracy.

[0630] Step 10:

[0631] The server notifies the user's device of the generated shopping recommendations. These notifications include coupon information and special offer details.

[0632] Step 11:

[0633] The device displays recommended information to the user as a notification. The notification includes a link, which the user can click to view more details. The user taps the notification to access the details page.

[0634] Step 12:

[0635] Users check notifications and click on information that interests them. Clicking displays detailed store and product information, improving the user's shopping experience.

[0636] (Example 1)

[0637] 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".

[0638] Conventional shopping suggestion systems are limited to suggestions based on the user's purchase history and lack the ability to provide dynamic suggestions that utilize real-time location information and the latest trend information obtained from social media. Furthermore, they struggle to provide highly accurate suggestions that integrate user preferences and marketing information from companies. In addition, conventional systems are unable to properly analyze and reflect users' specific interests and behavioral patterns, making it difficult to increase user satisfaction.

[0639] 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.

[0640] In this invention, the server includes user authentication means, external account linking means, purchase history acquisition means, location information acquisition means, SNS information collection means, analysis means using a generation AI model, suggestion information generation means, and suggestion information notification means. This enables highly accurate shopping suggestions tailored to the user's preferences by utilizing real-time location information and the latest trend information.

[0641] "User authentication means" refers to the means used to verify and authenticate a user's identity when they access a system.

[0642] "External account linking methods" refer to methods for linking external service accounts, such as electronic payment services and social media accounts, with the system.

[0643] A "purchase history acquisition method" is a means of acquiring a user's past purchase history from an external service and making it available within the system.

[0644] "Location information acquisition means" refers to a means for acquiring the user's current location in real time and transmitting it to the system.

[0645] "SNS information gathering methods" refer to methods for collecting real-time trend information and campaign information from social media.

[0646] "Analysis methods using generative AI models" refer to methods that use generative AI models to analyze users' purchase history, location information, social media information, etc., in order to analyze users' preferences and behavioral patterns.

[0647] The "proposal information generation means" is a means for generating optimal shopping suggestion information for the user based on the analysis results.

[0648] A "suggestion information notification means" is a means for notifying the user's terminal of the generated shopping suggestion information.

[0649] "Customization settings" are items that users configure based on their interests and preferences, and they serve as the basic data for the system to generate personalized suggestions.

[0650] "Company-provided information" refers to information collected for marketing purposes, such as sales information and recommended product information provided by companies.

[0651] This invention relates to a system that utilizes a user's purchase history, current location information, real-time information from social media, etc., and uses a generated AI model to provide personalized shopping suggestions. The specific system configuration and operation are described below.

[0652] System Configuration

[0653] This system includes the following means:

[0654] User authentication method: A function that verifies and authenticates a user's identity when they access a system.

[0655] External account integration method: A function that allows integration of external service accounts, such as electronic payment services and social media accounts, with the system.

[0656] Purchase history acquisition method: A function that retrieves the user's past purchase history from an external service.

[0657] Location information acquisition method: A function that acquires the user's current location in real time.

[0658] SNS information gathering method: A function that collects real-time trend information and campaign information from social media.

[0659] Analysis method using generative AI models: A function that uses generative AI models to analyze users' purchase history, location information, social media information, etc., and analyzes users' preferences and behavioral patterns.

[0660] Suggestion information generation means: A function that generates optimal shopping suggestion information for the user based on the analysis results.

[0661] Suggestion information notification means: A function that notifies the user's device of the generated shopping suggestion information.

[0662] Operation Description

[0663] The main functions of the system are as follows:

[0664] User authentication and external account integration

[0665] The user launches the app and enters their ID and password on the login screen. The server uses this information to verify the user's identity, and if authentication is successful, grants access to the system. The user then provides more data to the system by linking external accounts (e.g., electronic payment services or social media accounts). At this point, the server receives the information from the linked external accounts and stores it in a database. This makes it possible to understand the user's spending trends.

[0666] Acquisition of purchase history and social media information

[0667] The server retrieves user purchase history using APIs from integrated external services. This data is stored in a database and used for later analysis. Similarly, the server retrieves real-time trend and campaign information using social media APIs. This information is also stored in the database.

[0668] Customization settings and location information acquisition

[0669] Users can customize their interests and preferences in the app's settings screen. For example, setting interests in specific categories (fashion, groceries, electronics, etc.) provides the system with the basis for generating personalized recommendations. The device also acquires the user's location information (GPS information) in real time and sends it to the server.

[0670] Data analysis and shopping suggestion generation

[0671] The server integrates purchase history, customization settings, location information, and real-time information from social media, and inputs it into a generative AI model. Based on this data, the generative AI model generates optimal shopping suggestions for the user. Examples of specific prompts include: "What products did user A recently purchase?", "What categories is user B interested in?", and "What sales information would you recommend for user C, who is currently located in Tokyo?".

[0672] Proposal information notification

[0673] The server notifies the user's device of the shopping suggestion information it has generated. The device displays this notification to the user and provides a link to more detailed information, thereby enhancing the user's convenience in taking action based on the suggestion.

[0674] In this way, the system comprehensively analyzes users' purchase history, location information, and social media information, and uses a generated AI model to provide individually optimized shopping suggestions in real time. This allows users to enjoy efficient and convenient shopping, while also enabling companies to achieve effective marketing.

[0675] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0676] Step 1:

[0677] The user launches the app and enters their ID and password on the login screen.

[0678] Input: User-entered ID and password

[0679] Specific action: The user enters their ID and password on the login screen and presses the "Login" button.

[0680] Output: An authentication request is sent to the server.

[0681] Step 2:

[0682] The server verifies the user's authentication credentials, and if authentication is successful, it grants access to the system.

[0683] Input: Authentication request, database user information

[0684] Specific operation: The server compares the ID and password with the database, and if they match, it returns a response indicating successful authentication.

[0685] Output: Authentication success message and user profile retrieved.

[0686] Step 3:

[0687] Users can add and link electronic payment services and social media accounts on the external account linking screen.

[0688] Input: External account information (e.g., social media account)

[0689] Specific action: The user enters their external account information and presses the "Link" button.

[0690] Output: A connection request is sent to the external service.

[0691] Step 4:

[0692] The server receives information from linked external accounts and adds it to the user profile.

[0693] Input: Account information from an external service

[0694] Specific operation: The server uses the SNS API to retrieve information about linked accounts and saves it to the database.

[0695] Output: Stored in the database as a complete profile.

[0696] Step 5:

[0697] The server retrieves the user's purchase history from an external service.

[0698] Input: Request to the electronic payment service API

[0699] Specific operation: The server uses the API of the electronic payment service to retrieve past purchase history data and store it in the database.

[0700] Output: Purchase history data is saved to the database.

[0701] Step 6:

[0702] The server uses SNS APIs to retrieve real-time trend information and campaign information.

[0703] Input: Request to SNS API

[0704] Specific operation: The server uses the SNS API to retrieve the latest information related to the specified keywords and hashtags.

[0705] Output: The latest information from social media is saved to the database.

[0706] Step 7:

[0707] Users can customize their interests and preferences in the app's settings screen.

[0708] Input: User's interest category information

[0709] Specific operation: The user opens the settings menu, selects categories of interest using checkboxes, and presses the save button.

[0710] Output: The user's interest settings are stored in the database.

[0711] Step 8:

[0712] The device acquires the user's location information (GPS information) in real time and sends it to the server.

[0713] Input: Location information from GPS sensor

[0714] Specific operation: The device periodically acquires location information and sends it to the server.

[0715] Output: Location information is sent to the server and stored in the database.

[0716] Step 9:

[0717] The server integrates purchase history, customization settings, location information, and real-time information from social media, and inputs it into the generating AI model.

[0718] Input: Purchase history, customization settings, location information, social media information

[0719] Specific operation: The server generates various data as a single dataset and inputs prompt statements into the AI ​​model.

[0720] Output: Input dataset for the generative AI model

[0721] Step 10:

[0722] The generative AI model generates optimal shopping suggestions for the user.

[0723] Input: Integrated dataset and prompt statement

[0724] Specific operation: The generating AI model analyzes historical data and trend information based on the prompt text and outputs shopping suggestions.

[0725] Output: Suggested shopping information

[0726] Step 11:

[0727] The server notifies the user's terminal of the generated suggestion information.

[0728] Input: Suggestion information from the generated AI model

[0729] Specific operation: The server sends a push notification to the user's device, sending a message such as "Sale happening at your local [store name]!"

[0730] Output: Push notification message

[0731] Step 12:

[0732] The device displays notifications received by the user and provides a link to more detailed information.

[0733] Input: Push notification from server

[0734] Specific operation: The device displays a notification as a pop-up message, and when the user clicks it, a detailed information page opens.

[0735] Output: Shopping suggestions displayed to the user

[0736] (Application Example 1)

[0737] 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."

[0738] Traditional shopping suggestion systems struggled to fully utilize users' purchase history and location information to provide personalized recommendations, thus failing to improve the in-store shopping experience. Furthermore, the lack of a real-time means for users to receive suggested information while in a physical store led to delays in providing timely information, hindering effective marketing.

[0739] 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.

[0740] In this invention, the server includes a user authentication means, an external account linking means, a purchase history acquisition means, a location information acquisition means, an SNS information collection means, an analysis means using an artificial intelligence model, a suggestion information generation means, a suggestion information notification means, a means for making shopping suggestions in real time when the user approaches a physical store, and a means for providing detailed information and maps based on the notified suggestion information. This makes it possible to provide users with immediate and optimal shopping suggestions by comprehensively utilizing the user's purchase history, location information, real-time information from SNS, etc.

[0741] "User authentication means" refers to the means of verifying that a user is a legitimate user when accessing a system.

[0742] "External account linking method" refers to a method by which a system links with a user's external service accounts (such as electronic payment services or social media accounts).

[0743] A "purchase history acquisition method" is a means of acquiring records of products and services that a user has purchased in the past.

[0744] "Location information acquisition means" refers to methods for acquiring location information using technologies such as GPS in order to determine the user's current location.

[0745] "SNS information gathering methods" refer to methods for collecting real-time information about users and trends from social media.

[0746] "Analysis methods using artificial intelligence models" refer to methods that use artificial intelligence models based on collected data to analyze user preferences and behavioral patterns.

[0747] The "proposal information generation method" is a method for generating optimal shopping information and coupon information for users based on analysis results.

[0748] A "proposal information notification means" is a means of notifying the user's terminal of the generated proposal information.

[0749] "A means of providing shopping suggestions in real time" refers to a method of immediately providing appropriate shopping suggestions to users when they approach a physical store.

[0750] "Means of providing detailed information and maps" refers to means of providing users with links or maps to check more detailed information and store locations based on the suggested shopping information.

[0751] This invention relates to a system that utilizes a user's purchase history, location information, real-time information from social media, etc., and uses a generated AI model to provide personalized shopping suggestions. The system includes means for user authentication, means for linking external accounts, means for acquiring purchase history, means for acquiring location information, means for collecting social media information, means for analysis using an artificial intelligence model, means for generating suggestion information, means for notifying suggestion information, means for providing shopping suggestions in real time, and means for providing detailed information and maps.

[0752] System Configuration

[0753] The system primarily consists of a server and user terminals. The server is responsible for data analysis and generating suggestion information, while the user terminals are responsible for collecting information and displaying the suggested information.

[0754] Specific examples of hardware and software

[0755] Servers: High-performance servers are used for data processing. For example, cloud servers such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) can be used.

[0756] User devices: Smartphones are primarily used. This includes devices with mobile operating systems such as Android and iOS installed.

[0757] Generative AI models: Models using AI frameworks such as PyTorch and TensorFlow are used.

[0758] Feature details

[0759] 1. User Authentication Methods

[0760] When a user logs into the app for the first time, their authentication information is verified and permission to access the system is granted. At this time, the user can link external accounts (for example, electronic payment services or social media accounts).

[0761] 2. External account linking methods

[0762] After successful authentication, the system retrieves the user's purchase history from an external service and stores it in a database. This allows the system to understand the user's spending habits.

[0763] 3. Means of acquiring purchase history

[0764] Purchase history will be collected from electronic payment services and online shops to serve as basic data for analyzing user consumption behavior.

[0765] 4. Location information acquisition means

[0766] Using GPS technology, the system obtains the user's current location in real time. This allows it to identify which physical store the user is approaching.

[0767] 5. Means of gathering information from social media

[0768] It can collect trending and campaign information from social media and analyze user interests in real time.

[0769] 6. Analysis methods using artificial intelligence models

[0770] It integrates purchase history, location information, and social media data to analyze user preferences and behavioral patterns. By using generative AI models such as PyTorch, it generates highly accurate recommendation information.

[0771] 7. Proposal information generation means

[0772] Based on the analysis results, the system generates optimal shopping and coupon information for users. This also takes into account marketing information provided by companies.

[0773] 8. Proposal information notification means

[0774] The generated suggestion information is sent as a push notification to the user's smartphone. The notification includes information on special offers and coupons.

[0775] 9. Means of providing shopping suggestions in real time

[0776] When a user approaches a physical store, the system provides appropriate shopping suggestions on the spot. For example, it might send a notification like, "20% off sale at your nearest [brand name]!"

[0777] 10. Means of providing detailed information and maps

[0778] Based on the suggested information, provide users with links to access more detailed product information and store maps.

[0779] Specific example

[0780] For example, when a user arrives at a shopping mall, the system works as follows: First, a location information acquisition system identifies the user's location, and an AI model analyzes products and stores that the user might be interested in based on their purchase history and social media information. Then, a notification system sends a push notification saying, "There's a 30% off sale at your nearest electronics store!", along with more detailed information and a map.

[0781] Example of a prompt

[0782] Examples of prompt messages that provide suggestions based on the user's purchase history, current location, and social media trends are as follows:

[0783] "The user's purchase history includes electronics products, and their current location is within a shopping mall. According to social media trends, there is a sale on electronics products. Based on this information, we generate optimal shopping suggestions."

[0784] This allows users to enjoy shopping more efficiently, and enables companies to improve the accuracy of their targeted marketing.

[0785] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0786] Step 1: User authentication and external account linking

[0787] Input: User authentication information (User ID, password), external account information (electronic payment service or social media account)

[0788] Processing: The server authenticates the user based on the entered authentication information. After successful authentication, it links with an external account and obtains an authentication token from an external service (electronic payment service or social networking service).

[0789] Output: Authentication token and user profile information

[0790] Specific operation: When a user logs into the app, the server verifies the authentication information, and if successful, displays a pop-up prompting the user to link with an electronic payment service or social media.

[0791] Step 2: Obtain purchase history

[0792] Input: Authentication token, external account information

[0793] Processing: The server retrieves purchase history from electronic payment services and online shops using external account information. The retrieved data is then added to the user's profile.

[0794] Output: Purchase history data

[0795] Specific operation: Upon successful authentication, the server uses the authentication token to retrieve purchase history data from an external service's API and saves it to the database.

[0796] Step 3: Obtaining location information

[0797] Input: GPS data from the user's device

[0798] Process: The device acquires GPS data and sends its current location information to the server. The server uses this location information to determine the place the user is visiting.

[0799] Output: Current location information

[0800] Specific operation: The device obtains the user's current location via GPS and sends it to the server in real time. The server uses this data to determine which physical store the user is in.

[0801] Step 4: Gathering SNS information

[0802] Input: Authentication token, social media account information

[0803] Processing: The server uses social media account information to collect current trend and campaign information. This allows it to obtain real-time information related to the user's interests.

[0804] Output: SNS trend information, campaign information

[0805] Specific operation: The server periodically retrieves trending and campaign information using SNS APIs and stores it in a database.

[0806] Step 5: Data Integration and Analysis

[0807] Input: Purchase history data, current location information, social media trend information

[0808] Processing: The server integrates this data and uses a generative AI model to analyze user preferences and behavioral patterns. This generates foundational data for providing users with optimal shopping recommendations.

[0809] Output: Analysis results (user preference data, behavioral pattern data)

[0810] Specific operation: The server collects data, inputs that data into a generating AI model for analysis, and uses frameworks such as PyTorch to obtain highly accurate results.

[0811] Step 6: Generating Proposal Information

[0812] Input: Analysis results (user preference data, behavioral pattern data)

[0813] Processing: The server generates optimal shopping recommendations for the user based on the analysis results. These recommendations also incorporate marketing information provided by companies.

[0814] Output: Proposal Information

[0815] Specific operation: The server integrates analysis results with marketing information from companies and generates shopping suggestions tailored to the user.

[0816] Step 7: Notification of proposed information

[0817] Input: Proposal Information

[0818] Processing: The server pushes the generated suggestion information to the user's device. The notification may also include information on special offers and coupons.

[0819] Output: Push notification to user's device

[0820] Specific operation: The server sends the suggestion information to the user's smartphone, and a notification is displayed.

[0821] Step 8: Provide detailed information and maps.

[0822] Input: User action upon receiving the push notification (e.g., clicking a link)

[0823] Processing: The device displays more detailed product information and store locations to users who click the link in the push notification.

[0824] Output: Detailed information screen, map display

[0825] Specific operation: When the user clicks the notification, the device retrieves detailed information and map data from the server and displays it.

[0826] 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.

[0827] Modes for carrying out the invention

[0828] System Overview

[0829] This invention relates to a system that utilizes a user's purchase history, current location information, real-time information from social media, and an emotion engine that recognizes the user's emotions, and uses a generative AI model to provide personalized shopping suggestions. Specifically, the system consists of a user authentication means, an external account linking means, a purchase history acquisition means, a location information acquisition means, a social media information collection means, an analysis means using an artificial intelligence model, a suggestion information generation means, an emotion engine, and a suggestion information notification means.

[0830] Program processing

[0831] The system program performs the following operations:

[0832] 1. User authentication and data integration

[0833] When a user logs into the app for the first time, the user authentication method verifies the user's credentials and grants access to the system. At this time, the user can link external accounts (e.g., electronic payment services or social media accounts).

[0834] After successful user authentication, the server retrieves the user's purchase history from an external service. The retrieved data is stored in a database to analyze the user's consumption patterns.

[0835] 2. Customization settings and information gathering

[0836] Users can customize settings based on their interests in the app's settings screen. For example, they can specify that they are interested in a particular category (fashion, groceries, electronics, etc.).

[0837] The device acquires the user's location information in real time and sends it to the server. Additionally, the SNS information gathering mechanism collects real-time information (e.g., trends, campaign information) from social media.

[0838] 3. Emotion Recognition and Data Integration

[0839] The emotion engine installed in the device recognizes the user's emotions in real time and sends that data to the server. The emotion engine identifies emotions by analyzing the user's facial expressions, voice tone, etc.

[0840] The server integrates and analyzes emotional data, purchase history, customization settings, current location information, and social media information. Using an artificial intelligence model, it analyzes user preferences and behavioral patterns, and generates optimal suggestion information that also takes emotional states into account.

[0841] 4. Proposal information generation and notification

[0842] The server also collects recommendations provided by companies and filters them based on the user's preferences and emotions. This ensures that companies' marketing information is also presented to users with high accuracy.

[0843] The server notifies the user's device of the generated shopping recommendations. These notifications include coupon information and special offer details.

[0844] The device displays recommended information to the user as a notification. If the user shows interest in the suggestion, it provides a link to access detailed store and product information.

[0845] Specific example

[0846] Example 1: User's first use

[0847] 1. The user launches the app for the first time, enters their ID and password on the authentication screen, and logs in. Afterward, they link their electronic payment service and social media account.

[0848] 2. The server retrieves the user's past purchase history from external services and stores it in a database. It analyzes consumption trends and builds a user profile.

[0849] Example 2: Suggestions based on emotions and real-time information

[0850] 1. The device detects the user's location in a shopping mall using GPS. Simultaneously, the emotion engine recognizes the user's state of excitement from their facial expressions.

[0851] 2. The server checks the purchase history to confirm that the user has previously purchased items from a specific brand within that mall.

[0852] 3. The server retrieves sales information for the brand from social media and uses a generative AI model and sentiment data to generate optimal suggestions for the user.

[0853] 4. The device sends a push notification to the user saying, "20% off sale at your nearest [brand name]!" and provides a link to more information. When the user clicks the notification, the store's map information and sale details are displayed.

[0854] In this way, the system combines users' purchase history, current location information, and real-time emotional information to provide optimal shopping suggestions for each individual user. This allows users to have a more personalized and efficient shopping experience. Businesses can also improve the accuracy of targeted marketing that takes into account users' emotional states, enabling more effective customer acquisition.

[0855] The following describes the processing flow.

[0856] Step 1:

[0857] The user launches the app for the first time and authenticates with their Yahoo! ID. The user enters their ID and password on the login screen and clicks the "Login" button.

[0858] Step 2:

[0859] The server authenticates the user's ID and password, and if authentication is successful, creates a user profile in the database. The server uses an authentication API to verify the user's authentication information.

[0860] Step 3:

[0861] Users link their electronic payment services and social media accounts within the app. Users select "Electronic Payment Linkage" or "Social Media Linkage" from the settings menu.

[0862] Step 4:

[0863] The server obtains purchase history data from the electronic payment service with the user's consent. The server uses the electronic payment service's API to retrieve the user's past transaction data and stores it in the database.

[0864] Step 5:

[0865] Users can customize settings based on their interests in the app's settings screen. They can select categories such as fashion, groceries, and electronics, and configure notification frequency and preferred store lists.

[0866] Step 6:

[0867] The device periodically acquires the user's current location information and sends it to the server. The device uses a GPS sensor to collect location information and sends it to the server at regular intervals.

[0868] Step 7:

[0869] The emotion engine installed in the device recognizes the user's emotions in real time and sends that data to the server. The emotion engine identifies emotions by analyzing the user's facial expressions, voice tone, etc.

[0870] Step 8:

[0871] The server uses social media information gathering methods to collect real-time information related to users from social media (e.g., trends, campaign information).

[0872] Step 9:

[0873] The server integrates and analyzes the user's purchase history, customization settings, current location information, sentiment data, and social media information. Using artificial intelligence models, it analyzes the user's preferences and behavioral patterns to generate optimal recommendation information.

[0874] Step 10:

[0875] The server collects recommendation information provided by companies and filters it based on user preferences and sentiment data. This ensures that companies' marketing information is also suggested to users with high accuracy.

[0876] Step 11:

[0877] The server notifies the user's device of the generated shopping recommendations. These notifications include coupon information and special offer details.

[0878] Step 12:

[0879] The device displays recommended information to the user as a notification. The notification includes a link, which the user can click to view more details. The user taps the notification to access the details page.

[0880] Step 13:

[0881] Users check notifications and click on information that interests them. Clicking displays detailed store and product information, improving the user's shopping experience.

[0882] (Example 2)

[0883] 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".

[0884] In today's shopping landscape, providing personalized purchase suggestions to users is crucial for maintaining high user satisfaction. However, traditional systems typically rely solely on purchase history and location data for suggestions, failing to consider users' momentary emotions or real-time social media information. As a result, providing optimal suggestions for users has been difficult, and the marketing effectiveness for companies has been limited.

[0885] 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.

[0886] In this invention, the server includes user authentication means, external account linking means, purchase history acquisition means, location information acquisition means, SNS information collection means, emotion recognition means, analysis means using an artificial intelligence model, suggestion information generation means, and suggestion information notification means. This enables comprehensive analysis of the user's purchase history, current location information, real-time emotion information, and SNS information to provide optimal shopping suggestions to individual users.

[0887] "User authentication means" refers to the means used to verify the identity of a user when they access a system.

[0888] "External account linking methods" refer to methods for linking a system with external services (e.g., electronic payment services or social networking services).

[0889] A "purchase history acquisition method" is a means of acquiring a user's past purchase history and importing it into the system.

[0890] "Location information acquisition means" refers to methods for acquiring the user's current location information using GPS or similar technologies.

[0891] "SNS information gathering methods" refer to methods for collecting information from social media in real time.

[0892] "Means of recognizing emotions" refers to methods for identifying emotions from a user's facial expressions, voice, etc.

[0893] "Analysis methods using artificial intelligence models" refer to methods for analyzing data acquired using artificial intelligence models to analyze user preferences and behavioral patterns.

[0894] The "proposal information generation means" is a means of generating optimal shopping suggestions for the user based on the analysis results.

[0895] A "proposal information notification means" is a means of notifying the user's terminal of the generated proposal information.

[0896] Modes for carrying out the invention

[0897] System Program Overview

[0898] This invention relates to a system that utilizes a user's purchase history, current location information, real-time information from social media, and an emotion engine that recognizes the user's emotions, and uses a generative AI model to provide personalized shopping suggestions. This system includes user authentication means, external account linking means, purchase history acquisition means, location information acquisition means, social media information collection means, emotion recognition means, analysis means using an artificial intelligence model, suggestion information generation means, and suggestion information notification means.

[0899] Hardware and software to use

[0900] Server: Performs database management, API integration, and data analysis using artificial intelligence models.

[0901] Device: Smartphones, tablets, etc. It receives user input and activates the emotion engine.

[0902] Emotion engine: Software that analyzes the user's facial expressions and voice tone to identify their emotions.

[0903] GPS function: Obtains the user's location information.

[0904] SNS information gathering tools: Scraping tools and APIs for collecting real-time information from social media.

[0905] Explanation of the program's processing

[0906] 1. User Authentication

[0907] The user logs into the app for the first time, and their identity is verified through an authentication method. The authentication information is securely transmitted to the server.

[0908] The server verifies the received authentication information and initiates external account linking upon successful authentication.

[0909] 2. External account integration and data acquisition

[0910] The user links their account with an electronic payment service or social media account. Authentication information for the linking service is entered.

[0911] The server uses APIs from external services to retrieve purchase history and social media activity data, and stores it in a database.

[0912] 3. Customization settings

[0913] Users can customize their settings within the app based on their interests. For example, they can select specific categories or brands.

[0914] The device sends the configured information to the server, which then stores it in the database.

[0915] 4. Obtaining location information

[0916] The device periodically obtains the user's current location using its GPS function and sends it to the server.

[0917] The server stores location information in a database and integrates it with related data.

[0918] 5. Obtaining SNS information

[0919] The device uses a social networking information gathering tool to acquire real-time information related to the specified keywords.

[0920] The server analyzes the collected information and stores it in a database.

[0921] 6. Emotion recognition

[0922] The device uses its camera and microphone to identify emotions from the user's facial expressions and voice, and acquires emotion data.

[0923] The device sends emotional data to the server.

[0924] 7. Data Integration and Analysis

[0925] The server integrates emotional data, purchase history, customization settings, current location information, and social media information, and analyzes the data using an artificial intelligence model.

[0926] Artificial intelligence models analyze user preferences and behavioral patterns.

[0927] 8. Generation of proposed information

[0928] The server collects marketing information provided by companies and filters it based on the user's preferences and emotions.

[0929] We use an artificial intelligence model to generate optimal shopping suggestions.

[0930] 9. Notification of proposed information

[0931] The server notifies the terminal of the shopping suggestions it has generated. The notification includes coupon information and special offer information.

[0932] The device displays a notification to the user and provides a link to more information.

[0933] Specific example

[0934] 1. The user logs in for the first time and links their electronic payment service with their social media account.

[0935] 2. The server retrieves purchase history from an external service and saves it to the database.

[0936] 3. The GPS detects that the user is in a shopping mall, and the emotion engine recognizes the user's state of excitement.

[0937] 4. The server generates optimal suggestions using purchase history and sales information from social media.

[0938] 5. The device sends a push notification saying, "20% off sale at your nearest [brand name] store."

[0939] Examples of prompts to input into a generative AI model

[0940] "This user has a history of frequently purchasing fashion items. They are currently in a shopping mall. Their facial expression indicates excitement. Please generate effective shopping suggestions for this user."

[0941] "This user is interested in electronics and is currently located in central Tokyo. They have sales information for electronics brands on social media. Please create the best possible suggestions for this user."

[0942] In this way, the system continuously collects data from multiple sources and provides personalized shopping suggestions to each user, thereby improving the user experience and maximizing the marketing effectiveness of companies.

[0943] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0944] Step 1:

[0945] User Authentication

[0946] Operation:

[0947] The user launches the app for the first time and enters their ID and password on the authentication screen.

[0948] The server compares the received authentication information with the user information in the database, and if authentication is successful, it starts a session.

[0949] Input: User ID, Password

[0950] Output: Session started based on authentication success / failure result.

[0951] Specific processing:

[0952] The server receives the authentication information and compares it with the information in the database. If authentication is successful, it generates session information and grants the user access.

[0953] Step 2:

[0954] External account integration and data retrieval

[0955] Operation:

[0956] Users enter authentication information for linking their electronic payment service or social media account within the app.

[0957] The server sends API requests to linked external services to retrieve user purchase history and social media activity data. This data is stored in a database.

[0958] Input: External account credentials

[0959] Output: Purchase history data, social media activity data

[0960] Specific processing:

[0961] The server calls an external API to retrieve the user's purchase history and social media data. The retrieved data is stored in the database as the user's profile.

[0962] Step 3:

[0963] Customization settings

[0964] Operation:

[0965] Users can customize settings based on their interests in the app's settings screen. For example, they can select specific categories or brands.

[0966] The terminal sends the entered configuration information to the server and stores it in the database.

[0967] Input: User customization settings information

[0968] Output: Configuration information stored in the database

[0969] Specific processing:

[0970] The user sends their selected customization settings from the terminal to the server, which stores this information in a database for use in subsequent analysis processes.

[0971] Step 4:

[0972] Location information acquisition

[0973] Operation:

[0974] The device periodically obtains the user's current location using its GPS function and sends it to the server.

[0975] The server stores the received location information in a database.

[0976] Input: Location information obtained from GPS

[0977] Output: Location information stored in the database

[0978] Specific processing:

[0979] The device periodically uses GPS to obtain the user's current location and sends it to the server. The server stores the received location information in a database and updates the location information in real time.

[0980] Step 5:

[0981] Acquisition of SNS information

[0982] Operation:

[0983] The device retrieves real-time information from social media information gathering tools based on specified keywords.

[0984] The server stores the collected SNS information in a database and integrates it into the user's profile.

[0985] Input: Collected SNS information

[0986] Output: SNS information stored in the database

[0987] Specific processing:

[0988] The device uses an SNS collection tool to acquire information related to specified keywords and sends it to the server. The server stores the collected SNS information in a database.

[0989] Step 6:

[0990] emotion recognition

[0991] Operation:

[0992] The device uses its camera and microphone to analyze the user's facial expressions and voice in real time and identify their emotions.

[0993] The device sends the identified emotion data to the server.

[0994] Input: Facial expression, voice tone

[0995] Output: Identified sentiment data

[0996] Specific processing:

[0997] The emotion engine uses information acquired from the device's camera and microphone to recognize the user's emotions and sends the results to the server. The server stores the emotion data in a database.

[0998] Step 7:

[0999] Data Integration and Analysis

[1000] Operation:

[1001] The server integrates and analyzes emotional data, purchase history, customization settings, current location information, and social media information.

[1002] Using artificial intelligence models, we analyze user preferences and behavioral patterns to generate optimal shopping recommendations.

[1003] Input: Sentimental data, purchase history, customization settings, current location information, social media information

[1004] Output: Analysis results, proposed information

[1005] Specific processing:

[1006] The server uses integrated data to perform analysis using an artificial intelligence model, analyzing user preferences and behavioral patterns. Based on these results, it generates optimal shopping recommendations.

[1007] Step 8:

[1008] Generation of proposed information

[1009] Operation:

[1010] The server collects marketing information provided by companies (e.g., coupon information, special offer information) and filters it based on the user's preferences and emotions.

[1011] We use a generative AI model to generate optimal shopping suggestions for the user.

[1012] Input: Marketing information and analysis results from companies.

[1013] Output: Optimal shopping suggestions

[1014] Specific processing:

[1015] The system filters information provided by companies and uses a generative AI model to create optimal suggestions that take into account the user's preferences and emotional state.

[1016] Step 9:

[1017] Notification of proposed information

[1018] Operation:

[1019] The server notifies the user's device of the shopping suggestions it has generated. These notifications include coupon information and special offer information.

[1020] The device will display this notification to the user as a push notification, providing a link to more information.

[1021] Input: Generated shopping suggestions

[1022] Output: Notification to user terminal

[1023] Specific processing:

[1024] The server sends the generated suggestion information to the user's device, which then displays it to the user as a push notification. The notification includes a link to more information, which, when tapped by the user, displays information about the relevant store or product.

[1025] In this way, each step works together to create a system that can efficiently provide personalized suggestions to users.

[1026] (Application Example 2)

[1027] 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."

[1028] Traditional online shopping systems offered recommendations based on user preferences, but they did not provide personalized suggestions that took into account real-time emotional states or location information. This made it difficult to provide a shopping experience that aligned with users' actual interests and desires, resulting in many users spending a considerable amount of time finding suitable products. Furthermore, companies faced the challenge of being unable to conduct effective marketing based on users' real-time emotions and behavior.

[1029] 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.

[1030] In this invention, the server includes user authentication means, external account linking means, purchase history acquisition means, location information acquisition means, SNS information collection means, emotion recognition engine, analysis means using an artificial intelligence model, suggestion information generation means, and suggestion information notification means. This enables integrated analysis of the user's purchase history, current location information, SNS information, and emotional state, and allows for optimal shopping suggestions for each individual user using a generated AI model.

[1031] "User authentication means" refers to a method of verifying a user's authentication information and granting them access to the system.

[1032] "External account linking methods" refer to methods for linking with external services such as electronic payment services and social media accounts.

[1033] "Purchase history acquisition method" refers to a method for acquiring a user's past purchase history and storing it in the system.

[1034] "Location information acquisition means" refers to means of collecting information about the user's current location.

[1035] "SNS information gathering methods" refer to methods for collecting data such as trend information and campaign information from social networking services.

[1036] An "emotion engine" is a method of identifying emotions by analyzing the user's facial expressions and voice tone.

[1037] "Analysis methods using artificial intelligence models" refer to methods that use artificial intelligence to analyze user preferences and behavioral patterns.

[1038] The "proposal information generation means" is a means of generating shopping suggestions that are optimal for each individual user based on user data.

[1039] A "proposal information notification means" is a means of notifying the user's terminal of the generated proposal information.

[1040] "Custom settings" refers to the ability for users to adjust application settings based on their own interests.

[1041] "Company-provided information" refers to recommended information and campaign information offered by companies.

[1042] System Overview

[1043] This invention is a system that collects user purchase history, current location information, real-time information from social media, and sentiment information, and analyzes and integrates them to provide optimal shopping suggestions for individual users. Specifically, it provides a series of systems that generate and notify suggestion information using an artificial intelligence model for analyzing various types of information and an sentiment engine that recognizes user sentiment in real time. This system includes the following main means:

[1044] 1. User authentication method: Verify the user's authentication information and grant access to the system.

[1045] 2. External account linking methods: Methods for linking with electronic payment services and social media accounts.

[1046] 3. Purchase history acquisition method: Acquire the user's past purchase history and save it in the system.

[1047] 4. Means of acquiring location information: Collect the user's current location information.

[1048] 5. Social media information gathering methods: Gather trend information and campaign information from social networking services.

[1049] 6. Emotion Engine: Analyzes the user's facial expressions and voice tone to identify emotions.

[1050] 7. Analysis methods using artificial intelligence models: Use artificial intelligence to analyze user preferences and behavioral patterns.

[1051] 8. Suggestion information generation means: Based on user data, it generates shopping suggestions that are optimal for each individual user.

[1052] 9. Proposal Information Notification Means: Generated proposal information is notified to the user's terminal.

[1053] Program processing

[1054] The server collects and analyzes various data, generates personalized recommendations for each user, and notifies the user's device. This allows users to have a more efficient and personalized shopping experience. Specifically, the following data processing or calculations are performed:

[1055] 1. Use of hardware and software:

[1056] Smartphones: Used for user authentication, location information acquisition, emotion recognition, etc.

[1057] Emotion Engine: A library for recognizing user emotions in real time.

[1058] Artificial intelligence model: Data analysis and proposal information are generated using the GenerativeAIModel library.

[1059] 2. Data collection and analysis:

[1060] The server collects purchase history from external accounts and stores it in a database.

[1061] Real-time location information is collected using a GPS module, and social media information is obtained via an API.

[1062] User sentiment data is collected by the sentiment engine and sent to the server.

[1063] 3. Proposal generation using artificial intelligence models:

[1064] The server integrates all collected data and generates optimal shopping suggestions using a generative AI model. This generative AI model operates based on the following prompts:

[1065] "User ID: 1234, Location: Tokyo, Emotion: Excited, Purchase History: Fashion, Social Media Trend: Autumn Sale. Please generate the best suggestions for this user."

[1066] Specific example

[1067] 1. First-time use case:

[1068] The user launches the app for the first time, enters their ID and password on the authentication screen to log in, and then links their electronic payment service and social media account.

[1069] The server retrieves the user's past purchase history from external services and stores it in a database. It then analyzes consumption trends and builds user profiles.

[1070] 2. Case of real-time proposals:

[1071] The system uses GPS to detect that the user is in a shopping mall. Simultaneously, an emotion engine recognizes the user's level of excitement from their facial expressions.

[1072] The server checks the purchase history to confirm that the user has previously purchased items from a specific brand within that mall.

[1073] The server retrieves sales information for a brand from social media, and uses a generative AI model and sentiment data to generate optimal suggestions for the user.

[1074] A push notification is sent to the user's device stating, "20% off sale at your nearest [brand name]!" and providing a link to more information. When the user clicks the notification, store map information and sale details are displayed.

[1075] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1076] Step 1:

[1077] User authentication and external integration

[1078] Input: User authentication information (ID, password), external account information (electronic payment account, social media account)

[1079] Specific operation: When a user logs into the smartphone app for the first time, they enter authentication information and authenticate using the authentication method. Additionally, users can link their accounts with electronic payment services and social media accounts using external account linking methods.

[1080] Output: Authentication success and the status of the external account linkage are sent to the server.

[1081] Step 2:

[1082] Retrieving purchase history

[1083] Input: User ID

[1084] Specific operation: The server collects the user's past purchase history using a purchase history acquisition method from an external service. The acquired purchase history is stored in a database and used to analyze the user's consumption trends.

[1085] Output: Purchase history data is saved to the server's database.

[1086] Step 3:

[1087] Retrieve custom settings

[1088] Input: User's interests and settings information

[1089] Specific operation: The user selects a category of interest (e.g., fashion, groceries, electronics, etc.) from the app's settings screen.

[1090] Output: Configuration information is sent to the server.

[1091] Step 4:

[1092] Real-time information gathering

[1093] Input: Location information, social media information

[1094] Specific operation: The device's GPS module acquires the user's location information in real time and sends it to the server. In addition, the SNS information collection method collects real-time trend information and campaign information from SNS.

[1095] Output: Location information and SNS information are sent to the server.

[1096] Step 5:

[1097] emotion recognition

[1098] Input: User's facial expression, voice tone

[1099] Specific operation: The emotion engine uses the camera and microphone built into the device to recognize the user's emotions in real time. The acquired emotion data is sent to the server.

[1100] Output: Emotional data is sent to the server.

[1101] Step 6:

[1102] Data integration and analysis

[1103] Input: Purchase history data, settings information, location information, social media information, sentiment data

[1104] Specific operation: The server integrates all collected data and analyzes it using an artificial intelligence model. The generative AI model generates optimal suggestion information based on the user's preferences, behavioral patterns, and emotional state. Instructions are given to the AI ​​model using prompts. Example of a prompt: "User ID: 1234, Location: Tokyo, Emotion: Excited, Purchase History: Fashion, SNS Trend: Autumn Sale, Please generate optimal suggestions for the user."

[1105] Output: Generated suggestion information is obtained.

[1106] Step 7:

[1107] Notification of proposed information

[1108] Input: Generated suggestion information

[1109] Specific operation: The server sends generated shopping suggestion information to the user's terminal via push notifications through the suggestion information notification system. The notification also includes a link to detailed information.

[1110] Output: The suggested information is displayed as a notification on the user's device.

[1111] Step 8:

[1112] Providing detailed information

[1113] Input: User action (notification click)

[1114] Specific operation: When the user clicks the notification, the app displays detailed information (store map, sale details, etc.).

[1115] Output: The detailed information screen is displayed on the user's device.

[1116] 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.

[1117] 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.

[1118] 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.

[1119] [Third Embodiment]

[1120] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1121] 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.

[1122] 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).

[1123] 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.

[1124] 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.

[1125] 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).

[1126] 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.

[1127] 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.

[1128] 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.

[1129] 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.

[1130] 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.

[1131] 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".

[1132] Modes for carrying out the invention

[1133] System Overview

[1134] This invention relates to a system that utilizes a user's purchase history, current location information, real-time information from social media, etc., and uses a generated AI model to provide personalized shopping suggestions. Specifically, the system consists of a user authentication means, an external account linking means, a purchase history acquisition means, a location information acquisition means, a social media information collection means, an analysis means using an artificial intelligence model, a suggestion information generation means, and a suggestion information notification means.

[1135] Program processing

[1136] The system program performs the following operations:

[1137] 1. User authentication and data integration

[1138] When a user logs into the app for the first time, the user authentication method verifies the user's credentials and grants access to the system. At this time, the user can link external accounts (e.g., electronic payment services or social media accounts).

[1139] After successful user authentication, the server retrieves the user's purchase history from an external service. The retrieved data is stored in a database to analyze the user's consumption patterns.

[1140] 2. Customization settings and information gathering

[1141] Users can customize settings based on their interests in the app's settings screen. For example, they can specify that they are interested in a particular category (fashion, groceries, electronics, etc.).

[1142] The device acquires the user's location information in real time and sends it to the server. Additionally, the SNS information gathering mechanism collects real-time information (e.g., trends, campaign information) from social media.

[1143] 3. Data Analysis and Proposal Generation

[1144] The server integrates and analyzes the user's purchase history, customization settings, current location information, and real-time information from social media. Using an artificial intelligence model, it analyzes the user's preferences and behavioral patterns to generate optimal shopping recommendations.

[1145] The server also collects recommendations from companies and selects those that match the user's preferences. This ensures that marketing information provided by companies is also suggested to users with high accuracy.

[1146] 4. Information Distribution and User Interaction

[1147] The server notifies the user's device of the generated shopping recommendations. These notifications include coupon information and special offer details.

[1148] The device displays recommended information to the user as a notification. If the user shows interest in the suggestion, it provides a link to access detailed store and product information.

[1149] Specific example

[1150] Example 1: User's first use

[1151] 1. The user launches the app for the first time, enters their ID and password on the authentication screen, and logs in. Afterward, they link their electronic payment service and social media account.

[1152] 2. The server retrieves the user's past purchase history from external services and stores it in a database. It analyzes consumption trends and builds a user profile.

[1153] Example 2: Real-time information suggestion

[1154] 1. The device detects that the user is in a shopping mall using GPS.

[1155] 2. The server checks the purchase history to confirm that the user has previously purchased items from a specific brand within that mall.

[1156] 3. The server retrieves sales information for the brand from social media and uses a generative AI model to generate optimal suggestions for the user.

[1157] 4. The device sends a push notification to the user saying, "20% off sale at your nearest [brand name]!" and provides a link to more information. When the user clicks the notification, the store's map information and sale details are displayed.

[1158] In this way, the system combines users' purchase history with real-time information to provide optimal shopping suggestions to individual users. This allows users to enjoy shopping efficiently and conveniently. Companies can also improve the accuracy of their targeted marketing, enabling them to attract customers effectively.

[1159] The following describes the processing flow.

[1160] Step 1:

[1161] The user launches the app for the first time and authenticates with their Yahoo! ID. The user enters their ID and password on the login screen and clicks the "Login" button.

[1162] Step 2:

[1163] The server authenticates the user's ID and password, and if authentication is successful, creates a user profile in the database. The server uses an authentication API to verify the user's authentication information.

[1164] Step 3:

[1165] Users perform operations within the app to link their electronic payment services or social media accounts. Users select "Electronic Payment Linkage" or "Social Media Linkage" from the settings menu.

[1166] Step 4:

[1167] The server obtains purchase history data from the electronic payment service with the user's consent. The server uses the electronic payment service's API to retrieve the user's past transaction data and stores it in the database.

[1168] Step 5:

[1169] Users can customize settings based on their interests in the app's settings screen. They can select categories such as fashion, groceries, and electronics, and configure notification frequency and preferred store lists.

[1170] Step 6:

[1171] The device periodically acquires the user's current location information and sends it to the server. The device uses a GPS sensor to collect location information and sends it to the server at regular intervals.

[1172] Step 7:

[1173] The server uses social media information gathering methods to collect real-time information related to users from social media (e.g., trends, campaign information).

[1174] Step 8:

[1175] The server integrates and analyzes the user's purchase history, customization settings, current location information, and social media information. Using artificial intelligence models, it analyzes the user's preferences and behavioral patterns to generate optimal recommendation information.

[1176] Step 9:

[1177] The server collects recommendation information provided by companies and filters it based on user preferences. This ensures that companies' marketing information is also presented to users with high accuracy.

[1178] Step 10:

[1179] The server notifies the user's device of the generated shopping recommendations. These notifications include coupon information and special offer details.

[1180] Step 11:

[1181] The device displays recommended information to the user as a notification. The notification includes a link, which the user can click to view more details. The user taps the notification to access the details page.

[1182] Step 12:

[1183] Users check notifications and click on information that interests them. Clicking displays detailed store and product information, improving the user's shopping experience.

[1184] (Example 1)

[1185] 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."

[1186] Conventional shopping suggestion systems are limited to suggestions based on the user's purchase history and lack the ability to provide dynamic suggestions that utilize real-time location information and the latest trend information obtained from social media. Furthermore, they struggle to provide highly accurate suggestions that integrate user preferences and marketing information from companies. In addition, conventional systems are unable to properly analyze and reflect users' specific interests and behavioral patterns, making it difficult to increase user satisfaction.

[1187] 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.

[1188] In this invention, the server includes user authentication means, external account linking means, purchase history acquisition means, location information acquisition means, SNS information collection means, analysis means using a generation AI model, suggestion information generation means, and suggestion information notification means. This enables highly accurate shopping suggestions tailored to the user's preferences by utilizing real-time location information and the latest trend information.

[1189] "User authentication means" refers to the means used to verify and authenticate a user's identity when they access a system.

[1190] "External account linking methods" refer to methods for linking external service accounts, such as electronic payment services and social media accounts, with the system.

[1191] A "purchase history acquisition method" is a means of acquiring a user's past purchase history from an external service and making it available within the system.

[1192] "Location information acquisition means" refers to a means for acquiring the user's current location in real time and transmitting it to the system.

[1193] "SNS information gathering methods" refer to methods for collecting real-time trend information and campaign information from social media.

[1194] "Analysis methods using generative AI models" refer to methods that use generative AI models to analyze users' purchase history, location information, social media information, etc., in order to analyze users' preferences and behavioral patterns.

[1195] The "proposal information generation means" is a means for generating optimal shopping suggestion information for the user based on the analysis results.

[1196] A "suggestion information notification means" is a means for notifying the user's terminal of the generated shopping suggestion information.

[1197] "Customization settings" are items that users configure based on their interests and preferences, and they serve as the basic data for the system to generate personalized suggestions.

[1198] "Company-provided information" refers to information collected for marketing purposes, such as sales information and recommended product information provided by companies.

[1199] This invention relates to a system that utilizes a user's purchase history, current location information, real-time information from social media, etc., and uses a generated AI model to provide personalized shopping suggestions. The specific system configuration and operation are described below.

[1200] System Configuration

[1201] This system includes the following means:

[1202] User authentication method: A function that verifies and authenticates a user's identity when they access a system.

[1203] External account integration method: A function that allows integration of external service accounts, such as electronic payment services and social media accounts, with the system.

[1204] Purchase history acquisition method: A function that retrieves the user's past purchase history from an external service.

[1205] Location information acquisition method: A function that acquires the user's current location in real time.

[1206] SNS information gathering method: A function that collects real-time trend information and campaign information from social media.

[1207] Analysis method using generative AI models: A function that uses generative AI models to analyze users' purchase history, location information, social media information, etc., and analyzes users' preferences and behavioral patterns.

[1208] Suggestion information generation means: A function that generates optimal shopping suggestion information for the user based on the analysis results.

[1209] Suggestion information notification means: A function that notifies the user's device of the generated shopping suggestion information.

[1210] Operation Description

[1211] The main functions of the system are as follows:

[1212] User authentication and external account integration

[1213] The user launches the app and enters their ID and password on the login screen. The server uses this information to verify the user's identity, and if authentication is successful, grants access to the system. The user then provides more data to the system by linking external accounts (e.g., electronic payment services or social media accounts). At this point, the server receives the information from the linked external accounts and stores it in a database. This makes it possible to understand the user's spending trends.

[1214] Acquisition of purchase history and social media information

[1215] The server retrieves user purchase history using APIs from integrated external services. This data is stored in a database and used for later analysis. Similarly, the server retrieves real-time trend and campaign information using social media APIs. This information is also stored in the database.

[1216] Customization settings and location information acquisition

[1217] Users can customize their interests and preferences in the app's settings screen. For example, setting interests in specific categories (fashion, groceries, electronics, etc.) provides the system with the basis for generating personalized recommendations. The device also acquires the user's location information (GPS information) in real time and sends it to the server.

[1218] Data analysis and shopping suggestion generation

[1219] The server integrates purchase history, customization settings, location information, and real-time information from social media, and inputs it into a generative AI model. Based on this data, the generative AI model generates optimal shopping suggestions for the user. Examples of specific prompts include: "What products did user A recently purchase?", "What categories is user B interested in?", and "What sales information would you recommend for user C, who is currently located in Tokyo?".

[1220] Proposal information notification

[1221] The server notifies the user's device of the shopping suggestion information it has generated. The device displays this notification to the user and provides a link to more detailed information, thereby enhancing the user's convenience in taking action based on the suggestion.

[1222] In this way, the system comprehensively analyzes users' purchase history, location information, and social media information, and uses a generated AI model to provide individually optimized shopping suggestions in real time. This allows users to enjoy efficient and convenient shopping, while also enabling companies to achieve effective marketing.

[1223] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1224] Step 1:

[1225] The user launches the app and enters their ID and password on the login screen.

[1226] Input: User-entered ID and password

[1227] Specific action: The user enters their ID and password on the login screen and presses the "Login" button.

[1228] Output: An authentication request is sent to the server.

[1229] Step 2:

[1230] The server verifies the user's authentication credentials, and if authentication is successful, it grants access to the system.

[1231] Input: Authentication request, database user information

[1232] Specific operation: The server compares the ID and password with the database, and if they match, it returns a response indicating successful authentication.

[1233] Output: Authentication success message and user profile retrieved.

[1234] Step 3:

[1235] Users can add and link electronic payment services and social media accounts on the external account linking screen.

[1236] Input: External account information (e.g., social media account)

[1237] Specific action: The user enters their external account information and presses the "Link" button.

[1238] Output: A connection request is sent to the external service.

[1239] Step 4:

[1240] The server receives information from linked external accounts and adds it to the user profile.

[1241] Input: Account information from an external service

[1242] Specific operation: The server uses the SNS API to retrieve information about linked accounts and saves it to the database.

[1243] Output: Stored in the database as a complete profile.

[1244] Step 5:

[1245] The server retrieves the user's purchase history from an external service.

[1246] Input: Request to the electronic payment service API

[1247] Specific operation: The server uses the API of the electronic payment service to retrieve past purchase history data and store it in the database.

[1248] Output: Purchase history data is saved to the database.

[1249] Step 6:

[1250] The server uses SNS APIs to retrieve real-time trend information and campaign information.

[1251] Input: Request to SNS API

[1252] Specific operation: The server uses the SNS API to retrieve the latest information related to the specified keywords and hashtags.

[1253] Output: The latest information from social media is saved to the database.

[1254] Step 7:

[1255] Users can customize their interests and preferences in the app's settings screen.

[1256] Input: User's interest category information

[1257] Specific operation: The user opens the settings menu, selects categories of interest using checkboxes, and presses the save button.

[1258] Output: The user's interest settings are stored in the database.

[1259] Step 8:

[1260] The device acquires the user's location information (GPS information) in real time and sends it to the server.

[1261] Input: Location information from GPS sensor

[1262] Specific operation: The device periodically acquires location information and sends it to the server.

[1263] Output: Location information is sent to the server and stored in the database.

[1264] Step 9:

[1265] The server integrates purchase history, customization settings, location information, and real-time information from social media, and inputs it into the generating AI model.

[1266] Input: Purchase history, customization settings, location information, social media information

[1267] Specific operation: The server generates various data as a single dataset and inputs prompt statements into the AI ​​model.

[1268] Output: Input dataset for the generative AI model

[1269] Step 10:

[1270] The generative AI model generates optimal shopping suggestions for the user.

[1271] Input: Integrated dataset and prompt statement

[1272] Specific operation: The generating AI model analyzes historical data and trend information based on the prompt text and outputs shopping suggestions.

[1273] Output: Suggested shopping information

[1274] Step 11:

[1275] The server notifies the user's terminal of the generated suggestion information.

[1276] Input: Suggestion information from the generated AI model

[1277] Specific operation: The server sends a push notification to the user's device, sending a message such as "Sale happening at your local [store name]!"

[1278] Output: Push notification message

[1279] Step 12:

[1280] The device displays notifications received by the user and provides a link to more detailed information.

[1281] Input: Push notification from server

[1282] Specific operation: The device displays a notification as a pop-up message, and when the user clicks it, a detailed information page opens.

[1283] Output: Shopping suggestions displayed to the user

[1284] (Application Example 1)

[1285] 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."

[1286] Traditional shopping suggestion systems struggled to fully utilize users' purchase history and location information to provide personalized recommendations, thus failing to improve the in-store shopping experience. Furthermore, the lack of a real-time means for users to receive suggested information while in a physical store led to delays in providing timely information, hindering effective marketing.

[1287] 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.

[1288] In this invention, the server includes a user authentication means, an external account linking means, a purchase history acquisition means, a location information acquisition means, an SNS information collection means, an analysis means using an artificial intelligence model, a suggestion information generation means, a suggestion information notification means, a means for making shopping suggestions in real time when the user approaches a physical store, and a means for providing detailed information and maps based on the notified suggestion information. This makes it possible to provide users with immediate and optimal shopping suggestions by comprehensively utilizing the user's purchase history, location information, real-time information from SNS, etc.

[1289] "User authentication means" refers to the means of verifying that a user is a legitimate user when accessing a system.

[1290] "External account linking method" refers to a method by which a system links with a user's external service accounts (such as electronic payment services or social media accounts).

[1291] A "purchase history acquisition method" is a means of acquiring records of products and services that a user has purchased in the past.

[1292] "Location information acquisition means" refers to methods for acquiring location information using technologies such as GPS in order to determine the user's current location.

[1293] "SNS information gathering methods" refer to methods for collecting real-time information about users and trends from social media.

[1294] "Analysis methods using artificial intelligence models" refer to methods that use artificial intelligence models based on collected data to analyze user preferences and behavioral patterns.

[1295] The "proposal information generation method" is a method for generating optimal shopping information and coupon information for users based on analysis results.

[1296] A "proposal information notification means" is a means of notifying the user's terminal of the generated proposal information.

[1297] "A means of providing shopping suggestions in real time" refers to a method of immediately providing appropriate shopping suggestions to users when they approach a physical store.

[1298] "Means of providing detailed information and maps" refers to means of providing users with links or maps to check more detailed information and store locations based on the suggested shopping information.

[1299] This invention relates to a system that utilizes a user's purchase history, location information, real-time information from social media, etc., and uses a generated AI model to provide personalized shopping suggestions. The system includes means for user authentication, means for linking external accounts, means for acquiring purchase history, means for acquiring location information, means for collecting social media information, means for analysis using an artificial intelligence model, means for generating suggestion information, means for notifying suggestion information, means for providing shopping suggestions in real time, and means for providing detailed information and maps.

[1300] System Configuration

[1301] The system primarily consists of a server and user terminals. The server is responsible for data analysis and generating suggestion information, while the user terminals are responsible for collecting information and displaying the suggested information.

[1302] Specific examples of hardware and software

[1303] Servers: High-performance servers are used for data processing. For example, cloud servers such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) can be used.

[1304] User devices: Smartphones are primarily used. This includes devices with mobile operating systems such as Android and iOS installed.

[1305] Generative AI models: Models using AI frameworks such as PyTorch and TensorFlow are used.

[1306] Feature details

[1307] 1. User Authentication Methods

[1308] When a user logs into the app for the first time, their authentication information is verified and permission to access the system is granted. At this time, the user can link external accounts (for example, electronic payment services or social media accounts).

[1309] 2. External account linking methods

[1310] After successful authentication, the system retrieves the user's purchase history from an external service and stores it in a database. This allows the system to understand the user's spending habits.

[1311] 3. Means of acquiring purchase history

[1312] Purchase history will be collected from electronic payment services and online shops to serve as basic data for analyzing user consumption behavior.

[1313] 4. Location information acquisition means

[1314] Using GPS technology, the system obtains the user's current location in real time. This allows it to identify which physical store the user is approaching.

[1315] 5. Means of gathering information from social media

[1316] It can collect trending and campaign information from social media and analyze user interests in real time.

[1317] 6. Analysis methods using artificial intelligence models

[1318] It integrates purchase history, location information, and social media data to analyze user preferences and behavioral patterns. By using generative AI models such as PyTorch, it generates highly accurate recommendation information.

[1319] 7. Proposal information generation means

[1320] Based on the analysis results, the system generates optimal shopping and coupon information for users. This also takes into account marketing information provided by companies.

[1321] 8. Proposal information notification means

[1322] The generated suggestion information is sent as a push notification to the user's smartphone. The notification includes information on special offers and coupons.

[1323] 9. Means of providing shopping suggestions in real time

[1324] When a user approaches a physical store, the system provides appropriate shopping suggestions on the spot. For example, it might send a notification like, "20% off sale at your nearest [brand name]!"

[1325] 10. Means of providing detailed information and maps

[1326] Based on the suggested information, provide users with links to access more detailed product information and store maps.

[1327] Specific example

[1328] For example, when a user arrives at a shopping mall, the system works as follows: First, a location information acquisition system identifies the user's location, and an AI model analyzes products and stores that the user might be interested in based on their purchase history and social media information. Then, a notification system sends a push notification saying, "There's a 30% off sale at your nearest electronics store!", along with more detailed information and a map.

[1329] Example of a prompt

[1330] Examples of prompt messages that provide suggestions based on the user's purchase history, current location, and social media trends are as follows:

[1331] "The user's purchase history includes electronics products, and their current location is within a shopping mall. According to social media trends, there is a sale on electronics products. Based on this information, we generate optimal shopping suggestions."

[1332] This allows users to enjoy shopping more efficiently, and enables companies to improve the accuracy of their targeted marketing.

[1333] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1334] Step 1: User authentication and external account linking

[1335] Input: User authentication information (User ID, password), external account information (electronic payment service or social media account)

[1336] Processing: The server authenticates the user based on the entered authentication information. After successful authentication, it links with an external account and obtains an authentication token from an external service (electronic payment service or social networking service).

[1337] Output: Authentication token and user profile information

[1338] Specific operation: When a user logs into the app, the server verifies the authentication information, and if successful, displays a pop-up prompting the user to link with an electronic payment service or social media.

[1339] Step 2: Obtain purchase history

[1340] Input: Authentication token, external account information

[1341] Processing: The server retrieves purchase history from electronic payment services and online shops using external account information. The retrieved data is then added to the user's profile.

[1342] Output: Purchase history data

[1343] Specific operation: Upon successful authentication, the server uses the authentication token to retrieve purchase history data from an external service's API and saves it to the database.

[1344] Step 3: Obtaining location information

[1345] Input: GPS data from the user's device

[1346] Process: The device acquires GPS data and sends its current location information to the server. The server uses this location information to determine the place the user is visiting.

[1347] Output: Current location information

[1348] Specific operation: The device obtains the user's current location via GPS and sends it to the server in real time. The server uses this data to determine which physical store the user is in.

[1349] Step 4: Gathering SNS information

[1350] Input: Authentication token, social media account information

[1351] Processing: The server uses social media account information to collect current trend and campaign information. This allows it to obtain real-time information related to the user's interests.

[1352] Output: SNS trend information, campaign information

[1353] Specific operation: The server periodically retrieves trending and campaign information using SNS APIs and stores it in a database.

[1354] Step 5: Data Integration and Analysis

[1355] Input: Purchase history data, current location information, social media trend information

[1356] Processing: The server integrates this data and uses a generative AI model to analyze user preferences and behavioral patterns. This generates foundational data for providing users with optimal shopping recommendations.

[1357] Output: Analysis results (user preference data, behavioral pattern data)

[1358] Specific operation: The server collects data, inputs that data into a generating AI model for analysis, and uses frameworks such as PyTorch to obtain highly accurate results.

[1359] Step 6: Generating Proposal Information

[1360] Input: Analysis results (user preference data, behavioral pattern data)

[1361] Processing: The server generates optimal shopping recommendations for the user based on the analysis results. These recommendations also incorporate marketing information provided by companies.

[1362] Output: Proposal Information

[1363] Specific operation: The server integrates analysis results with marketing information from companies and generates shopping suggestions tailored to the user.

[1364] Step 7: Notification of proposed information

[1365] Input: Proposal Information

[1366] Processing: The server pushes the generated suggestion information to the user's device. The notification may also include information on special offers and coupons.

[1367] Output: Push notification to user's device

[1368] Specific operation: The server sends the suggestion information to the user's smartphone, and a notification is displayed.

[1369] Step 8: Provide detailed information and maps.

[1370] Input: User action upon receiving the push notification (e.g., clicking a link)

[1371] Processing: The device displays more detailed product information and store locations to users who click the link in the push notification.

[1372] Output: Detailed information screen, map display

[1373] Specific operation: When the user clicks the notification, the device retrieves detailed information and map data from the server and displays it.

[1374] 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.

[1375] Modes for carrying out the invention

[1376] System Overview

[1377] This invention relates to a system that utilizes a user's purchase history, current location information, real-time information from social media, and an emotion engine that recognizes the user's emotions, and uses a generative AI model to provide personalized shopping suggestions. Specifically, the system consists of a user authentication means, an external account linking means, a purchase history acquisition means, a location information acquisition means, a social media information collection means, an analysis means using an artificial intelligence model, a suggestion information generation means, an emotion engine, and a suggestion information notification means.

[1378] Program processing

[1379] The system program performs the following operations:

[1380] 1. User authentication and data integration

[1381] When a user logs into the app for the first time, the user authentication method verifies the user's credentials and grants access to the system. At this time, the user can link external accounts (e.g., electronic payment services or social media accounts).

[1382] After successful user authentication, the server retrieves the user's purchase history from an external service. The retrieved data is stored in a database to analyze the user's consumption patterns.

[1383] 2. Customization settings and information gathering

[1384] Users can customize settings based on their interests in the app's settings screen. For example, they can specify that they are interested in a particular category (fashion, groceries, electronics, etc.).

[1385] The device acquires the user's location information in real time and sends it to the server. Additionally, the SNS information gathering mechanism collects real-time information (e.g., trends, campaign information) from social media.

[1386] 3. Emotion Recognition and Data Integration

[1387] The emotion engine installed in the device recognizes the user's emotions in real time and sends that data to the server. The emotion engine identifies emotions by analyzing the user's facial expressions, voice tone, etc.

[1388] The server integrates and analyzes emotional data, purchase history, customization settings, current location information, and social media information. Using an artificial intelligence model, it analyzes user preferences and behavioral patterns, and generates optimal suggestion information that also takes emotional states into account.

[1389] 4. Proposal information generation and notification

[1390] The server also collects recommendations provided by companies and filters them based on the user's preferences and emotions. This ensures that companies' marketing information is also presented to users with high accuracy.

[1391] The server notifies the user's device of the generated shopping recommendations. These notifications include coupon information and special offer details.

[1392] The device displays recommended information to the user as a notification. If the user shows interest in the suggestion, it provides a link to access detailed store and product information.

[1393] Specific example

[1394] Example 1: User's first use

[1395] 1. The user launches the app for the first time, enters their ID and password on the authentication screen, and logs in. Afterward, they link their electronic payment service and social media account.

[1396] 2. The server retrieves the user's past purchase history from external services and stores it in a database. It analyzes consumption trends and builds a user profile.

[1397] Example 2: Suggestions based on emotions and real-time information

[1398] 1. The device detects the user's location in a shopping mall using GPS. Simultaneously, the emotion engine recognizes the user's state of excitement from their facial expressions.

[1399] 2. The server checks the purchase history to confirm that the user has previously purchased items from a specific brand within that mall.

[1400] 3. The server retrieves sales information for the brand from social media and uses a generative AI model and sentiment data to generate optimal suggestions for the user.

[1401] 4. The device sends a push notification to the user saying, "20% off sale at your nearest [brand name]!" and provides a link to more information. When the user clicks the notification, the store's map information and sale details are displayed.

[1402] In this way, the system combines users' purchase history, current location information, and real-time emotional information to provide optimal shopping suggestions for each individual user. This allows users to have a more personalized and efficient shopping experience. Businesses can also improve the accuracy of targeted marketing that takes into account users' emotional states, enabling more effective customer acquisition.

[1403] The following describes the processing flow.

[1404] Step 1:

[1405] The user launches the app for the first time and authenticates with their Yahoo! ID. The user enters their ID and password on the login screen and clicks the "Login" button.

[1406] Step 2:

[1407] The server authenticates the user's ID and password, and if authentication is successful, creates a user profile in the database. The server uses an authentication API to verify the user's authentication information.

[1408] Step 3:

[1409] Users link their electronic payment services and social media accounts within the app. Users select "Electronic Payment Linkage" or "Social Media Linkage" from the settings menu.

[1410] Step 4:

[1411] The server obtains purchase history data from the electronic payment service with the user's consent. The server uses the electronic payment service's API to retrieve the user's past transaction data and stores it in the database.

[1412] Step 5:

[1413] Users can customize settings based on their interests in the app's settings screen. They can select categories such as fashion, groceries, and electronics, and configure notification frequency and preferred store lists.

[1414] Step 6:

[1415] The device periodically acquires the user's current location information and sends it to the server. The device uses a GPS sensor to collect location information and sends it to the server at regular intervals.

[1416] Step 7:

[1417] The emotion engine installed in the device recognizes the user's emotions in real time and sends that data to the server. The emotion engine identifies emotions by analyzing the user's facial expressions, voice tone, etc.

[1418] Step 8:

[1419] The server uses social media information gathering methods to collect real-time information related to users from social media (e.g., trends, campaign information).

[1420] Step 9:

[1421] The server integrates and analyzes the user's purchase history, customization settings, current location information, sentiment data, and social media information. Using artificial intelligence models, it analyzes the user's preferences and behavioral patterns to generate optimal recommendation information.

[1422] Step 10:

[1423] The server collects recommendation information provided by companies and filters it based on user preferences and sentiment data. This ensures that companies' marketing information is also suggested to users with high accuracy.

[1424] Step 11:

[1425] The server notifies the user's device of the generated shopping recommendations. These notifications include coupon information and special offer details.

[1426] Step 12:

[1427] The device displays recommended information to the user as a notification. The notification includes a link, which the user can click to view more details. The user taps the notification to access the details page.

[1428] Step 13:

[1429] Users check notifications and click on information that interests them. Clicking displays detailed store and product information, improving the user's shopping experience.

[1430] (Example 2)

[1431] 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."

[1432] In today's shopping landscape, providing personalized purchase suggestions to users is crucial for maintaining high user satisfaction. However, traditional systems typically rely solely on purchase history and location data for suggestions, failing to consider users' momentary emotions or real-time social media information. As a result, providing optimal suggestions for users has been difficult, and the marketing effectiveness for companies has been limited.

[1433] 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.

[1434] In this invention, the server includes user authentication means, external account linking means, purchase history acquisition means, location information acquisition means, SNS information collection means, emotion recognition means, analysis means using an artificial intelligence model, suggestion information generation means, and suggestion information notification means. This enables comprehensive analysis of the user's purchase history, current location information, real-time emotion information, and SNS information to provide optimal shopping suggestions to individual users.

[1435] "User authentication means" refers to the means used to verify the identity of a user when they access a system.

[1436] "External account linking methods" refer to methods for linking a system with external services (e.g., electronic payment services or social networking services).

[1437] A "purchase history acquisition method" is a means of acquiring a user's past purchase history and importing it into the system.

[1438] "Location information acquisition means" refers to methods for acquiring the user's current location information using GPS or similar technologies.

[1439] "SNS information gathering methods" refer to methods for collecting information from social media in real time.

[1440] "Means of recognizing emotions" refers to methods for identifying emotions from a user's facial expressions, voice, etc.

[1441] "Analysis methods using artificial intelligence models" refer to methods for analyzing data acquired using artificial intelligence models to analyze user preferences and behavioral patterns.

[1442] The "proposal information generation means" is a means of generating optimal shopping suggestions for the user based on the analysis results.

[1443] A "proposal information notification means" is a means of notifying the user's terminal of the generated proposal information.

[1444] Modes for carrying out the invention

[1445] System Program Overview

[1446] This invention relates to a system that utilizes a user's purchase history, current location information, real-time information from social media, and an emotion engine that recognizes the user's emotions, and uses a generative AI model to provide personalized shopping suggestions. This system includes user authentication means, external account linking means, purchase history acquisition means, location information acquisition means, social media information collection means, emotion recognition means, analysis means using an artificial intelligence model, suggestion information generation means, and suggestion information notification means.

[1447] Hardware and software to use

[1448] Server: Performs database management, API integration, and data analysis using artificial intelligence models.

[1449] Device: Smartphones, tablets, etc. It receives user input and activates the emotion engine.

[1450] Emotion engine: Software that analyzes the user's facial expressions and voice tone to identify their emotions.

[1451] GPS function: Obtains the user's location information.

[1452] SNS information gathering tools: Scraping tools and APIs for collecting real-time information from social media.

[1453] Explanation of the program's processing

[1454] 1. User Authentication

[1455] The user logs into the app for the first time, and their identity is verified through an authentication method. The authentication information is securely transmitted to the server.

[1456] The server verifies the received authentication information and initiates external account linking upon successful authentication.

[1457] 2. External account integration and data acquisition

[1458] The user links their account with an electronic payment service or social media account. Authentication information for the linking service is entered.

[1459] The server uses APIs from external services to retrieve purchase history and social media activity data, and stores it in a database.

[1460] 3. Customization settings

[1461] Users can customize their settings within the app based on their interests. For example, they can select specific categories or brands.

[1462] The device sends the configured information to the server, which then stores it in the database.

[1463] 4. Obtaining location information

[1464] The device periodically obtains the user's current location using its GPS function and sends it to the server.

[1465] The server stores location information in a database and integrates it with related data.

[1466] 5. Obtaining SNS information

[1467] The device uses a social networking information gathering tool to acquire real-time information related to the specified keywords.

[1468] The server analyzes the collected information and stores it in a database.

[1469] 6. Emotion recognition

[1470] The device uses its camera and microphone to identify emotions from the user's facial expressions and voice, and acquires emotion data.

[1471] The device sends emotional data to the server.

[1472] 7. Data Integration and Analysis

[1473] The server integrates emotional data, purchase history, customization settings, current location information, and social media information, and analyzes the data using an artificial intelligence model.

[1474] Artificial intelligence models analyze user preferences and behavioral patterns.

[1475] 8. Generation of proposed information

[1476] The server collects marketing information provided by companies and filters it based on the user's preferences and emotions.

[1477] We use an artificial intelligence model to generate optimal shopping suggestions.

[1478] 9. Notification of proposed information

[1479] The server notifies the terminal of the shopping suggestions it has generated. The notification includes coupon information and special offer information.

[1480] The device displays a notification to the user and provides a link to more information.

[1481] Specific example

[1482] 1. The user logs in for the first time and links their electronic payment service with their social media account.

[1483] 2. The server retrieves purchase history from an external service and saves it to the database.

[1484] 3. The GPS detects that the user is in a shopping mall, and the emotion engine recognizes the user's state of excitement.

[1485] 4. The server generates optimal suggestions using purchase history and sales information from social media.

[1486] 5. The device sends a push notification saying, "20% off sale at your nearest [brand name] store."

[1487] Examples of prompts to input into a generative AI model

[1488] "This user has a history of frequently purchasing fashion items. They are currently in a shopping mall. Their facial expression indicates excitement. Please generate effective shopping suggestions for this user."

[1489] "This user is interested in electronics and is currently located in central Tokyo. They have sales information for electronics brands on social media. Please create the best possible suggestions for this user."

[1490] In this way, the system continuously collects data from multiple sources and provides personalized shopping suggestions to each user, thereby improving the user experience and maximizing the marketing effectiveness of companies.

[1491] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1492] Step 1:

[1493] User Authentication

[1494] Operation:

[1495] The user launches the app for the first time and enters their ID and password on the authentication screen.

[1496] The server compares the received authentication information with the user information in the database, and if authentication is successful, it starts a session.

[1497] Input: User ID, Password

[1498] Output: Session started based on authentication success / failure result.

[1499] Specific processing:

[1500] The server receives the authentication information and compares it with the information in the database. If authentication is successful, it generates session information and grants the user access.

[1501] Step 2:

[1502] External account integration and data retrieval

[1503] Operation:

[1504] Users enter authentication information for linking their electronic payment service or social media account within the app.

[1505] The server sends API requests to linked external services to retrieve user purchase history and social media activity data. This data is stored in a database.

[1506] Input: External account credentials

[1507] Output: Purchase history data, social media activity data

[1508] Specific processing:

[1509] The server calls an external API to retrieve the user's purchase history and social media data. The retrieved data is stored in the database as the user's profile.

[1510] Step 3:

[1511] Customization settings

[1512] Operation:

[1513] Users can customize settings based on their interests in the app's settings screen. For example, they can select specific categories or brands.

[1514] The terminal sends the entered configuration information to the server and stores it in the database.

[1515] Input: User customization settings information

[1516] Output: Configuration information stored in the database

[1517] Specific processing:

[1518] The user sends their selected customization settings from the terminal to the server, which stores this information in a database for use in subsequent analysis processes.

[1519] Step 4:

[1520] Location information acquisition

[1521] Operation:

[1522] The device periodically obtains the user's current location using its GPS function and sends it to the server.

[1523] The server stores the received location information in a database.

[1524] Input: Location information obtained from GPS

[1525] Output: Location information stored in the database

[1526] Specific processing:

[1527] The device periodically uses GPS to obtain the user's current location and sends it to the server. The server stores the received location information in a database and updates the location information in real time.

[1528] Step 5:

[1529] Acquisition of SNS information

[1530] Operation:

[1531] The device retrieves real-time information from social media information gathering tools based on specified keywords.

[1532] The server stores the collected SNS information in a database and integrates it into the user's profile.

[1533] Input: Collected SNS information

[1534] Output: SNS information stored in the database

[1535] Specific processing:

[1536] The device uses an SNS collection tool to acquire information related to specified keywords and sends it to the server. The server stores the collected SNS information in a database.

[1537] Step 6:

[1538] emotion recognition

[1539] Operation:

[1540] The device uses its camera and microphone to analyze the user's facial expressions and voice in real time and identify their emotions.

[1541] The device sends the identified emotion data to the server.

[1542] Input: Facial expression, voice tone

[1543] Output: Identified sentiment data

[1544] Specific processing:

[1545] The emotion engine uses information acquired from the device's camera and microphone to recognize the user's emotions and sends the results to the server. The server stores the emotion data in a database.

[1546] Step 7:

[1547] Data Integration and Analysis

[1548] Operation:

[1549] The server integrates and analyzes emotional data, purchase history, customization settings, current location information, and social media information.

[1550] Using artificial intelligence models, we analyze user preferences and behavioral patterns to generate optimal shopping recommendations.

[1551] Input: Sentimental data, purchase history, customization settings, current location information, social media information

[1552] Output: Analysis results, proposed information

[1553] Specific processing:

[1554] The server uses integrated data to perform analysis using an artificial intelligence model, analyzing user preferences and behavioral patterns. Based on these results, it generates optimal shopping recommendations.

[1555] Step 8:

[1556] Generation of proposed information

[1557] Operation:

[1558] The server collects marketing information provided by companies (e.g., coupon information, special offer information) and filters it based on the user's preferences and emotions.

[1559] We use a generative AI model to generate optimal shopping suggestions for the user.

[1560] Input: Marketing information and analysis results from companies.

[1561] Output: Optimal shopping suggestions

[1562] Specific processing:

[1563] The system filters information provided by companies and uses a generative AI model to create optimal suggestions that take into account the user's preferences and emotional state.

[1564] Step 9:

[1565] Notification of proposed information

[1566] Operation:

[1567] The server notifies the user's device of the shopping suggestions it has generated. These notifications include coupon information and special offer information.

[1568] The device will display this notification to the user as a push notification, providing a link to more information.

[1569] Input: Generated shopping suggestions

[1570] Output: Notification to user terminal

[1571] Specific processing:

[1572] The server sends the generated suggestion information to the user's device, which then displays it to the user as a push notification. The notification includes a link to more information, which, when tapped by the user, displays information about the relevant store or product.

[1573] In this way, each step works together to create a system that can efficiently provide personalized suggestions to users.

[1574] (Application Example 2)

[1575] 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."

[1576] Traditional online shopping systems offered recommendations based on user preferences, but they did not provide personalized suggestions that took into account real-time emotional states or location information. This made it difficult to provide a shopping experience that aligned with users' actual interests and desires, resulting in many users spending a considerable amount of time finding suitable products. Furthermore, companies faced the challenge of being unable to conduct effective marketing based on users' real-time emotions and behavior.

[1577] 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.

[1578] In this invention, the server includes user authentication means, external account linking means, purchase history acquisition means, location information acquisition means, SNS information collection means, emotion recognition engine, analysis means using an artificial intelligence model, suggestion information generation means, and suggestion information notification means. This enables integrated analysis of the user's purchase history, current location information, SNS information, and emotional state, and allows for optimal shopping suggestions for each individual user using a generated AI model.

[1579] "User authentication means" refers to a method of verifying a user's authentication information and granting them access to the system.

[1580] "External account linking methods" refer to methods for linking with external services such as electronic payment services and social media accounts.

[1581] "Purchase history acquisition method" refers to a method for acquiring a user's past purchase history and storing it in the system.

[1582] "Location information acquisition means" refers to means of collecting information about the user's current location.

[1583] "SNS information gathering methods" refer to methods for collecting data such as trend information and campaign information from social networking services.

[1584] An "emotion engine" is a method of identifying emotions by analyzing the user's facial expressions and voice tone.

[1585] "Analysis methods using artificial intelligence models" refer to methods that use artificial intelligence to analyze user preferences and behavioral patterns.

[1586] The "proposal information generation means" is a means of generating shopping suggestions that are optimal for each individual user based on user data.

[1587] A "proposal information notification means" is a means of notifying the user's terminal of the generated proposal information.

[1588] "Custom settings" refers to the ability for users to adjust application settings based on their own interests.

[1589] "Company-provided information" refers to recommended information and campaign information offered by companies.

[1590] System Overview

[1591] This invention is a system that collects user purchase history, current location information, real-time information from social media, and sentiment information, and analyzes and integrates them to provide optimal shopping suggestions for individual users. Specifically, it provides a series of systems that generate and notify suggestion information using an artificial intelligence model for analyzing various types of information and an sentiment engine that recognizes user sentiment in real time. This system includes the following main means:

[1592] 1. User authentication method: Verify the user's authentication information and grant access to the system.

[1593] 2. External account linking methods: Methods for linking with electronic payment services and social media accounts.

[1594] 3. Purchase history acquisition method: Acquire the user's past purchase history and save it in the system.

[1595] 4. Means of acquiring location information: Collect the user's current location information.

[1596] 5. Social media information gathering methods: Gather trend information and campaign information from social networking services.

[1597] 6. Emotion Engine: Analyzes the user's facial expressions and voice tone to identify emotions.

[1598] 7. Analysis methods using artificial intelligence models: Use artificial intelligence to analyze user preferences and behavioral patterns.

[1599] 8. Suggestion information generation means: Based on user data, it generates shopping suggestions that are optimal for each individual user.

[1600] 9. Proposal Information Notification Means: Generated proposal information is notified to the user's terminal.

[1601] Program processing

[1602] The server collects and analyzes various data, generates personalized recommendations for each user, and notifies the user's device. This allows users to have a more efficient and personalized shopping experience. Specifically, the following data processing or calculations are performed:

[1603] 1. Use of hardware and software:

[1604] Smartphones: Used for user authentication, location information acquisition, emotion recognition, etc.

[1605] Emotion Engine: A library for recognizing user emotions in real time.

[1606] Artificial intelligence model: Data analysis and proposal information are generated using the GenerativeAIModel library.

[1607] 2. Data collection and analysis:

[1608] The server collects purchase history from external accounts and stores it in a database.

[1609] Real-time location information is collected using a GPS module, and social media information is obtained via an API.

[1610] User sentiment data is collected by the sentiment engine and sent to the server.

[1611] 3. Proposal generation using artificial intelligence models:

[1612] The server integrates all collected data and generates optimal shopping suggestions using a generative AI model. This generative AI model operates based on the following prompts:

[1613] "User ID: 1234, Location: Tokyo, Emotion: Excited, Purchase History: Fashion, Social Media Trend: Autumn Sale. Please generate the best suggestions for this user."

[1614] Specific example

[1615] 1. First-time use case:

[1616] The user launches the app for the first time, enters their ID and password on the authentication screen to log in, and then links their electronic payment service and social media account.

[1617] The server retrieves the user's past purchase history from external services and stores it in a database. It then analyzes consumption trends and builds user profiles.

[1618] 2. Case of real-time proposals:

[1619] The system uses GPS to detect that the user is in a shopping mall. Simultaneously, an emotion engine recognizes the user's level of excitement from their facial expressions.

[1620] The server checks the purchase history to confirm that the user has previously purchased items from a specific brand within that mall.

[1621] The server retrieves sales information for a brand from social media, and uses a generative AI model and sentiment data to generate optimal suggestions for the user.

[1622] A push notification is sent to the user's device stating, "20% off sale at your nearest [brand name]!" and providing a link to more information. When the user clicks the notification, store map information and sale details are displayed.

[1623] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1624] Step 1:

[1625] User authentication and external integration

[1626] Input: User authentication information (ID, password), external account information (electronic payment account, social media account)

[1627] Specific operation: When a user logs into the smartphone app for the first time, they enter authentication information and authenticate using the authentication method. Additionally, users can link their accounts with electronic payment services and social media accounts using external account linking methods.

[1628] Output: Authentication success and the status of the external account linkage are sent to the server.

[1629] Step 2:

[1630] Retrieving purchase history

[1631] Input: User ID

[1632] Specific operation: The server collects the user's past purchase history using a purchase history acquisition method from an external service. The acquired purchase history is stored in a database and used to analyze the user's consumption trends.

[1633] Output: Purchase history data is saved to the server's database.

[1634] Step 3:

[1635] Retrieve custom settings

[1636] Input: User's interests and settings information

[1637] Specific operation: The user selects a category of interest (e.g., fashion, groceries, electronics, etc.) from the app's settings screen.

[1638] Output: Configuration information is sent to the server.

[1639] Step 4:

[1640] Real-time information gathering

[1641] Input: Location information, social media information

[1642] Specific operation: The device's GPS module acquires the user's location information in real time and sends it to the server. In addition, the SNS information collection method collects real-time trend information and campaign information from SNS.

[1643] Output: Location information and SNS information are sent to the server.

[1644] Step 5:

[1645] emotion recognition

[1646] Input: User's facial expression, voice tone

[1647] Specific operation: The emotion engine uses the camera and microphone built into the device to recognize the user's emotions in real time. The acquired emotion data is sent to the server.

[1648] Output: Emotional data is sent to the server.

[1649] Step 6:

[1650] Data integration and analysis

[1651] Input: Purchase history data, settings information, location information, social media information, sentiment data

[1652] Specific operation: The server integrates all collected data and analyzes it using an artificial intelligence model. The generative AI model generates optimal suggestion information based on the user's preferences, behavioral patterns, and emotional state. Instructions are given to the AI ​​model using prompts. Example of a prompt: "User ID: 1234, Location: Tokyo, Emotion: Excited, Purchase History: Fashion, SNS Trend: Autumn Sale, Please generate optimal suggestions for the user."

[1653] Output: Generated suggestion information is obtained.

[1654] Step 7:

[1655] Notification of proposed information

[1656] Input: Generated suggestion information

[1657] Specific operation: The server sends generated shopping suggestion information to the user's terminal via push notifications through the suggestion information notification system. The notification also includes a link to detailed information.

[1658] Output: The suggested information is displayed as a notification on the user's device.

[1659] Step 8:

[1660] Providing detailed information

[1661] Input: User action (notification click)

[1662] Specific operation: When the user clicks the notification, the app displays detailed information (store map, sale details, etc.).

[1663] Output: The detailed information screen is displayed on the user's device.

[1664] 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.

[1665] 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.

[1666] 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.

[1667] [Fourth Embodiment]

[1668] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1669] 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.

[1670] 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).

[1671] 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.

[1672] 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.

[1673] 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).

[1674] 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.

[1675] 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.

[1676] 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.

[1677] 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.

[1678] 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.

[1679] 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.

[1680] 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".

[1681] Modes for carrying out the invention

[1682] System Overview

[1683] This invention relates to a system that utilizes a user's purchase history, current location information, real-time information from social media, etc., and uses a generated AI model to provide personalized shopping suggestions. Specifically, the system consists of a user authentication means, an external account linking means, a purchase history acquisition means, a location information acquisition means, a social media information collection means, an analysis means using an artificial intelligence model, a suggestion information generation means, and a suggestion information notification means.

[1684] Program processing

[1685] The system program performs the following operations:

[1686] 1. User authentication and data integration

[1687] When a user logs into the app for the first time, the user authentication method verifies the user's credentials and grants access to the system. At this time, the user can link external accounts (e.g., electronic payment services or social media accounts).

[1688] After successful user authentication, the server retrieves the user's purchase history from an external service. The retrieved data is stored in a database to analyze the user's consumption patterns.

[1689] 2. Customization settings and information gathering

[1690] Users can customize settings based on their interests in the app's settings screen. For example, they can specify that they are interested in a particular category (fashion, groceries, electronics, etc.).

[1691] The device acquires the user's location information in real time and sends it to the server. Additionally, the SNS information gathering mechanism collects real-time information (e.g., trends, campaign information) from social media.

[1692] 3. Data Analysis and Proposal Generation

[1693] The server integrates and analyzes the user's purchase history, customization settings, current location information, and real-time information from social media. Using an artificial intelligence model, it analyzes the user's preferences and behavioral patterns to generate optimal shopping recommendations.

[1694] The server also collects recommendations from companies and selects those that match the user's preferences. This ensures that marketing information provided by companies is also suggested to users with high accuracy.

[1695] 4. Information Distribution and User Interaction

[1696] The server notifies the user's device of the generated shopping recommendations. These notifications include coupon information and special offer details.

[1697] The device displays recommended information to the user as a notification. If the user shows interest in the suggestion, it provides a link to access detailed store and product information.

[1698] Specific example

[1699] Example 1: User's first use

[1700] 1. The user launches the app for the first time, enters their ID and password on the authentication screen, and logs in. Afterward, they link their electronic payment service and social media account.

[1701] 2. The server retrieves the user's past purchase history from external services and stores it in a database. It analyzes consumption trends and builds a user profile.

[1702] Example 2: Real-time information suggestion

[1703] 1. The device detects that the user is in a shopping mall using GPS.

[1704] 2. The server checks the purchase history to confirm that the user has previously purchased items from a specific brand within that mall.

[1705] 3. The server retrieves sales information for the brand from social media and uses a generative AI model to generate optimal suggestions for the user.

[1706] 4. The device sends a push notification to the user saying, "20% off sale at your nearest [brand name]!" and provides a link to more information. When the user clicks the notification, the store's map information and sale details are displayed.

[1707] In this way, the system combines users' purchase history with real-time information to provide optimal shopping suggestions to individual users. This allows users to enjoy shopping efficiently and conveniently. Companies can also improve the accuracy of their targeted marketing, enabling them to attract customers effectively.

[1708] The following describes the processing flow.

[1709] Step 1:

[1710] The user launches the app for the first time and authenticates with their Yahoo! ID. The user enters their ID and password on the login screen and clicks the "Login" button.

[1711] Step 2:

[1712] The server authenticates the user's ID and password, and if authentication is successful, creates a user profile in the database. The server uses an authentication API to verify the user's authentication information.

[1713] Step 3:

[1714] Users perform operations within the app to link their electronic payment services or social media accounts. Users select "Electronic Payment Linkage" or "Social Media Linkage" from the settings menu.

[1715] Step 4:

[1716] The server obtains purchase history data from the electronic payment service with the user's consent. The server uses the electronic payment service's API to retrieve the user's past transaction data and stores it in the database.

[1717] Step 5:

[1718] Users can customize settings based on their interests in the app's settings screen. They can select categories such as fashion, groceries, and electronics, and configure notification frequency and preferred store lists.

[1719] Step 6:

[1720] The device periodically acquires the user's current location information and sends it to the server. The device uses a GPS sensor to collect location information and sends it to the server at regular intervals.

[1721] Step 7:

[1722] The server uses social media information gathering methods to collect real-time information related to users from social media (e.g., trends, campaign information).

[1723] Step 8:

[1724] The server integrates and analyzes the user's purchase history, customization settings, current location information, and social media information. Using artificial intelligence models, it analyzes the user's preferences and behavioral patterns to generate optimal recommendation information.

[1725] Step 9:

[1726] The server collects recommendation information provided by companies and filters it based on user preferences. This ensures that companies' marketing information is also presented to users with high accuracy.

[1727] Step 10:

[1728] The server notifies the user's device of the generated shopping recommendations. These notifications include coupon information and special offer details.

[1729] Step 11:

[1730] The device displays recommended information to the user as a notification. The notification includes a link, which the user can click to view more details. The user taps the notification to access the details page.

[1731] Step 12:

[1732] Users check notifications and click on information that interests them. Clicking displays detailed store and product information, improving the user's shopping experience.

[1733] (Example 1)

[1734] 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".

[1735] Conventional shopping suggestion systems are limited to suggestions based on the user's purchase history and lack the ability to provide dynamic suggestions that utilize real-time location information and the latest trend information obtained from social media. Furthermore, they struggle to provide highly accurate suggestions that integrate user preferences and marketing information from companies. In addition, conventional systems are unable to properly analyze and reflect users' specific interests and behavioral patterns, making it difficult to increase user satisfaction.

[1736] 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.

[1737] In this invention, the server includes user authentication means, external account linking means, purchase history acquisition means, location information acquisition means, SNS information collection means, analysis means using a generation AI model, suggestion information generation means, and suggestion information notification means. This enables highly accurate shopping suggestions tailored to the user's preferences by utilizing real-time location information and the latest trend information.

[1738] "User authentication means" refers to the means used to verify and authenticate a user's identity when they access a system.

[1739] "External account linking methods" refer to methods for linking external service accounts, such as electronic payment services and social media accounts, with the system.

[1740] A "purchase history acquisition method" is a means of acquiring a user's past purchase history from an external service and making it available within the system.

[1741] "Location information acquisition means" refers to a means for acquiring the user's current location in real time and transmitting it to the system.

[1742] "SNS information gathering methods" refer to methods for collecting real-time trend information and campaign information from social media.

[1743] "Analysis methods using generative AI models" refer to methods that use generative AI models to analyze users' purchase history, location information, social media information, etc., in order to analyze users' preferences and behavioral patterns.

[1744] The "proposal information generation means" is a means for generating optimal shopping suggestion information for the user based on the analysis results.

[1745] A "suggestion information notification means" is a means for notifying the user's terminal of the generated shopping suggestion information.

[1746] "Customization settings" are items that users configure based on their interests and preferences, and they serve as the basic data for the system to generate personalized suggestions.

[1747] "Company-provided information" refers to information collected for marketing purposes, such as sales information and recommended product information provided by companies.

[1748] This invention relates to a system that utilizes a user's purchase history, current location information, real-time information from social media, etc., and uses a generated AI model to provide personalized shopping suggestions. The specific system configuration and operation are described below.

[1749] System Configuration

[1750] This system includes the following means:

[1751] User authentication method: A function that verifies and authenticates a user's identity when they access a system.

[1752] External account integration method: A function that allows integration of external service accounts, such as electronic payment services and social media accounts, with the system.

[1753] Purchase history acquisition method: A function that retrieves the user's past purchase history from an external service.

[1754] Location information acquisition method: A function that acquires the user's current location in real time.

[1755] SNS information gathering method: A function that collects real-time trend information and campaign information from social media.

[1756] Analysis method using generative AI models: A function that uses generative AI models to analyze users' purchase history, location information, social media information, etc., and analyzes users' preferences and behavioral patterns.

[1757] Suggestion information generation means: A function that generates optimal shopping suggestion information for the user based on the analysis results.

[1758] Suggestion information notification means: A function that notifies the user's device of the generated shopping suggestion information.

[1759] Operation Description

[1760] The main functions of the system are as follows:

[1761] User authentication and external account integration

[1762] The user launches the app and enters their ID and password on the login screen. The server uses this information to verify the user's identity, and if authentication is successful, grants access to the system. The user then provides more data to the system by linking external accounts (e.g., electronic payment services or social media accounts). At this point, the server receives the information from the linked external accounts and stores it in a database. This makes it possible to understand the user's spending trends.

[1763] Acquisition of purchase history and social media information

[1764] The server retrieves user purchase history using APIs from integrated external services. This data is stored in a database and used for later analysis. Similarly, the server retrieves real-time trend and campaign information using social media APIs. This information is also stored in the database.

[1765] Customization settings and location information acquisition

[1766] Users can customize their interests and preferences in the app's settings screen. For example, setting interests in specific categories (fashion, groceries, electronics, etc.) provides the system with the basis for generating personalized recommendations. The device also acquires the user's location information (GPS information) in real time and sends it to the server.

[1767] Data analysis and shopping suggestion generation

[1768] The server integrates purchase history, customization settings, location information, and real-time information from social media, and inputs it into a generative AI model. Based on this data, the generative AI model generates optimal shopping suggestions for the user. Examples of specific prompts include: "What products did user A recently purchase?", "What categories is user B interested in?", and "What sales information would you recommend for user C, who is currently located in Tokyo?".

[1769] Proposal information notification

[1770] The server notifies the user's device of the shopping suggestion information it has generated. The device displays this notification to the user and provides a link to more detailed information, thereby enhancing the user's convenience in taking action based on the suggestion.

[1771] In this way, the system comprehensively analyzes users' purchase history, location information, and social media information, and uses a generated AI model to provide individually optimized shopping suggestions in real time. This allows users to enjoy efficient and convenient shopping, while also enabling companies to achieve effective marketing.

[1772] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1773] Step 1:

[1774] The user launches the app and enters their ID and password on the login screen.

[1775] Input: User-entered ID and password

[1776] Specific action: The user enters their ID and password on the login screen and presses the "Login" button.

[1777] Output: An authentication request is sent to the server.

[1778] Step 2:

[1779] The server verifies the user's authentication credentials, and if authentication is successful, it grants access to the system.

[1780] Input: Authentication request, database user information

[1781] Specific operation: The server compares the ID and password with the database, and if they match, it returns a response indicating successful authentication.

[1782] Output: Authentication success message and user profile retrieved.

[1783] Step 3:

[1784] Users can add and link electronic payment services and social media accounts on the external account linking screen.

[1785] Input: External account information (e.g., social media account)

[1786] Specific action: The user enters their external account information and presses the "Link" button.

[1787] Output: A connection request is sent to the external service.

[1788] Step 4:

[1789] The server receives information from linked external accounts and adds it to the user profile.

[1790] Input: Account information from an external service

[1791] Specific operation: The server uses the SNS API to retrieve information about linked accounts and saves it to the database.

[1792] Output: Stored in the database as a complete profile.

[1793] Step 5:

[1794] The server retrieves the user's purchase history from an external service.

[1795] Input: Request to the electronic payment service API

[1796] Specific operation: The server uses the API of the electronic payment service to retrieve past purchase history data and store it in the database.

[1797] Output: Purchase history data is saved to the database.

[1798] Step 6:

[1799] The server uses SNS APIs to retrieve real-time trend information and campaign information.

[1800] Input: Request to SNS API

[1801] Specific operation: The server uses the SNS API to retrieve the latest information related to the specified keywords and hashtags.

[1802] Output: The latest information from social media is saved to the database.

[1803] Step 7:

[1804] Users can customize their interests and preferences in the app's settings screen.

[1805] Input: User's interest category information

[1806] Specific operation: The user opens the settings menu, selects categories of interest using checkboxes, and presses the save button.

[1807] Output: The user's interest settings are stored in the database.

[1808] Step 8:

[1809] The device acquires the user's location information (GPS information) in real time and sends it to the server.

[1810] Input: Location information from GPS sensor

[1811] Specific operation: The device periodically acquires location information and sends it to the server.

[1812] Output: Location information is sent to the server and stored in the database.

[1813] Step 9:

[1814] The server integrates purchase history, customization settings, location information, and real-time information from social media, and inputs it into the generating AI model.

[1815] Input: Purchase history, customization settings, location information, social media information

[1816] Specific operation: The server generates various data as a single dataset and inputs prompt statements into the AI ​​model.

[1817] Output: Input dataset for the generative AI model

[1818] Step 10:

[1819] The generative AI model generates optimal shopping suggestions for the user.

[1820] Input: Integrated dataset and prompt statement

[1821] Specific operation: The generating AI model analyzes historical data and trend information based on the prompt text and outputs shopping suggestions.

[1822] Output: Suggested shopping information

[1823] Step 11:

[1824] The server notifies the user's terminal of the generated suggestion information.

[1825] Input: Suggestion information from the generated AI model

[1826] Specific operation: The server sends a push notification to the user's device, sending a message such as "Sale happening at your local [store name]!"

[1827] Output: Push notification message

[1828] Step 12:

[1829] The device displays notifications received by the user and provides a link to more detailed information.

[1830] Input: Push notification from server

[1831] Specific operation: The device displays a notification as a pop-up message, and when the user clicks it, a detailed information page opens.

[1832] Output: Shopping suggestions displayed to the user

[1833] (Application Example 1)

[1834] 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".

[1835] Traditional shopping suggestion systems struggled to fully utilize users' purchase history and location information to provide personalized recommendations, thus failing to improve the in-store shopping experience. Furthermore, the lack of a real-time means for users to receive suggested information while in a physical store led to delays in providing timely information, hindering effective marketing.

[1836] 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.

[1837] In this invention, the server includes a user authentication means, an external account linking means, a purchase history acquisition means, a location information acquisition means, an SNS information collection means, an analysis means using an artificial intelligence model, a suggestion information generation means, a suggestion information notification means, a means for making shopping suggestions in real time when the user approaches a physical store, and a means for providing detailed information and maps based on the notified suggestion information. This makes it possible to provide users with immediate and optimal shopping suggestions by comprehensively utilizing the user's purchase history, location information, real-time information from SNS, etc.

[1838] "User authentication means" refers to the means of verifying that a user is a legitimate user when accessing a system.

[1839] "External account linking method" refers to a method by which a system links with a user's external service accounts (such as electronic payment services or social media accounts).

[1840] A "purchase history acquisition method" is a means of acquiring records of products and services that a user has purchased in the past.

[1841] "Location information acquisition means" refers to methods for acquiring location information using technologies such as GPS in order to determine the user's current location.

[1842] "SNS information gathering methods" refer to methods for collecting real-time information about users and trends from social media.

[1843] "Analysis methods using artificial intelligence models" refer to methods that use artificial intelligence models based on collected data to analyze user preferences and behavioral patterns.

[1844] The "proposal information generation method" is a method for generating optimal shopping information and coupon information for users based on analysis results.

[1845] A "proposal information notification means" is a means of notifying the user's terminal of the generated proposal information.

[1846] "A means of providing shopping suggestions in real time" refers to a method of immediately providing appropriate shopping suggestions to users when they approach a physical store.

[1847] "Means of providing detailed information and maps" refers to means of providing users with links or maps to check more detailed information and store locations based on the suggested shopping information.

[1848] This invention relates to a system that utilizes a user's purchase history, location information, real-time information from social media, etc., and uses a generated AI model to provide personalized shopping suggestions. The system includes means for user authentication, means for linking external accounts, means for acquiring purchase history, means for acquiring location information, means for collecting social media information, means for analysis using an artificial intelligence model, means for generating suggestion information, means for notifying suggestion information, means for providing shopping suggestions in real time, and means for providing detailed information and maps.

[1849] System Configuration

[1850] The system primarily consists of a server and user terminals. The server is responsible for data analysis and generating suggestion information, while the user terminals are responsible for collecting information and displaying the suggested information.

[1851] Specific examples of hardware and software

[1852] Servers: High-performance servers are used for data processing. For example, cloud servers such as Amazon Web Services (AWS) and Google Cloud Platform (GCP) can be used.

[1853] User devices: Smartphones are primarily used. This includes devices with mobile operating systems such as Android and iOS installed.

[1854] Generative AI models: Models using AI frameworks such as PyTorch and TensorFlow are used.

[1855] Feature details

[1856] 1. User Authentication Methods

[1857] When a user logs into the app for the first time, their authentication information is verified and permission to access the system is granted. At this time, the user can link external accounts (for example, electronic payment services or social media accounts).

[1858] 2. External account linking methods

[1859] After successful authentication, the system retrieves the user's purchase history from an external service and stores it in a database. This allows the system to understand the user's spending habits.

[1860] 3. Means of acquiring purchase history

[1861] Purchase history will be collected from electronic payment services and online shops to serve as basic data for analyzing user consumption behavior.

[1862] 4. Location information acquisition means

[1863] Using GPS technology, the system obtains the user's current location in real time. This allows it to identify which physical store the user is approaching.

[1864] 5. Means of gathering information from social media

[1865] It can collect trending and campaign information from social media and analyze user interests in real time.

[1866] 6. Analysis methods using artificial intelligence models

[1867] It integrates purchase history, location information, and social media data to analyze user preferences and behavioral patterns. By using generative AI models such as PyTorch, it generates highly accurate recommendation information.

[1868] 7. Proposal information generation means

[1869] Based on the analysis results, the system generates optimal shopping and coupon information for users. This also takes into account marketing information provided by companies.

[1870] 8. Proposal information notification means

[1871] The generated suggestion information is sent as a push notification to the user's smartphone. The notification includes information on special offers and coupons.

[1872] 9. Means of providing shopping suggestions in real time

[1873] When a user approaches a physical store, the system provides appropriate shopping suggestions on the spot. For example, it might send a notification like, "20% off sale at your nearest [brand name]!"

[1874] 10. Means of providing detailed information and maps

[1875] Based on the suggested information, provide users with links to access more detailed product information and store maps.

[1876] Specific example

[1877] For example, when a user arrives at a shopping mall, the system works as follows: First, a location information acquisition system identifies the user's location, and an AI model analyzes products and stores that the user might be interested in based on their purchase history and social media information. Then, a notification system sends a push notification saying, "There's a 30% off sale at your nearest electronics store!", along with more detailed information and a map.

[1878] Example of a prompt

[1879] Examples of prompt messages that provide suggestions based on the user's purchase history, current location, and social media trends are as follows:

[1880] "The user's purchase history includes electronics products, and their current location is within a shopping mall. According to social media trends, there is a sale on electronics products. Based on this information, we generate optimal shopping suggestions."

[1881] This allows users to enjoy shopping more efficiently, and enables companies to improve the accuracy of their targeted marketing.

[1882] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1883] Step 1: User authentication and external account linking

[1884] Input: User authentication information (User ID, password), external account information (electronic payment service or social media account)

[1885] Processing: The server authenticates the user based on the entered authentication information. After successful authentication, it links with an external account and obtains an authentication token from an external service (electronic payment service or social networking service).

[1886] Output: Authentication token and user profile information

[1887] Specific operation: When a user logs into the app, the server verifies the authentication information, and if successful, displays a pop-up prompting the user to link with an electronic payment service or social media.

[1888] Step 2: Obtain purchase history

[1889] Input: Authentication token, external account information

[1890] Processing: The server retrieves purchase history from electronic payment services and online shops using external account information. The retrieved data is then added to the user's profile.

[1891] Output: Purchase history data

[1892] Specific operation: Upon successful authentication, the server uses the authentication token to retrieve purchase history data from an external service's API and saves it to the database.

[1893] Step 3: Obtaining location information

[1894] Input: GPS data from the user's device

[1895] Process: The device acquires GPS data and sends its current location information to the server. The server uses this location information to determine the place the user is visiting.

[1896] Output: Current location information

[1897] Specific operation: The device obtains the user's current location via GPS and sends it to the server in real time. The server uses this data to determine which physical store the user is in.

[1898] Step 4: Gathering SNS information

[1899] Input: Authentication token, social media account information

[1900] Processing: The server uses social media account information to collect current trend and campaign information. This allows it to obtain real-time information related to the user's interests.

[1901] Output: SNS trend information, campaign information

[1902] Specific operation: The server periodically retrieves trending and campaign information using SNS APIs and stores it in a database.

[1903] Step 5: Data Integration and Analysis

[1904] Input: Purchase history data, current location information, social media trend information

[1905] Processing: The server integrates this data and uses a generative AI model to analyze user preferences and behavioral patterns. This generates foundational data for providing users with optimal shopping recommendations.

[1906] Output: Analysis results (user preference data, behavioral pattern data)

[1907] Specific operation: The server collects data, inputs that data into a generating AI model for analysis, and uses frameworks such as PyTorch to obtain highly accurate results.

[1908] Step 6: Generating Proposal Information

[1909] Input: Analysis results (user preference data, behavioral pattern data)

[1910] Processing: The server generates optimal shopping recommendations for the user based on the analysis results. These recommendations also incorporate marketing information provided by companies.

[1911] Output: Proposal Information

[1912] Specific operation: The server integrates analysis results with marketing information from companies and generates shopping suggestions tailored to the user.

[1913] Step 7: Notification of proposed information

[1914] Input: Proposal Information

[1915] Processing: The server pushes the generated suggestion information to the user's device. The notification may also include information on special offers and coupons.

[1916] Output: Push notification to user's device

[1917] Specific operation: The server sends the suggestion information to the user's smartphone, and a notification is displayed.

[1918] Step 8: Provide detailed information and maps.

[1919] Input: User action upon receiving the push notification (e.g., clicking a link)

[1920] Processing: The device displays more detailed product information and store locations to users who click the link in the push notification.

[1921] Output: Detailed information screen, map display

[1922] Specific operation: When the user clicks the notification, the device retrieves detailed information and map data from the server and displays it.

[1923] 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.

[1924] Modes for carrying out the invention

[1925] System Overview

[1926] This invention relates to a system that utilizes a user's purchase history, current location information, real-time information from social media, and an emotion engine that recognizes the user's emotions, and uses a generative AI model to provide personalized shopping suggestions. Specifically, the system consists of a user authentication means, an external account linking means, a purchase history acquisition means, a location information acquisition means, a social media information collection means, an analysis means using an artificial intelligence model, a suggestion information generation means, an emotion engine, and a suggestion information notification means.

[1927] Program processing

[1928] The system program performs the following operations:

[1929] 1. User authentication and data integration

[1930] When a user logs into the app for the first time, the user authentication method verifies the user's credentials and grants access to the system. At this time, the user can link external accounts (e.g., electronic payment services or social media accounts).

[1931] After successful user authentication, the server retrieves the user's purchase history from an external service. The retrieved data is stored in a database to analyze the user's consumption patterns.

[1932] 2. Customization settings and information gathering

[1933] Users can customize settings based on their interests in the app's settings screen. For example, they can specify that they are interested in a particular category (fashion, groceries, electronics, etc.).

[1934] The device acquires the user's location information in real time and sends it to the server. Additionally, the SNS information gathering mechanism collects real-time information (e.g., trends, campaign information) from social media.

[1935] 3. Emotion Recognition and Data Integration

[1936] The emotion engine installed in the device recognizes the user's emotions in real time and sends that data to the server. The emotion engine identifies emotions by analyzing the user's facial expressions, voice tone, etc.

[1937] The server integrates and analyzes emotional data, purchase history, customization settings, current location information, and social media information. Using an artificial intelligence model, it analyzes user preferences and behavioral patterns, and generates optimal suggestion information that also takes emotional states into account.

[1938] 4. Proposal information generation and notification

[1939] The server also collects recommendations provided by companies and filters them based on the user's preferences and emotions. This ensures that companies' marketing information is also presented to users with high accuracy.

[1940] The server notifies the user's device of the generated shopping recommendations. These notifications include coupon information and special offer details.

[1941] The device displays recommended information to the user as a notification. If the user shows interest in the suggestion, it provides a link to access detailed store and product information.

[1942] Specific example

[1943] Example 1: User's first use

[1944] 1. The user launches the app for the first time, enters their ID and password on the authentication screen, and logs in. Afterward, they link their electronic payment service and social media account.

[1945] 2. The server retrieves the user's past purchase history from external services and stores it in a database. It analyzes consumption trends and builds a user profile.

[1946] Example 2: Suggestions based on emotions and real-time information

[1947] 1. The device detects the user's location in a shopping mall using GPS. Simultaneously, the emotion engine recognizes the user's state of excitement from their facial expressions.

[1948] 2. The server checks the purchase history to confirm that the user has previously purchased items from a specific brand within that mall.

[1949] 3. The server retrieves sales information for the brand from social media and uses a generative AI model and sentiment data to generate optimal suggestions for the user.

[1950] 4. The device sends a push notification to the user saying, "20% off sale at your nearest [brand name]!" and provides a link to more information. When the user clicks the notification, the store's map information and sale details are displayed.

[1951] In this way, the system combines users' purchase history, current location information, and real-time emotional information to provide optimal shopping suggestions for each individual user. This allows users to have a more personalized and efficient shopping experience. Businesses can also improve the accuracy of targeted marketing that takes into account users' emotional states, enabling more effective customer acquisition.

[1952] The following describes the processing flow.

[1953] Step 1:

[1954] The user launches the app for the first time and authenticates with their Yahoo! ID. The user enters their ID and password on the login screen and clicks the "Login" button.

[1955] Step 2:

[1956] The server authenticates the user's ID and password, and if authentication is successful, creates a user profile in the database. The server uses an authentication API to verify the user's authentication information.

[1957] Step 3:

[1958] Users link their electronic payment services and social media accounts within the app. Users select "Electronic Payment Linkage" or "Social Media Linkage" from the settings menu.

[1959] Step 4:

[1960] The server obtains purchase history data from the electronic payment service with the user's consent. The server uses the electronic payment service's API to retrieve the user's past transaction data and stores it in the database.

[1961] Step 5:

[1962] Users can customize settings based on their interests in the app's settings screen. They can select categories such as fashion, groceries, and electronics, and configure notification frequency and preferred store lists.

[1963] Step 6:

[1964] The device periodically acquires the user's current location information and sends it to the server. The device uses a GPS sensor to collect location information and sends it to the server at regular intervals.

[1965] Step 7:

[1966] The emotion engine installed in the device recognizes the user's emotions in real time and sends that data to the server. The emotion engine identifies emotions by analyzing the user's facial expressions, voice tone, etc.

[1967] Step 8:

[1968] The server uses social media information gathering methods to collect real-time information related to users from social media (e.g., trends, campaign information).

[1969] Step 9:

[1970] The server integrates and analyzes the user's purchase history, customization settings, current location information, sentiment data, and social media information. Using artificial intelligence models, it analyzes the user's preferences and behavioral patterns to generate optimal recommendation information.

[1971] Step 10:

[1972] The server collects recommendation information provided by companies and filters it based on user preferences and sentiment data. This ensures that companies' marketing information is also suggested to users with high accuracy.

[1973] Step 11:

[1974] The server notifies the user's device of the generated shopping recommendations. These notifications include coupon information and special offer details.

[1975] Step 12:

[1976] The device displays recommended information to the user as a notification. The notification includes a link, which the user can click to view more details. The user taps the notification to access the details page.

[1977] Step 13:

[1978] Users check notifications and click on information that interests them. Clicking displays detailed store and product information, improving the user's shopping experience.

[1979] (Example 2)

[1980] 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".

[1981] In today's shopping landscape, providing personalized purchase suggestions to users is crucial for maintaining high user satisfaction. However, traditional systems typically rely solely on purchase history and location data for suggestions, failing to consider users' momentary emotions or real-time social media information. As a result, providing optimal suggestions for users has been difficult, and the marketing effectiveness for companies has been limited.

[1982] 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.

[1983] In this invention, the server includes user authentication means, external account linking means, purchase history acquisition means, location information acquisition means, SNS information collection means, emotion recognition means, analysis means using an artificial intelligence model, suggestion information generation means, and suggestion information notification means. This enables comprehensive analysis of the user's purchase history, current location information, real-time emotion information, and SNS information to provide optimal shopping suggestions to individual users.

[1984] "User authentication means" refers to the means used to verify the identity of a user when they access a system.

[1985] "External account linking methods" refer to methods for linking a system with external services (e.g., electronic payment services or social networking services).

[1986] A "purchase history acquisition method" is a means of acquiring a user's past purchase history and importing it into the system.

[1987] "Location information acquisition means" refers to methods for acquiring the user's current location information using GPS or similar technologies.

[1988] "SNS information gathering methods" refer to methods for collecting information from social media in real time.

[1989] "Means of recognizing emotions" refers to methods for identifying emotions from a user's facial expressions, voice, etc.

[1990] "Analysis methods using artificial intelligence models" refer to methods for analyzing data acquired using artificial intelligence models to analyze user preferences and behavioral patterns.

[1991] The "proposal information generation means" is a means of generating optimal shopping suggestions for the user based on the analysis results.

[1992] A "proposal information notification means" is a means of notifying the user's terminal of the generated proposal information.

[1993] Modes for carrying out the invention

[1994] System Program Overview

[1995] This invention relates to a system that utilizes a user's purchase history, current location information, real-time information from social media, and an emotion engine that recognizes the user's emotions, and uses a generative AI model to provide personalized shopping suggestions. This system includes user authentication means, external account linking means, purchase history acquisition means, location information acquisition means, social media information collection means, emotion recognition means, analysis means using an artificial intelligence model, suggestion information generation means, and suggestion information notification means.

[1996] Hardware and software to use

[1997] Server: Performs database management, API integration, and data analysis using artificial intelligence models.

[1998] Device: Smartphones, tablets, etc. It receives user input and activates the emotion engine.

[1999] Emotion engine: Software that analyzes the user's facial expressions and voice tone to identify their emotions.

[2000] GPS function: Obtains the user's location information.

[2001] SNS information gathering tools: Scraping tools and APIs for collecting real-time information from social media.

[2002] Explanation of the program's processing

[2003] 1. User Authentication

[2004] The user logs into the app for the first time, and their identity is verified through an authentication method. The authentication information is securely transmitted to the server.

[2005] The server verifies the received authentication information and initiates external account linking upon successful authentication.

[2006] 2. External account integration and data acquisition

[2007] The user links their account with an electronic payment service or social media account. Authentication information for the linking service is entered.

[2008] The server uses APIs from external services to retrieve purchase history and social media activity data, and stores it in a database.

[2009] 3. Customization settings

[2010] Users can customize their settings within the app based on their interests. For example, they can select specific categories or brands.

[2011] The device sends the configured information to the server, which then stores it in the database.

[2012] 4. Obtaining location information

[2013] The device periodically obtains the user's current location using its GPS function and sends it to the server.

[2014] The server stores location information in a database and integrates it with related data.

[2015] 5. Obtaining SNS information

[2016] The device uses a social networking information gathering tool to acquire real-time information related to the specified keywords.

[2017] The server analyzes the collected information and stores it in a database.

[2018] 6. Emotion recognition

[2019] The device uses its camera and microphone to identify emotions from the user's facial expressions and voice, and acquires emotion data.

[2020] The device sends emotional data to the server.

[2021] 7. Data Integration and Analysis

[2022] The server integrates emotional data, purchase history, customization settings, current location information, and social media information, and analyzes the data using an artificial intelligence model.

[2023] Artificial intelligence models analyze user preferences and behavioral patterns.

[2024] 8. Generation of proposed information

[2025] The server collects marketing information provided by companies and filters it based on the user's preferences and emotions.

[2026] We use an artificial intelligence model to generate optimal shopping suggestions.

[2027] 9. Notification of proposed information

[2028] The server notifies the terminal of the shopping suggestions it has generated. The notification includes coupon information and special offer information.

[2029] The device displays a notification to the user and provides a link to more information.

[2030] Specific example

[2031] 1. The user logs in for the first time and links their electronic payment service with their social media account.

[2032] 2. The server retrieves purchase history from an external service and saves it to the database.

[2033] 3. The GPS detects that the user is in a shopping mall, and the emotion engine recognizes the user's state of excitement.

[2034] 4. The server generates optimal suggestions using purchase history and sales information from social media.

[2035] 5. The device sends a push notification saying, "20% off sale at your nearest [brand name] store."

[2036] Examples of prompts to input into a generative AI model

[2037] "This user has a history of frequently purchasing fashion items. They are currently in a shopping mall. Their facial expression indicates excitement. Please generate effective shopping suggestions for this user."

[2038] "This user is interested in electronics and is currently located in central Tokyo. They have sales information for electronics brands on social media. Please create the best possible suggestions for this user."

[2039] In this way, the system continuously collects data from multiple sources and provides personalized shopping suggestions to each user, thereby improving the user experience and maximizing the marketing effectiveness of companies.

[2040] The flow of the specific processing in Example 2 will be explained using Figure 13.

[2041] Step 1:

[2042] User Authentication

[2043] Operation:

[2044] The user launches the app for the first time and enters their ID and password on the authentication screen.

[2045] The server compares the received authentication information with the user information in the database, and if authentication is successful, it starts a session.

[2046] Input: User ID, Password

[2047] Output: Session started based on authentication success / failure result.

[2048] Specific processing:

[2049] The server receives the authentication information and compares it with the information in the database. If authentication is successful, it generates session information and grants the user access.

[2050] Step 2:

[2051] External account integration and data retrieval

[2052] Operation:

[2053] Users enter authentication information for linking their electronic payment service or social media account within the app.

[2054] The server sends API requests to linked external services to retrieve user purchase history and social media activity data. This data is stored in a database.

[2055] Input: External account credentials

[2056] Output: Purchase history data, social media activity data

[2057] Specific processing:

[2058] The server calls an external API to retrieve the user's purchase history and social media data. The retrieved data is stored in the database as the user's profile.

[2059] Step 3:

[2060] Customization settings

[2061] Operation:

[2062] Users can customize settings based on their interests in the app's settings screen. For example, they can select specific categories or brands.

[2063] The terminal sends the entered configuration information to the server and stores it in the database.

[2064] Input: User customization settings information

[2065] Output: Configuration information stored in the database

[2066] Specific processing:

[2067] The user sends their selected customization settings from the terminal to the server, which stores this information in a database for use in subsequent analysis processes.

[2068] Step 4:

[2069] Location information acquisition

[2070] Operation:

[2071] The device periodically obtains the user's current location using its GPS function and sends it to the server.

[2072] The server stores the received location information in a database.

[2073] Input: Location information obtained from GPS

[2074] Output: Location information stored in the database

[2075] Specific processing:

[2076] The device periodically uses GPS to obtain the user's current location and sends it to the server. The server stores the received location information in a database and updates the location information in real time.

[2077] Step 5:

[2078] Acquisition of SNS information

[2079] Operation:

[2080] The device retrieves real-time information from social media information gathering tools based on specified keywords.

[2081] The server stores the collected SNS information in a database and integrates it into the user's profile.

[2082] Input: Collected SNS information

[2083] Output: SNS information stored in the database

[2084] Specific processing:

[2085] The device uses an SNS collection tool to acquire information related to specified keywords and sends it to the server. The server stores the collected SNS information in a database.

[2086] Step 6:

[2087] emotion recognition

[2088] Operation:

[2089] The device uses its camera and microphone to analyze the user's facial expressions and voice in real time and identify their emotions.

[2090] The device sends the identified emotion data to the server.

[2091] Input: Facial expression, voice tone

[2092] Output: Identified sentiment data

[2093] Specific processing:

[2094] The emotion engine uses information acquired from the device's camera and microphone to recognize the user's emotions and sends the results to the server. The server stores the emotion data in a database.

[2095] Step 7:

[2096] Data Integration and Analysis

[2097] Operation:

[2098] The server integrates and analyzes emotional data, purchase history, customization settings, current location information, and social media information.

[2099] Using artificial intelligence models, we analyze user preferences and behavioral patterns to generate optimal shopping recommendations.

[2100] Input: Sentimental data, purchase history, customization settings, current location information, social media information

[2101] Output: Analysis results, proposed information

[2102] Specific processing:

[2103] The server uses integrated data to perform analysis using an artificial intelligence model, analyzing user preferences and behavioral patterns. Based on these results, it generates optimal shopping recommendations.

[2104] Step 8:

[2105] Generation of proposed information

[2106] Operation:

[2107] The server collects marketing information provided by companies (e.g., coupon information, special offer information) and filters it based on the user's preferences and emotions.

[2108] We use a generative AI model to generate optimal shopping suggestions for the user.

[2109] Input: Marketing information and analysis results from companies.

[2110] Output: Optimal shopping suggestions

[2111] Specific processing:

[2112] The system filters information provided by companies and uses a generative AI model to create optimal suggestions that take into account the user's preferences and emotional state.

[2113] Step 9:

[2114] Notification of proposed information

[2115] Operation:

[2116] The server notifies the user's device of the shopping suggestions it has generated. These notifications include coupon information and special offer information.

[2117] The device will display this notification to the user as a push notification, providing a link to more information.

[2118] Input: Generated shopping suggestions

[2119] Output: Notification to user terminal

[2120] Specific processing:

[2121] The server sends the generated suggestion information to the user's device, which then displays it to the user as a push notification. The notification includes a link to more information, which, when tapped by the user, displays information about the relevant store or product.

[2122] In this way, each step works together to create a system that can efficiently provide personalized suggestions to users.

[2123] (Application Example 2)

[2124] 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".

[2125] Traditional online shopping systems offered recommendations based on user preferences, but they did not provide personalized suggestions that took into account real-time emotional states or location information. This made it difficult to provide a shopping experience that aligned with users' actual interests and desires, resulting in many users spending a considerable amount of time finding suitable products. Furthermore, companies faced the challenge of being unable to conduct effective marketing based on users' real-time emotions and behavior.

[2126] 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.

[2127] In this invention, the server includes user authentication means, external account linking means, purchase history acquisition means, location information acquisition means, SNS information collection means, emotion recognition engine, analysis means using an artificial intelligence model, suggestion information generation means, and suggestion information notification means. This enables integrated analysis of the user's purchase history, current location information, SNS information, and emotional state, and allows for optimal shopping suggestions for each individual user using a generated AI model.

[2128] "User authentication means" refers to a method of verifying a user's authentication information and granting them access to the system.

[2129] "External account linking methods" refer to methods for linking with external services such as electronic payment services and social media accounts.

[2130] "Purchase history acquisition method" refers to a method for acquiring a user's past purchase history and storing it in the system....

Claims

1. A user authentication method that verifies the user's authentication information and grants access to the system when the user logs into the system for the first time, An external account linking method that allows users to link their external service accounts to the system and retrieve data from those services, A purchase history acquisition method that obtains purchase history data from external services used by users and utilizes this data within the system, A location information acquisition means that uses the user's device to acquire real-time location information and transmits that data to the system, A means of collecting SNS information that gathers real-time information from social networking services and utilizes it within the system, Analysis methods using artificial intelligence models, A suggestion information generation method that utilizes artificial intelligence technology to generate optimal suggestion information by analyzing user preferences and behavioral patterns based on acquired data, A system including a means for notifying the user's terminal of generated proposal information and providing the user with the proposal information at an appropriate time.

2. The system according to claim 1, further comprising means for obtaining user customization settings and generating suggestion information based thereon.

3. The system according to claim 1, further comprising means for obtaining proposal information from companies and filtering this information based on user preferences.

Images