System

Abstract

A system is provided.SOLUTION: A system comprising: means for acquiring account information and settlement history information of a user; means for analyzing the acquired settlement history information in real time using a generated AI model and detecting an abnormal pattern; means for notifying the user when an abnormal pattern is detected; and means for receiving a security query from the user, analyzing the query content using the generated AI model, and performing an appropriate response.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] As smartphone payments become more widespread, security risks such as fraudulent use and leaks of personal information are increasing. These security risks can prevent users from using smartphone payments safely. Other issues include the lack of a system that can quickly respond to abnormal transactions and the lack of 24 / 7 support. The purpose of this invention is to solve these issues and provide an environment in which users can safely use smartphone payments. [Means for solving the problem]

[0005] The present invention solves the above problems by providing a means for acquiring user account information and payment history data, a means for analyzing the acquired payment history data in real time using a generative AI model to detect abnormal patterns, a means for notifying the user when an abnormal pattern is detected, and a means for accepting security-related inquiries from users, analyzing the content of the inquiry using a generative AI model, and taking appropriate action.

[0006] Specifically, the generative AI model learns users' trading patterns and detects abnormal patterns by taking into account factors such as unusual trading times, trading locations, and transaction amounts. When an abnormal pattern is detected, the user is notified in real time via push notification, SMS, email, etc. In addition, a 24 / 7 support desk has been set up, and the generative AI model will promptly respond to security-related inquiries from users, providing an environment in which users can use the service with peace of mind.

[0007] "User" refers to an individual or corporation that uses the system to make payments and manage accounts.

[0008] "Account information" refers to information used to authenticate a user, including a user ID, password, email address, etc.

[0009] "Payment history data" refers to a record of transactions conducted by a user, and includes information such as the date and time of the transaction, the amount, the location, and the transaction details.

[0010] A "generative AI model" is an algorithmic model that uses machine learning and is used to detect anomalies and perform automatic responses.

[0011] An "anomalous pattern" is a transaction characteristic that deviates from normal transaction behavior and may be an indication of fraud or suspicious activity.

[0012] "Real-time analysis" refers to processing acquired or received data immediately and reflecting the analysis results instantly.

[0013] "Means of notification" refers to the method of notifying the user of an abnormality when it is detected, and includes push notification, SMS, email, etc.

[0014] "Security Inquiry" means a user's question or inquiry regarding suspected fraud, potential personal information leaks, and other security-related issues.

[0015] "Analyzing the content of inquiries" refers to analyzing the information contained in questions and inquiries from users to determine the appropriate response.

[0016] "Appropriate response" means providing the most appropriate solution to a user's security issue or question, including specific actions such as providing information, locking an account, or resetting a password. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The present invention is a system that acquires user account information and payment history data, analyzes it in real time using a generative AI model to detect abnormal patterns, and notifies users of the abnormalities. It also has the function of accepting security-related inquiries from users, analyzing the inquiries using a generative AI model, and responding appropriately.

[0039] System Overview

[0040] The server is responsible for collecting data from the user's smartphone device, detecting anomalies, sending notifications, and responding to inquiries, allowing users to safely and efficiently manage their accounts and payments.

[0041] What the program does

[0042] Data collection

[0043] The server periodically obtains user account information and payment history data, including user ID, transaction date and time, transaction amount, and transaction location. The terminal transmits the data to the server in real time every time the user makes a payment on their smartphone.

[0044] Real-time analysis of data

[0045] The server uses the generative AI model to analyze the acquired payment history data in real time and detect abnormal patterns. Specifically, it identifies abnormal transactions based on payment patterns (e.g., trading time, trading location, and transaction amount).

[0046] notification

[0047] If the server detects an abnormal pattern, it will immediately notify the user via push notification, SMS, email, etc. When the device receives the notification, it will display an alert to the user, helping them to take prompt action.

[0048] Inquiry response

[0049] When a user has a security question or wants to consult, they send an inquiry from their device to the support desk. The server then uses a generative AI model to analyze the inquiry and take appropriate action. Specific actions include locking the account, resetting the password, and confirming transactions.

[0050] Specific examples

[0051] Anomaly detection example

[0052] 1. The area that User A normally uses is assumed to be within Japan.

[0053] 2. A large payment is made from overseas late at night due to unauthorized access.

[0054] 3. The server's generative AI model uses an anomaly detection algorithm to identify this anomalous transaction.

[0055] 4. The server sends a push notification to User A informing him of the abnormal transaction.

[0056] 5. User A checks the notification and changes the account password to prevent unauthorized use.

[0057] Examples of responding to inquiries

[0058] 1. User B becomes concerned about their recent transaction history and contacts support within the app.

[0059] 2. The server receives the query and analyzes the content using a generative AI model.

[0060] 3. If no abnormalities are found, User B is automatically notified of this information and informed that he or she can continue trading with confidence.

[0061] 4. User B reads the answer and has his / her concerns resolved.

[0062] As described above, the system of the present invention effectively protects the security of smartphone payments for users and provides functions for rapid response. By using this system, users can create an environment in which they can use smartphone payments with peace of mind.

[0063] The processing flow will be explained below.

[0064] Step 1:

[0065] The terminal processes the user's payment and generates payment data (user ID, transaction date and time, transaction amount, transaction location, etc.).

[0066] Step 2:

[0067] The terminal transmits the generated payment data to the server in real time.

[0068] Step 3:

[0069] The server stores the received payment data in a database.

[0070] Step 4:

[0071] The server uses the generated AI model to analyze payment data in real time and detect abnormal patterns.

[0072] Step 5:

[0073] The generative AI model compares a user's past payment history and identifies anomalous patterns based on the time of day, location, and amount of the transaction.

[0074] Step 6:

[0075] If the server detects an abnormal pattern, it generates a message to notify the user of the anomaly detection result.

[0076] Step 7:

[0077] The server generates a notification message and sends it to the device via push notification, SMS, or email.

[0078] Step 8:

[0079] The device receives the notification message and displays an alert to the user.

[0080] Step 9:

[0081] The user checks the notification and takes appropriate action, such as changing the account password, if necessary.

[0082] Step 10:

[0083] If users have any security questions or concerns, they can submit an inquiry from within the app.

[0084] Step 11:

[0085] The server receives a query from the user and passes the query to the generative AI model.

[0086] Step 12:

[0087] The generative AI model analyzes the inquiry content and generates an appropriate response.

[0088] Step 13:

[0089] The server generates a reply message to the user based on the generated countermeasure and sends it to the terminal.

[0090] Step 14:

[0091] The device receives the reply message and displays it to the user.

[0092] Step 15:

[0093] Based on the information provided by the user, necessary measures are taken to resolve security issues.

[0094] Example 1

[0095] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0096] The conventional system had insufficient security measures for user account information and payment history data, making it difficult to detect fraudulent transactions early and respond appropriately. Notifications after anomalies were detected and responses to user inquiries were delayed, making it difficult to prevent fraudulent transactions. Furthermore, there was a lack of support for users to respond quickly when they received notifications.

[0097] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0098] In this invention, the server includes means for acquiring user account information and payment history data, means for analyzing the acquired payment history data in real time using a generative AI model to detect abnormal patterns, means for notifying the user when an abnormal pattern is detected, means for accepting security-related inquiries from users, analyzing the inquiries using the generative AI model, and taking appropriate action, and means for supporting users who receive notifications so that they can respond quickly. This enables early detection of abnormal payment patterns and immediate response, and supports users in responding quickly when they receive notifications.

[0099] "User account information" refers to data necessary for personal authentication of a user and information related to account management.

[0100] "Payment History Data" means data that includes detailed records of payments made by a User.

[0101] A "generative AI model" is an artificial intelligence model that has been trained using machine learning algorithms to automatically perform specific tasks.

[0102] "Real-time analysis" refers to processing and analyzing data as soon as it is generated.

[0103] An "anomalous pattern" is a pattern that indicates an abnormal transaction that deviates from normal transactions.

[0104] "Notifications" are messages or alerts intended to inform users of unusual transactions or security-related information.

[0105] "Security Inquiry" means a user's inquiry or consultation regarding a security issue or concern regarding the system or a transaction.

[0106] "Analysis" means examining data in detail to clarify its content and meaning.

[0107] "Appropriate response" means taking the most appropriate action to resolve the user's security issue based on the analysis results.

[0108] "Support" means providing advice and assistance necessary for users to use the system.

[0109] The present invention is a system that acquires and analyzes user account information and payment history data, detects abnormal transactions, and notifies users. It also includes a function that uses a generative AI model to respond appropriately to user security inquiries.

[0110] Hardware and software used

[0111] The server plays a central role in this system. Specifically, the following hardware and software are used:

[0112] Database management systems (e.g. MySQL, PostgreSQL)

[0113] Execution environment for generative AI models (e.g., TensorFlow, PyTorch)

[0114] Notification systems (e.g., Firebase Cloud Messaging, Twilio)

[0115] API server (e.g. Node.js, Django)

[0116] The device is the user's smartphone, which is compatible with both Android and iOS.

[0117] Specific operation of the system

[0118] The server periodically obtains the user's account information and payment history data. This includes information sent from the terminal using the API. For example, if a user makes a payment of 1,000 yen, the transaction data (user ID, transaction date and time, transaction amount, transaction location, etc.) is sent to the server in real time.

[0119] The server uses a generative AI model to analyze the acquired payment history data in real time and detect abnormal transaction patterns. The generative AI model takes into account the user's usual trading hours, trading locations, and transaction amounts. For example, if a user's account normally only trades domestically during the day, and a large overseas transaction is made late at night, the model will determine that this transaction is anomalous.

[0120] If an abnormal pattern is detected, the server immediately notifies the device. The user is notified of the abnormal transaction via push notification, SMS, or email. When the device receives the notification, an alert is displayed to the user. For example, if a user detects a fraudulent transaction overseas, the information is immediately sent to the user via push notification.

[0121] When a user makes a security inquiry, the app sends the inquiry to the support desk. The device then sends the inquiry to the server. The server uses a generative AI model to analyze the inquiry and determine the appropriate response. For example, if a user requests a password reset, the server guides the user through the procedure and notifies the user.

[0122] Specific examples

[0123] Anomaly detection example

[0124] 1. The area that User A normally uses is assumed to be within Japan.

[0125] 2. A large payment is made from overseas late at night due to unauthorized access.

[0126] 3. The server's generative AI model detects this anomalous transaction.

[0127] 4. The server immediately sends a push notification to User A informing him of the abnormal transaction.

[0128] 5. User A checks the notification and changes the account password to prevent unauthorized use.

[0129] Examples of responding to inquiries

[0130] 1. User B becomes concerned about their recent transaction history and contacts support within the app.

[0131] 2. The server receives the query and analyzes the content using a generative AI model.

[0132] 3. If no abnormalities are found, User B is automatically notified of this information and informed that he or she can continue trading with confidence.

[0133] 4. User B reads the answer and has his / her concerns resolved.

[0134] Example prompt sentence:

[0135] "I'm concerned about my recent transaction history. I'd like to contact support."

[0136] "There is a large amount of payment from overseas, please confirm."

[0137] The above is a specific embodiment for carrying out the present invention.

[0138] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0139] Step 1: Data collection

[0140] The server periodically obtains the user's account information and payment history data. Every time the terminal (smartphone) application makes a payment, it generates data such as the user ID, transaction date and time, transaction amount, and transaction location, and sends this data to the server in real time.

[0141] Input: Payment data generated when a user makes a payment on their smartphone

[0142] Data processing: The terminal sends the payment data to the server as an API request

[0143] Output: Payment data stored on the server

[0144] Step 2: Analyzing data in real time

[0145] The server uses a generative AI model to analyze the acquired payment history data in real time to detect abnormal transaction patterns. The generative AI model takes into account normal trading hours, trading locations, and transaction amounts to identify abnormal transactions.

[0146] Input: Payment data stored on the server

[0147] Data processing: Analyze data using generative AI models to detect anomalous patterns

[0148] Output: Alert data when abnormal transactions occur

[0149] Step 3: Notification of anomaly detection

[0150] If the server detects an abnormal pattern, it immediately notifies the device, informing the user of the details of the abnormal transaction using at least one of push notification, SMS, and email.

[0151] Input: Abnormal transaction alert data

[0152] Data processing: generating and sending notification messages

[0153] Output: A notification message that will be displayed on the user's terminal.

[0154] Step 4: User response

[0155] The user receives a notification, checks the alert, and takes appropriate action (e.g., change password) through the app if necessary.

[0156] Input: Notification message

[0157] Data processing: Check the notification content and take measures

[0158] Output: User response data sent to the server

[0159] Step 5: Handling inquiries

[0160] The user submits a security inquiry from the app. The device sends the inquiry to the server, which analyzes it using the generative AI model. An appropriate countermeasure is determined and notified to the user.

[0161] Input: User message

[0162] Data processing: Analyzing inquiries and determining responses using generative AI models

[0163] Output: The workaround message sent to the user's device

[0164] Specific behavior:

[0165] When User C makes a payment of 500 yen using his / her smartphone, the device sends the transaction data (user ID, transaction date and time, transaction amount, transaction location, etc.) to the server in real time (Step 1).

[0166] The server inputs the data into the generated AI model, analyzes transaction patterns in real time, and detects an anomaly, for example, if a large payment is made overseas late at night (Step 2).

[0167] The server sends a push notification to User C based on the abnormal transaction data, and the device receives the notification and displays an alert to the user (Step 3).

[0168] User C sees the alert, selects an action within the app, and sends a response to the server (step 4).

[0169] If User C has any questions or concerns, they can contact support through the app, and the device will send the inquiry to the server. The server will analyze the inquiry using the generated AI model and notify the user of the appropriate response (Step 5).

[0170] (Application example 1)

[0171] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0172] In recent years, the spread of electronic payments using smartphones has led to an increase in cybercrime attempts to fraudulently obtain users' payment information. However, current electronic payment systems are sometimes slow to detect and respond to payment anomalies, making it difficult to fully ensure user security. There is also a need for systems to respond quickly and appropriately to security-related inquiries from users. This has led to an urgent need to build a system that allows users to use electronic payments with peace of mind.

[0173] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0174] In this invention, the server includes means for acquiring user account information and payment history data, means for analyzing the acquired payment history data in real time using a generative AI model and detecting abnormal patterns, means for notifying the user when an abnormal pattern is detected, means for accepting security-related inquiries from users, analyzing the inquiries using a generative AI model, and taking appropriate measures, means for continuously monitoring user payment information, means for analyzing abnormal transactions in real time based on the monitored data, and means for immediately issuing an alert and encouraging further safety measures when an abnormal transaction occurs. This makes it possible to monitor user payment information in real time, quickly detect abnormal transactions, and take immediate countermeasures.

[0175] "Account information" refers to data including identification information and authentication information required when a user uses a service.

[0176] "Payment history data" refers to information about all transactions conducted by a user, specifically including transaction date and time, transaction amount, transaction location, transaction ID, etc.

[0177] A "generative AI model" is an artificial intelligence model designed to perform pattern recognition and anomaly detection using machine learning and deep learning.

[0178] "Means of real-time analysis" refers to technology that processes data instantly and provides analysis results instantly.

[0179] An "anomalous pattern" refers to an irregular transaction that deviates from normal transaction patterns and may indicate fraud or error.

[0180] "Notification methods" refer to communication methods used to notify users of abnormal transactions and important information, and specifically include push notifications, SMS, email, etc.

[0181] "Means for analyzing inquiries" refers to technology that automatically understands the content of inquiries from users and provides appropriate answers and countermeasures.

[0182] "Means for continuously monitoring payment information" refers to technology that constantly monitors users' transaction activities and detects suspicious transactions in real time.

[0183] "Means for analyzing abnormal transactions in real time based on monitoring data" refers to technology that instantly processes data acquired during monitoring and detects abnormal transactions.

[0184] "Means for issuing warnings" refers to technology that issues warnings to users when abnormal transactions are detected, encouraging them to take prompt action.

[0185] "Safety measures prompting" refers to technology that prompts users to take additional security measures when abnormal transactions or security threats are detected.

[0186] The present invention is a security system for maintaining the safety of users' electronic payments. A specific embodiment of this system is described below.

[0187] System Overview

[0188] The server plays a key role in collecting data from users' smartphones, detecting anomalies, sending notifications, and responding to inquiries, allowing users to safely and efficiently manage their accounts and payments.

[0189] Hardware / Software used

[0190] server

[0191] The server is responsible for collecting data, analyzing abnormal patterns in real time, sending notifications, and analyzing inquiries.

[0192] Install a generative AI model (e.g., Isolation Forest model) to perform anomaly detection.

[0193] Send notification emails using an SMTP server.

[0194] Terminal

[0195] When a user makes a transaction using their smartphone, the data is sent to the server.

[0196] Notify users via push notification, SMS, email, etc.

[0197] Program processing explanation

[0198] 1. Data Collection

[0199] The terminal sends payment data (user ID, transaction date and time, transaction amount, transaction location, etc.) to the server.

[0200] The server periodically retrieves this data and stores it in a database.

[0201] 2. Real-time analysis

[0202] The server analyzes the acquired payment history data in real time using a generative AI model (Isolation Forest model) and detects abnormal patterns.

[0203] Specifically, it identifies abnormal transactions based on trading time, trading location, and transaction amount.

[0204] 3. Notification

[0205] If the server detects an abnormal pattern, it will immediately notify the user.

[0206] Notification methods include push notification, SMS, and email.

[0207] The device receives these notifications and displays an alert to the user.

[0208] 4. Response to inquiries

[0209] When a user has a question or wants to consult about security, the user sends an inquiry from the terminal to the support desk.

[0210] The server uses a generative AI model to analyze the inquiry and take appropriate action, such as locking the account, resetting the password, or confirming the transaction.

[0211] Specific examples

[0212] Anomaly detection example

[0213] 1. The area that User A normally uses is assumed to be within Japan.

[0214] 2. A large payment is made from overseas late at night due to unauthorized access.

[0215] 3. The server's generative AI model uses an anomaly detection algorithm to identify this anomalous transaction.

[0216] 4. The server sends a push notification to User A informing him of the abnormal transaction.

[0217] 5. User A checks the notification and changes the account password to prevent unauthorized use.

[0218] Examples of responding to inquiries

[0219] 1. User B becomes concerned about their recent transaction history and contacts support within the app.

[0220] 2. The server receives the query and analyzes the content using a generative AI model.

[0221] 3. If no abnormalities are found, User B is automatically notified of this information and informed that he or she can continue trading with confidence.

[0222] 4. User B reads the answer and has his / her concerns resolved.

[0223] Prompt Sentence Examples

[0224] Determine whether the following transactions are unusual:

[0225] Transaction ID: 1234

[0226] Date: 2023-11-01

[0227] Price: 10,000 yen

[0228] Location: Tokyo

[0229] Analyze whether there is an abnormality based on the following items.

[0230] Trading Area

[0231] Trading Hours

[0232] Transaction amount

[0233] The above is a specific example of the embodiment of the present invention. By using this system, users can make electronic payments more safely.

[0234] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0235] Step 1:

[0236] Data collection

[0237] Each time a user makes an electronic payment, the terminal generates payment data, such as the user ID, transaction date and time, transaction amount, and transaction location. This data is sent in real time to the server, which stores the received data in a database and stores it for continuous monitoring.

[0238] Input: User payment data generated during electronic payment (user ID, transaction date and time, transaction amount, transaction location, etc.)

[0239] Output: Payment data records stored in a database

[0240] Step 2:

[0241] Real-time analytics

[0242] The server monitors the payment data stored in the database in real time and analyzes anomalous patterns using a generative AI model (Isolation Forest model), identifying anomalous transactions based on factors such as the time of day, place of transaction, and transaction amount.

[0243] Input: Records of payment data stored in the database

[0244] Output: Flags for abnormal transactions (transactions that are determined to be abnormal are flagged)

[0245] Step 3:

[0246] notification

[0247] If the server detects an abnormal transaction, it will immediately notify the user via push notification, SMS, email, etc. The device will receive the notification and display an alert to the user.

[0248] Input: Transaction data identified as abnormal by real-time analysis

[0249] Output: Notification to user (push notification, SMS, email)

[0250] Step 4:

[0251] Inquiry response

[0252] When a user makes a security inquiry, they send it to the support desk from their device. The server receives it and analyzes the inquiry using a generative AI model. Based on the analysis results, the server takes appropriate action. This can include locking the account, resetting the password, or confirming transactions.

[0253] Input: Security inquiry from user

[0254] Output: The server responds appropriately and notifies the user

[0255] Step 5:

[0256] Continuous monitoring

[0257] The server continuously monitors users' payment information and detects and responds to any abnormalities as necessary, thereby ensuring the safety of users' payment information at all times.

[0258] Input: New payment data collected automatically

[0259] Output: Real-time updated payment database and record of anomalous transactions

[0260] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0261] System Overview

[0262] The present invention is a system that acquires user account information and payment history data, detects abnormal patterns by combining a generative AI model and an emotion engine for real-time analysis, and notifies users of the abnormalities. It also has a function to accept security-related inquiries from users, analyze the content of the inquiry and the user's emotions using the generative AI model and the emotion engine, and respond appropriately.

[0263] What the program does

[0264] Data collection

[0265] The server periodically obtains the user's account information and payment history data, including the user ID, transaction date and time, transaction amount, transaction location, etc. The terminal transmits the data to the server in real time every time the user makes a payment on their smartphone.

[0266] Real-time analysis of data

[0267] The server uses the generative AI model to analyze the acquired payment history data in real time and detect abnormal patterns. Specifically, it identifies abnormal transactions based on payment patterns (e.g., trading time, trading location, and transaction amount).

[0268] notification

[0269] If the server detects an abnormal pattern, it will immediately notify the user via push notification, SMS, email, etc. When the device receives the notification, it will display an alert to the user, helping them to take prompt action.

[0270] Inquiry response

[0271] When a user has a question or inquiry about security, they send it to the support desk from their device. The server then analyzes the inquiry using a generative AI model and emotion engine, and generates an appropriate response. Specific responses include locking the account, resetting the password, and confirming transactions, and the response is based on the user's emotions analyzed by the emotion engine.

[0272] Use of emotion engine

[0273] The emotion engine can recognize a user's emotions through voice or text analysis. For example, if a user makes a text-based inquiry, the engine analyzes the text to identify emotions (anxiety, anger, relief, etc.) and generates an appropriate response. For voice-based inquiries, the engine analyzes the tone of the voice and the phrasing to recognize emotions and reflect them in the response.

[0274] Specific examples

[0275] Anomaly detection example

[0276] 1. The area that User A normally uses is assumed to be within Japan.

[0277] 2. A large payment is made from overseas late at night due to unauthorized access.

[0278] 3. The server's generative AI model uses an anomaly detection algorithm to identify this anomalous transaction.

[0279] 4. The server sends a push notification to User A informing him of the abnormal transaction.

[0280] 5. User A checks the notification and changes the account password to prevent unauthorized use.

[0281] Examples of responding to inquiries

[0282] 1. User B becomes concerned about their recent transaction history and contacts support within the app.

[0283] 2. The server receives the query and analyzes the content and user sentiment using a generative AI model and emotion engine.

[0284] 3. If no abnormalities are found, User B is automatically notified of this information and informed that he or she can continue trading with confidence.

[0285] 4. User B reads the answer and resolves their concerns. If the emotion engine recognizes the user's concerns, it provides additional information or support to further reassure them.

[0286] As described above, the system of the present invention provides a high level of security for smartphone payments and functions for quick and appropriate responses. In particular, by combining it with an emotion engine, it becomes possible to respond in a detailed manner according to the emotions of each individual user, greatly improving user satisfaction and peace of mind.

[0287] The processing flow will be explained below.

[0288] Step 1:

[0289] The terminal processes the user's payment and generates payment data (user ID, transaction date and time, transaction amount, transaction location, etc.).

[0290] Step 2:

[0291] The terminal transmits the generated payment data to the server in real time.

[0292] Step 3:

[0293] The server stores the received payment data in a database.

[0294] Step 4:

[0295] The server uses the generated AI model to analyze payment data in real time and detect abnormal patterns.

[0296] Step 5:

[0297] The generative AI model compares a user's past payment history and identifies anomalous patterns based on the time of day, location, and amount of the transaction.

[0298] Step 6:

[0299] If the server detects an abnormality, it generates a message to notify the user based on the results of the abnormality detection.

[0300] Step 7:

[0301] The server generates a notification message and sends it to the device via push notification, SMS, or email.

[0302] Step 8:

[0303] The device receives the notification message and displays an alert to the user.

[0304] Step 9:

[0305] The user checks the notification and takes appropriate action, such as changing the account password, if necessary.

[0306] Step 10:

[0307] If users have any security questions or concerns, they can submit an inquiry from within the app.

[0308] Step 11:

[0309] The server receives a query from the user and passes the query to the generative AI model.

[0310] Step 12:

[0311] The generative AI model analyzes the inquiry content and generates an appropriate response.

[0312] Step 13:

[0313] The emotion engine analyzes the content of the user's inquiry and recognizes the user's emotions (anxiety, anger, relief, etc.).

[0314] Step 14:

[0315] The server generates an optimal reply message for the user based on the generated countermeasure and the user's emotions recognized by the emotion engine, and sends it to the device.

[0316] Step 15:

[0317] The device receives the reply message and displays it to the user.

[0318] Step 16:

[0319] Based on the information provided by the user, necessary measures are taken to resolve security issues.

[0320] Example 2

[0321] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0322] Conventional systems had issues such as being unable to respond in real time when anomalies occurred in users' transaction history data, and difficulty in responding appropriately and quickly to safety-related inquiries from users. Furthermore, they were unable to respond in a way that took users' feelings into consideration, which led to a decline in user satisfaction and a sense of security. It was necessary to solve these issues.

[0323] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring user account information and transaction history data, means for analyzing the acquired transaction history data in real time using a generative AI model and detecting abnormal patterns, means for notifying the user when an abnormal pattern is detected, and means for accepting safety-related inquiries from users, analyzing the inquiry content using the generative AI model and an emotion engine, and providing an appropriate response. This makes it possible to detect abnormalities in user transaction data in real time and quickly notify the user, and to respond to user inquiries appropriately and in accordance with their emotions.

[0324] "Account Information" means information used to identify and authenticate a user, including user ID, password, contact information, etc.

[0325] "Transaction history data" refers to detailed information about transactions conducted by a user, including the transaction date and time, transaction amount, transaction location, and payment method.

[0326] A "generative AI model" is a model that uses artificial intelligence algorithms to analyze and process data to generate new insights and patterns.

[0327] "Real-time analysis" means processing and analyzing data immediately after it is generated or acquired.

[0328] An "abnormal pattern" is a transaction that significantly deviates from normal transaction patterns, such as a deviation from normal trading hours or locations, or a high value transaction.

[0329] "Notification" means a means of informing a User of anomaly detection or other important information, which may take the form of a push notification, text message, electronic message, etc.

[0330] A "security inquiry" is an inquiry made by a user to raise questions or concerns about the security of their account or unusual transactions.

[0331] The "emotion engine" is an algorithm that analyzes the user's emotional state (anxiety, anger, relief, etc.) from their text and voice, and generates countermeasures based on the results.

[0332] The present invention is a system that acquires user account information and transaction history data, analyzes them in real time using a generative AI model and an emotion engine to detect abnormal patterns, and notifies users of any abnormalities. It also has the function of accepting safety-related inquiries from users, analyzing them, and taking appropriate action.

[0333] System program generation

[0334] The system's program is built around the interaction between a server, a device, and a user. The server is responsible for the main data processing, while the device is responsible for receiving user input and notifications. These roles are realized by integrating a generative AI model and an emotion engine.

[0335] Hardware and software used

[0336] Server: Uses cloud computing services (e.g., AWS, Google Cloud) and uses a database management system (e.g., MySQL).

[0337] Terminal: A mobile device such as a smartphone or tablet is used, and a dedicated payment application is run on it.

[0338] Generative AI models: Use machine learning frameworks such as TensorFlow and PyTorch.

[0339] Emotion engine: Uses NLP libraries (e.g. spaCy, NLTK) and speech analysis tools (e.g. Google Speech-to-Text API).

[0340] What the program does

[0341] The server periodically retrieves user account information and transaction history data and analyzes it in real time using a generative AI model. The retrieved data is stored in a database. If an abnormal trading pattern is detected, the server will notify the user. Notification methods include push notifications, text messages, and electronic messages.

[0342] When a user makes a safety inquiry, the inquiry is sent from the device to the server, which uses a generative AI model and emotion engine to analyze the inquiry and generate an appropriate response, such as locking the account, resetting the password, or confirming the transaction.

[0343] Specific examples

[0344] 1. Anomaly detection example:

[0345] User A's usual area of ​​use is domestic, and a high-value transaction is made from overseas late at night.

[0346] The server's generated AI model analyzes the transaction data in real time and identifies these anomalous transactions.

[0347] The server sends a push notification to User A, informing him of the details of the abnormal transaction.

[0348] User A checks the notification and changes the account password to prevent unauthorized use.

[0349] 2. Example of how to respond to an inquiry:

[0350] User B becomes concerned about his recent transaction history and contacts support via a dedicated application.

[0351] The server receives the query and analyzes the content and user sentiment using a generative AI model and emotion engine.

[0352] It confirms that there are no abnormalities and automatically notifies User B of this information and that they can continue trading with confidence.

[0353] User B reads the response and is relieved of their concerns.

[0354] Prompt Sentence Examples

[0355] 1. Detecting abnormal patterns:

[0356] "Please create a program to detect abnormal patterns in user transaction history data. Anomalies include high-value transactions from locations significantly different from the usual area, or transactions late at night."

[0357] 2. Security inquiry analysis:

[0358] "Develop a program that uses generative AI models and an emotion engine to generate appropriate responses to user security inquiries. If the user's emotion is anxiety or anger, generate a response that also provides reassurance."

[0359] The above is an embodiment of the present invention, which makes it possible to detect anomalies in user transaction data in real time, to promptly notify the user, and to respond appropriately to user inquiries.

[0360] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0361] Step 1:

[0362] The server periodically retrieves the user's account information and transaction history data.

[0363] Input: User ID, transaction date and time, transaction amount, transaction location, etc.

[0364] Data processing: Normalize the acquired data and format it to be saved in the database.

[0365] Output: Save the formatted transaction data to the database.

[0366] Specific operation: The server retrieves transaction data through the API and stores it in a MySQL database using SQL queries.

[0367] Step 2:

[0368] Each time a user makes a payment, the terminal transmits the transaction data to the server in real time.

[0369] Input: User transaction data generated on the device.

[0370] Data processing: The transaction data is converted into JSON format and sent to the server using a secure communication method.

[0371] Output: Transaction data in JSON format as sent to the server.

[0372] Specific operation: When payment is completed, the terminal generates transaction data and sends a POST request to the server using HTTPS communication.

[0373] Step 3:

[0374] The server stores the received transaction data in a database.

[0375] Input: Transaction data sent from the terminal in JSON format.

[0376] Data processing: Parse JSON data and convert it into a format suitable for the database.

[0377] Output: Transaction data stored in a database.

[0378] Specific operation: The server parses the received transaction data and stores it in the database using a MySQL INSERT query.

[0379] Step 4:

[0380] The server uses generative AI models to analyze trading data in real time and detect anomalous patterns.

[0381] Input: Transaction data stored in the database.

[0382] Data computation: Based on the generative AI model, stored transaction data is input into anomaly detection algorithms to identify abnormal patterns.

[0383] Output: Details of the detected anomalous transactions (date, time, location, amount, etc.).

[0384] How it works: The server retrieves transaction data from the database, inputs it into the AI ​​model, and analyzes abnormal patterns in real time. The output of the AI ​​model is details of abnormal transactions.

[0385] Step 5:

[0386] If the server detects an abnormal pattern, it notifies the user.

[0387] Input: Transaction data that is determined to be anomalous.

[0388] Data processing: Generation of notification messages (including details of abnormal transactions).

[0389] Output: Notification to the user (push notification, text message, email, etc.).

[0390] Specific operation: The server generates a notification message based on the details of the abnormal transaction and calls an API to send the notification to the user's device.

[0391] Step 6:

[0392] The device receives the notification from the server and displays an alert to the user.

[0393] Input: The notification message sent by the server.

[0394] Data processing: Parsing notification messages.

[0395] Output: The alert that appears on the user's screen.

[0396] Specific operation: The device analyzes the received notification message and displays an alert through the user interface, allowing the user to receive the alert and respond appropriately.

[0397] Step 7:

[0398] If a user has a safety inquiry, the inquiry is sent from the device to the support desk.

[0399] Input: The query entered by the user.

[0400] Data processing: Creating and sending query messages.

[0401] Output: The query message sent to the server.

[0402] Specific operation: The terminal receives the user's input, generates a message to send it to the server, and sends it.

[0403] Step 8:

[0404] The server receives queries from users and analyzes them using generative AI models and emotion engines.

[0405] Input: The query message sent by the user.

[0406] Data calculation: Analyzing the query content and identifying user sentiment using an emotion engine.

[0407] Output: Analysis results and appropriate action plans.

[0408] Specific operation: The server inputs the received inquiry into the generative AI model and analyzes the inquiry content. At the same time, it uses the emotion engine to analyze the user's emotional state. As a result, it generates an appropriate response.

[0409] Step 9:

[0410] The server sends the generated response / solution to the user.

[0411] Input: Analysis results and countermeasures.

[0412] Data processing: Generating response messages (including content based on user sentiment).

[0413] Output: The response message sent to the user's terminal.

[0414] Specific operation: The server generates a response message based on the analysis results and countermeasures and sends it to the user's device.

[0415] Step 10:

[0416] The terminal displays the received response message to the user.

[0417] Input: The response message sent by the server.

[0418] Data processing: Parsing the response message.

[0419] Output: The response that is displayed on the user's screen.

[0420] Specific operation: The terminal analyzes the received response message and displays it through the user interface. The user reads the response and responds appropriately.

[0421] This allows us to detect anomalies in users' transaction data in real time, notify them quickly, and respond appropriately to user inquiries.

[0422] (Application example 2)

[0423] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0424] Conventional security systems lack the means to not only monitor user account information and payment history data, but also to perform real-time analysis to detect abnormal transactions and respond quickly and appropriately to user inquiries. Furthermore, they respond without taking user emotions into consideration, which leaves users unable to fully alleviate their anxiety and dissatisfaction. The present invention aims to solve these problems by maintaining a high level of security for user transactions while enabling detailed responses tailored to user emotions.

[0425] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring user account information and payment history data, means for analyzing the acquired payment history data in real time using a generative AI model to detect abnormal patterns, means for notifying the user when an abnormal pattern is detected, means for accepting security-related inquiries from users, analyzing the inquiries using a generative AI model, and taking appropriate measures, and means for analyzing user emotions using an emotion engine and generating responses based on the analysis results. This enables rapid detection and notification of abnormal transactions, as well as detailed responses tailored to user emotions.

[0426] "User Account Information" means information used to personally identify a User and related authentication data, including, but not limited to, User ID, password, and email address.

[0427] "Payment History Data" refers to information regarding the history of transactions made by a User, including transaction dates, transaction amounts, and transaction locations.

[0428] A "generative AI model" refers to an artificial intelligence model that is trained to analyze large amounts of data and detect specific patterns or anomalies.

[0429] "Real-time analytics" refers to the process of processing acquired data and generating results almost immediately.

[0430] "Abnormal Pattern" refers to a pattern of suspicious or fraudulent activity that differs from normal transactions.

[0431] "Emotion engine" refers to software or a system for recognizing a user's emotions through speech or text analysis.

[0432] "Security inquiries from users" refers to questions or inquiries sent by users to resolve their security-related doubts or concerns.

[0433] "Notification" means any action taken to warn or inform a User when an anomalous pattern is detected, including push notification, SMS, or email.

[0434] "Appropriate response" refers to actions taken in response to a user's inquiry to resolve the issue or provide reassurance, such as locking the account or resetting the password.

[0435] The system of the present invention acquires and analyzes user account information and payment history data in real time, and performs abnormal pattern detection and sentiment analysis to provide users with safe and reliable security. Detailed embodiments of the present invention will be described below.

[0436] System Overview

[0437] Data collection

[0438] The server periodically obtains the user's account information and payment history data, including the user ID, transaction date and time, transaction amount, transaction location, etc. In addition, the terminal (e.g., smartphone) sends the data to the server in real time every time the user makes a payment.

[0439] Real-time analysis of data

[0440] The server uses a generative AI model to analyze the acquired payment history data in real time and detect abnormal patterns. Specifically, it compares it with normal transaction patterns (e.g., trading time, trading location, transaction amount) to identify abnormal transactions. This allows the server to continuously monitor users' transaction patterns and immediately detect any abnormalities.

[0441] notification

[0442] If the server detects an abnormal pattern, it will immediately notify the user via push notification, SMS, or email. When the device receives the notification, it will display an alert to the user, urging them to take immediate action.

[0443] Inquiry response

[0444] When a user has a security question or wants to consult, they send an inquiry from their device to the support desk. The server analyzes the inquiry using the generative AI model and emotion engine and generates an appropriate response. Specific responses include locking the account, resetting the password, and confirming the transaction. The emotion engine then analyzes the user's emotions and generates a response that provides reassurance if the user is feeling anxious, for example.

[0445] Use of emotion engine

[0446] The emotion engine can recognize a user's emotions through voice or text analysis. When a user makes a text-based inquiry, it analyzes the text to identify emotions (e.g., anxiety, anger, relief, etc.) and generates an appropriate response. When a user makes a voice-based inquiry, it analyzes the tone of the voice and the phrasing to recognize emotions and reflect them in the response accordingly.

[0447] Specific examples

[0448] Anomaly detection example

[0449] 1. The area that User A normally uses is domestic.

[0450] 2. Large amounts of money are paid from overseas late at night.

[0451] 3. The server's generative AI model uses an anomaly detection algorithm to identify this anomalous transaction.

[0452] 4. The server sends a push notification to User A informing him of the abnormal transaction.

[0453] 5. User A checks the notification and changes their account password to prevent unauthorized use.

[0454] Examples of responding to inquiries

[0455] 1. User B becomes concerned about their recent transaction history and contacts support within the app.

[0456] 2. The server receives the query and analyzes the content and user sentiment using a generative AI model and emotion engine.

[0457] 3. If no abnormalities are found, User B is automatically notified of this information and informed that they can continue trading with confidence.

[0458] 4. User B reads the answer and resolves their concerns. If the emotion engine recognizes the user's concerns, it provides additional information or support to further reassure them.

[0459] Prompt Sentence Examples

[0460] 1. Enter the prompt: "I'm concerned about my recent transaction history. Is this transaction safe?"

[0461] 2. Emotion analysis result: "Anxiety"

[0462] 3. Produces response: "No anomalies detected. Enjoy your day."

[0463] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0464] Step 1: Data collection

[0465] The server periodically obtains the user's account information and payment history data, including the user ID, transaction date and time, transaction amount, and transaction location. In addition, the terminal (e.g., smartphone) sends the data to the server in real time every time the user makes a payment. The input is the user's payment event, and the output is the payment data stored on the server.

[0466] Step 2: Analyzing data in real time

[0467] The server uses a generative AI model to analyze the acquired payment history data in real time. Specifically, the payment history data is used as input and analyzed to detect anomalous patterns. The generative AI model compares it with normal transaction patterns (e.g., trading time, trading location, transaction amount) to identify anomalous transactions. The output is the detection result of anomalous transactions.

[0468] Step 3: Notification of abnormal transactions

[0469] If the server detects an abnormal pattern, it immediately notifies the user. Notification methods include push notification, SMS, and / or email. The input is the result of detecting an abnormal transaction, and the output is a notification sent to the user. The terminal receives the notification and performs specific operations such as displaying an alert to the user.

[0470] Step 4: Receiving an inquiry

[0471] When a user has a question or wants to consult about security, they send an inquiry from their terminal to the support desk. The user's inquiry is sent to the terminal as input, and the inquiry is sent to the server as output.

[0472] Step 5: Query analysis

[0473] The server uses a generative AI model and an emotion engine to analyze the inquiry and generate an appropriate response. Specifically, the generative AI model analyzes the inquiry using the user's inquiry text as input, and the emotion engine recognizes the user's emotion. The output is the user's emotion analysis results and a response.

[0474] Step 6: Response Generation

[0475] The server generates a response to the user based on the analysis results. For example, if it confirms that there are no abnormalities, it automatically notifies the user of that information and tells them that they can continue trading with peace of mind. The input includes the emotion analysis results and countermeasures, and the output is a response to the user.

[0476] Step 7: Notification of response

[0477] The server notifies the user of the generated response. Specifically, the response is sent to the device by at least one of push notification, SMS, and email. The input is the response to the user, and the output is the user receiving the response.

[0478] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0479] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0480] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0481] [Second embodiment]

[0482] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0483] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0484] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0485] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0486] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0487] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0488] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0489] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0490] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0491] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0492] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0493] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0494] The present invention is a system that acquires user account information and payment history data, analyzes it in real time using a generative AI model to detect abnormal patterns, and notifies users of the abnormalities. It also has the function of accepting security-related inquiries from users, analyzing the inquiries using a generative AI model, and responding appropriately.

[0495] System Overview

[0496] The server is responsible for collecting data from the user's smartphone device, detecting anomalies, sending notifications, and responding to inquiries, allowing users to safely and efficiently manage their accounts and payments.

[0497] What the program does

[0498] Data collection

[0499] The server periodically obtains user account information and payment history data, including user ID, transaction date and time, transaction amount, and transaction location. The terminal transmits the data to the server in real time every time the user makes a payment on their smartphone.

[0500] Real-time analysis of data

[0501] The server uses the generative AI model to analyze the acquired payment history data in real time and detect abnormal patterns. Specifically, it identifies abnormal transactions based on payment patterns (e.g., trading time, trading location, and transaction amount).

[0502] notification

[0503] If the server detects an abnormal pattern, it will immediately notify the user via push notification, SMS, email, etc. When the device receives the notification, it will display an alert to the user, helping them to take prompt action.

[0504] Inquiry response

[0505] When a user has a security question or wants to consult, they send an inquiry from their device to the support desk. The server then uses a generative AI model to analyze the inquiry and take appropriate action. Specific actions include locking the account, resetting the password, and confirming transactions.

[0506] Specific examples

[0507] Anomaly detection example

[0508] 1. The area that User A normally uses is assumed to be within Japan.

[0509] 2. A large payment is made from overseas late at night due to unauthorized access.

[0510] 3. The server's generative AI model uses an anomaly detection algorithm to identify this anomalous transaction.

[0511] 4. The server sends a push notification to User A informing him of the abnormal transaction.

[0512] 5. User A checks the notification and changes the account password to prevent unauthorized use.

[0513] Examples of responding to inquiries

[0514] 1. User B becomes concerned about their recent transaction history and contacts support within the app.

[0515] 2. The server receives the query and analyzes the content using a generative AI model.

[0516] 3. If no abnormalities are found, User B is automatically notified of this information and informed that he or she can continue trading with confidence.

[0517] 4. User B reads the answer and has his / her concerns resolved.

[0518] As described above, the system of the present invention effectively protects the security of smartphone payments for users and provides functions for rapid response. By using this system, users can create an environment in which they can use smartphone payments with peace of mind.

[0519] The processing flow will be explained below.

[0520] Step 1:

[0521] The terminal processes the user's payment and generates payment data (user ID, transaction date and time, transaction amount, transaction location, etc.).

[0522] Step 2:

[0523] The terminal transmits the generated payment data to the server in real time.

[0524] Step 3:

[0525] The server stores the received payment data in a database.

[0526] Step 4:

[0527] The server uses the generated AI model to analyze payment data in real time and detect abnormal patterns.

[0528] Step 5:

[0529] The generative AI model compares a user's past payment history and identifies anomalous patterns based on the time of day, location, and amount of the transaction.

[0530] Step 6:

[0531] If the server detects an abnormal pattern, it generates a message to notify the user of the anomaly detection result.

[0532] Step 7:

[0533] The server generates a notification message and sends it to the device via push notification, SMS, or email.

[0534] Step 8:

[0535] The device receives the notification message and displays an alert to the user.

[0536] Step 9:

[0537] The user checks the notification and takes appropriate action, such as changing the account password, if necessary.

[0538] Step 10:

[0539] If users have any security questions or concerns, they can submit an inquiry from within the app.

[0540] Step 11:

[0541] The server receives a query from the user and passes the query to the generative AI model.

[0542] Step 12:

[0543] The generative AI model analyzes the inquiry content and generates an appropriate response.

[0544] Step 13:

[0545] The server generates a reply message to the user based on the generated countermeasure and sends it to the terminal.

[0546] Step 14:

[0547] The device receives the reply message and displays it to the user.

[0548] Step 15:

[0549] Based on the information provided by the user, necessary measures are taken to resolve security issues.

[0550] Example 1

[0551] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0552] The conventional system had insufficient security measures for user account information and payment history data, making it difficult to detect fraudulent transactions early and respond appropriately. Notifications after anomalies were detected and responses to user inquiries were delayed, making it difficult to prevent fraudulent transactions. Furthermore, there was a lack of support for users to respond quickly when they received notifications.

[0553] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0554] In this invention, the server includes means for acquiring user account information and payment history data, means for analyzing the acquired payment history data in real time using a generative AI model to detect abnormal patterns, means for notifying the user when an abnormal pattern is detected, means for accepting security-related inquiries from users, analyzing the inquiries using the generative AI model, and taking appropriate action, and means for supporting users who receive notifications so that they can respond quickly. This enables early detection of abnormal payment patterns and immediate response, and supports users in responding quickly when they receive notifications.

[0555] "User account information" refers to data necessary for personal authentication of a user and information related to account management.

[0556] "Payment History Data" means data that includes detailed records of payments made by a User.

[0557] A "generative AI model" is an artificial intelligence model that has been trained using machine learning algorithms to automatically perform specific tasks.

[0558] "Real-time analysis" refers to processing and analyzing data as soon as it is generated.

[0559] An "anomalous pattern" is a pattern that indicates an abnormal transaction that deviates from normal transactions.

[0560] "Notifications" are messages or alerts intended to inform users of unusual transactions or security-related information.

[0561] "Security Inquiry" means a user's inquiry or consultation regarding a security issue or concern regarding the system or a transaction.

[0562] "Analysis" means examining data in detail to clarify its content and meaning.

[0563] "Appropriate response" means taking the most appropriate action to resolve the user's security issue based on the analysis results.

[0564] "Support" means providing advice and assistance necessary for users to use the system.

[0565] The present invention is a system that acquires and analyzes user account information and payment history data, detects abnormal transactions, and notifies users. It also includes a function that uses a generative AI model to respond appropriately to user security inquiries.

[0566] Hardware and software used

[0567] The server plays a central role in this system. Specifically, the following hardware and software are used:

[0568] Database management systems (e.g. MySQL, PostgreSQL)

[0569] Execution environment for generative AI models (e.g., TensorFlow, PyTorch)

[0570] Notification systems (e.g., Firebase Cloud Messaging, Twilio)

[0571] API server (e.g. Node.js, Django)

[0572] The device is the user's smartphone, which is compatible with both Android and iOS.

[0573] Specific operation of the system

[0574] The server periodically obtains the user's account information and payment history data. This includes information sent from the terminal using the API. For example, if a user makes a payment of 1,000 yen, the transaction data (user ID, transaction date and time, transaction amount, transaction location, etc.) is sent to the server in real time.

[0575] The server uses a generative AI model to analyze the acquired payment history data in real time and detect abnormal transaction patterns. The generative AI model takes into account the user's usual trading hours, trading locations, and transaction amounts. For example, if a user's account normally only trades domestically during the day, and a large overseas transaction is made late at night, the model will determine that this transaction is anomalous.

[0576] If an abnormal pattern is detected, the server immediately notifies the device. The user is notified of the abnormal transaction via push notification, SMS, or email. When the device receives the notification, an alert is displayed to the user. For example, if a user detects a fraudulent transaction overseas, the information is immediately sent to the user via push notification.

[0577] When a user makes a security inquiry, the app sends the inquiry to the support desk. The device then sends the inquiry to the server. The server uses a generative AI model to analyze the inquiry and determine the appropriate response. For example, if a user requests a password reset, the server guides the user through the procedure and notifies the user.

[0578] Specific examples

[0579] Anomaly detection example

[0580] 1. The area that User A normally uses is assumed to be within Japan.

[0581] 2. A large payment is made from overseas late at night due to unauthorized access.

[0582] 3. The server's generative AI model detects this anomalous transaction.

[0583] 4. The server immediately sends a push notification to User A informing him of the abnormal transaction.

[0584] 5. User A checks the notification and changes the account password to prevent unauthorized use.

[0585] Examples of responding to inquiries

[0586] 1. User B becomes concerned about their recent transaction history and contacts support within the app.

[0587] 2. The server receives the query and analyzes the content using a generative AI model.

[0588] 3. If no abnormalities are found, User B is automatically notified of this information and informed that he or she can continue trading with confidence.

[0589] 4. User B reads the answer and has his / her concerns resolved.

[0590] Example prompt sentence:

[0591] "I'm concerned about my recent transaction history. I'd like to contact support."

[0592] "There is a large amount of payment from overseas, please confirm."

[0593] The above is a specific embodiment for carrying out the present invention.

[0594] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0595] Step 1: Data collection

[0596] The server periodically obtains the user's account information and payment history data. Every time the terminal (smartphone) application makes a payment, it generates data such as the user ID, transaction date and time, transaction amount, and transaction location, and sends this data to the server in real time.

[0597] Input: Payment data generated when a user makes a payment on their smartphone

[0598] Data processing: The terminal sends the payment data to the server as an API request

[0599] Output: Payment data stored on the server

[0600] Step 2: Analyzing data in real time

[0601] The server uses a generative AI model to analyze the acquired payment history data in real time to detect abnormal transaction patterns. The generative AI model takes into account normal trading hours, trading locations, and transaction amounts to identify abnormal transactions.

[0602] Input: Payment data stored on the server

[0603] Data processing: Analyze data using generative AI models to detect anomalous patterns

[0604] Output: Alert data when abnormal transactions occur

[0605] Step 3: Notification of anomaly detection

[0606] If the server detects an abnormal pattern, it immediately notifies the device, informing the user of the details of the abnormal transaction using at least one of push notification, SMS, and email.

[0607] Input: Abnormal transaction alert data

[0608] Data processing: generating and sending notification messages

[0609] Output: A notification message that will be displayed on the user's terminal.

[0610] Step 4: User response

[0611] The user receives a notification, checks the alert, and takes appropriate action (e.g., change password) through the app if necessary.

[0612] Input: Notification message

[0613] Data processing: Check the notification content and take measures

[0614] Output: User response data sent to the server

[0615] Step 5: Handling inquiries

[0616] The user submits a security inquiry from the app. The device sends the inquiry to the server, which analyzes it using the generative AI model. An appropriate countermeasure is determined and notified to the user.

[0617] Input: User message

[0618] Data processing: Analyzing inquiries and determining responses using generative AI models

[0619] Output: The workaround message sent to the user's device

[0620] Specific behavior:

[0621] When User C makes a payment of 500 yen using his / her smartphone, the device sends the transaction data (user ID, transaction date and time, transaction amount, transaction location, etc.) to the server in real time (Step 1).

[0622] The server inputs the data into the generated AI model, analyzes transaction patterns in real time, and detects an anomaly, for example, if a large payment is made overseas late at night (Step 2).

[0623] The server sends a push notification to User C based on the abnormal transaction data, and the device receives the notification and displays an alert to the user (Step 3).

[0624] User C sees the alert, selects an action within the app, and sends a response to the server (step 4).

[0625] If User C has any questions or concerns, they can contact support through the app, and the device will send the inquiry to the server. The server will analyze the inquiry using the generated AI model and notify the user of the appropriate response (Step 5).

[0626] (Application example 1)

[0627] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0628] In recent years, the spread of electronic payments using smartphones has led to an increase in cybercrime attempts to fraudulently obtain users' payment information. However, current electronic payment systems are sometimes slow to detect and respond to payment anomalies, making it difficult to fully ensure user security. There is also a need for systems to respond quickly and appropriately to security-related inquiries from users. This has led to an urgent need to build a system that allows users to use electronic payments with peace of mind.

[0629] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0630] In this invention, the server includes means for acquiring user account information and payment history data, means for analyzing the acquired payment history data in real time using a generative AI model and detecting abnormal patterns, means for notifying the user when an abnormal pattern is detected, means for accepting security-related inquiries from users, analyzing the inquiries using a generative AI model, and taking appropriate measures, means for continuously monitoring user payment information, means for analyzing abnormal transactions in real time based on the monitored data, and means for immediately issuing an alert and encouraging further safety measures when an abnormal transaction occurs. This makes it possible to monitor user payment information in real time, quickly detect abnormal transactions, and take immediate countermeasures.

[0631] "Account information" refers to data including identification information and authentication information required when a user uses a service.

[0632] "Payment history data" refers to information about all transactions conducted by a user, specifically including transaction date and time, transaction amount, transaction location, transaction ID, etc.

[0633] A "generative AI model" is an artificial intelligence model designed to perform pattern recognition and anomaly detection using machine learning and deep learning.

[0634] "Means of real-time analysis" refers to technology that processes data instantly and provides analysis results instantly.

[0635] An "anomalous pattern" refers to an irregular transaction that deviates from normal transaction patterns and may indicate fraud or error.

[0636] "Notification methods" refer to communication methods used to notify users of abnormal transactions and important information, and specifically include push notifications, SMS, email, etc.

[0637] "Means for analyzing inquiries" refers to technology that automatically understands the content of inquiries from users and provides appropriate answers and countermeasures.

[0638] "Means for continuously monitoring payment information" refers to technology that constantly monitors users' transaction activities and detects suspicious transactions in real time.

[0639] "Means for analyzing abnormal transactions in real time based on monitoring data" refers to technology that instantly processes data acquired during monitoring and detects abnormal transactions.

[0640] "Means for issuing warnings" refers to technology that issues warnings to users when abnormal transactions are detected, encouraging them to take prompt action.

[0641] "Safety measures prompting" refers to technology that prompts users to take additional security measures when abnormal transactions or security threats are detected.

[0642] The present invention is a security system for maintaining the safety of users' electronic payments. A specific embodiment of this system is described below.

[0643] System Overview

[0644] The server plays a key role in collecting data from users' smartphones, detecting anomalies, sending notifications, and responding to inquiries, allowing users to safely and efficiently manage their accounts and payments.

[0645] Hardware / Software used

[0646] server

[0647] The server is responsible for collecting data, analyzing abnormal patterns in real time, sending notifications, and analyzing inquiries.

[0648] Install a generative AI model (e.g., Isolation Forest model) to perform anomaly detection.

[0649] Send notification emails using an SMTP server.

[0650] Terminal

[0651] When a user makes a transaction using their smartphone, the data is sent to the server.

[0652] Notify users via push notification, SMS, email, etc.

[0653] Program processing explanation

[0654] 1. Data Collection

[0655] The terminal sends payment data (user ID, transaction date and time, transaction amount, transaction location, etc.) to the server.

[0656] The server periodically retrieves this data and stores it in a database.

[0657] 2. Real-time analysis

[0658] The server analyzes the acquired payment history data in real time using a generative AI model (Isolation Forest model) and detects abnormal patterns.

[0659] Specifically, it identifies abnormal transactions based on trading time, trading location, and transaction amount.

[0660] 3. Notification

[0661] If the server detects an abnormal pattern, it will immediately notify the user.

[0662] Notification methods include push notification, SMS, and email.

[0663] The device receives these notifications and displays an alert to the user.

[0664] 4. Response to inquiries

[0665] When a user has a question or wants to consult about security, the user sends an inquiry from the terminal to the support desk.

[0666] The server uses a generative AI model to analyze the inquiry and take appropriate action, such as locking the account, resetting the password, or confirming the transaction.

[0667] Specific examples

[0668] Anomaly detection example

[0669] 1. The area that User A normally uses is assumed to be within Japan.

[0670] 2. A large payment is made from overseas late at night due to unauthorized access.

[0671] 3. The server's generative AI model uses an anomaly detection algorithm to identify this anomalous transaction.

[0672] 4. The server sends a push notification to User A informing him of the abnormal transaction.

[0673] 5. User A checks the notification and changes the account password to prevent unauthorized use.

[0674] Examples of responding to inquiries

[0675] 1. User B becomes concerned about their recent transaction history and contacts support within the app.

[0676] 2. The server receives the query and analyzes the content using a generative AI model.

[0677] 3. If no abnormalities are found, User B is automatically notified of this information and informed that he or she can continue trading with confidence.

[0678] 4. User B reads the answer and has his / her concerns resolved.

[0679] Prompt Sentence Examples

[0680] Determine whether the following transactions are unusual:

[0681] Transaction ID: 1234

[0682] Date: 2023-11-01

[0683] Price: 10,000 yen

[0684] Location: Tokyo

[0685] Analyze whether there is an abnormality based on the following items.

[0686] Trading Area

[0687] Trading Hours

[0688] Transaction amount

[0689] The above is a specific example of the embodiment of the present invention. By using this system, users can make electronic payments more safely.

[0690] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0691] Step 1:

[0692] Data collection

[0693] Each time a user makes an electronic payment, the terminal generates payment data, such as the user ID, transaction date and time, transaction amount, and transaction location. This data is sent in real time to the server, which stores the received data in a database and stores it for continuous monitoring.

[0694] Input: User payment data generated during electronic payment (user ID, transaction date and time, transaction amount, transaction location, etc.)

[0695] Output: Payment data records stored in a database

[0696] Step 2:

[0697] Real-time analytics

[0698] The server monitors the payment data stored in the database in real time and analyzes anomalous patterns using a generative AI model (Isolation Forest model), identifying anomalous transactions based on factors such as the time of day, place of transaction, and transaction amount.

[0699] Input: Records of payment data stored in the database

[0700] Output: Flags for abnormal transactions (transactions that are determined to be abnormal are flagged)

[0701] Step 3:

[0702] notification

[0703] If the server detects an abnormal transaction, it will immediately notify the user via push notification, SMS, email, etc. The device will receive the notification and display an alert to the user.

[0704] Input: Transaction data identified as abnormal by real-time analysis

[0705] Output: Notification to user (push notification, SMS, email)

[0706] Step 4:

[0707] Inquiry response

[0708] When a user makes a security inquiry, they send it to the support desk from their device. The server receives it and analyzes the inquiry using a generative AI model. Based on the analysis results, the server takes appropriate action. This can include locking the account, resetting the password, or confirming transactions.

[0709] Input: Security inquiry from user

[0710] Output: The server responds appropriately and notifies the user

[0711] Step 5:

[0712] Continuous monitoring

[0713] The server continuously monitors users' payment information and detects and responds to any abnormalities as necessary, thereby ensuring the safety of users' payment information at all times.

[0714] Input: New payment data collected automatically

[0715] Output: Real-time updated payment database and record of anomalous transactions

[0716] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0717] System Overview

[0718] The present invention is a system that acquires user account information and payment history data, detects abnormal patterns by combining a generative AI model and an emotion engine for real-time analysis, and notifies users of the abnormalities. It also has a function to accept security-related inquiries from users, analyze the content of the inquiry and the user's emotions using the generative AI model and the emotion engine, and respond appropriately.

[0719] What the program does

[0720] Data collection

[0721] The server periodically obtains the user's account information and payment history data, including the user ID, transaction date and time, transaction amount, transaction location, etc. The terminal transmits the data to the server in real time every time the user makes a payment on their smartphone.

[0722] Real-time analysis of data

[0723] The server uses the generative AI model to analyze the acquired payment history data in real time and detect abnormal patterns. Specifically, it identifies abnormal transactions based on payment patterns (e.g., trading time, trading location, and transaction amount).

[0724] notification

[0725] If the server detects an abnormal pattern, it will immediately notify the user via push notification, SMS, email, etc. When the device receives the notification, it will display an alert to the user, helping them to take prompt action.

[0726] Inquiry response

[0727] When a user has a question or inquiry about security, they send it to the support desk from their device. The server then analyzes the inquiry using a generative AI model and emotion engine, and generates an appropriate response. Specific responses include locking the account, resetting the password, and confirming transactions, and the response is based on the user's emotions analyzed by the emotion engine.

[0728] Use of emotion engine

[0729] The emotion engine can recognize a user's emotions through voice or text analysis. For example, if a user makes a text-based inquiry, the engine analyzes the text to identify emotions (anxiety, anger, relief, etc.) and generates an appropriate response. For voice-based inquiries, the engine analyzes the tone of the voice and the phrasing to recognize emotions and reflect them in the response.

[0730] Specific examples

[0731] Anomaly detection example

[0732] 1. The area that User A normally uses is assumed to be within Japan.

[0733] 2. A large payment is made from overseas late at night due to unauthorized access.

[0734] 3. The server's generative AI model uses an anomaly detection algorithm to identify this anomalous transaction.

[0735] 4. The server sends a push notification to User A informing him of the abnormal transaction.

[0736] 5. User A checks the notification and changes the account password to prevent unauthorized use.

[0737] Examples of responding to inquiries

[0738] 1. User B becomes concerned about their recent transaction history and contacts support within the app.

[0739] 2. The server receives the query and analyzes the content and user sentiment using a generative AI model and emotion engine.

[0740] 3. If no abnormalities are found, User B is automatically notified of this information and informed that he or she can continue trading with confidence.

[0741] 4. User B reads the answer and resolves their concerns. If the emotion engine recognizes the user's concerns, it provides additional information or support to further reassure them.

[0742] As described above, the system of the present invention provides a high level of security for smartphone payments and functions for quick and appropriate responses. In particular, by combining it with an emotion engine, it becomes possible to respond in a detailed manner according to the emotions of each individual user, greatly improving user satisfaction and peace of mind.

[0743] The processing flow will be explained below.

[0744] Step 1:

[0745] The terminal processes the user's payment and generates payment data (user ID, transaction date and time, transaction amount, transaction location, etc.).

[0746] Step 2:

[0747] The terminal transmits the generated payment data to the server in real time.

[0748] Step 3:

[0749] The server stores the received payment data in a database.

[0750] Step 4:

[0751] The server uses the generated AI model to analyze payment data in real time and detect abnormal patterns.

[0752] Step 5:

[0753] The generative AI model compares a user's past payment history and identifies anomalous patterns based on the time of day, location, and amount of the transaction.

[0754] Step 6:

[0755] If the server detects an abnormality, it generates a message to notify the user based on the results of the abnormality detection.

[0756] Step 7:

[0757] The server generates a notification message and sends it to the device via push notification, SMS, or email.

[0758] Step 8:

[0759] The device receives the notification message and displays an alert to the user.

[0760] Step 9:

[0761] The user checks the notification and takes appropriate action, such as changing the account password, if necessary.

[0762] Step 10:

[0763] If users have any security questions or concerns, they can submit an inquiry from within the app.

[0764] Step 11:

[0765] The server receives a query from the user and passes the query to the generative AI model.

[0766] Step 12:

[0767] The generative AI model analyzes the inquiry content and generates an appropriate response.

[0768] Step 13:

[0769] The emotion engine analyzes the content of the user's inquiry and recognizes the user's emotions (anxiety, anger, relief, etc.).

[0770] Step 14:

[0771] The server generates an optimal reply message for the user based on the generated countermeasure and the user's emotions recognized by the emotion engine, and sends it to the device.

[0772] Step 15:

[0773] The device receives the reply message and displays it to the user.

[0774] Step 16:

[0775] Based on the information provided by the user, necessary measures are taken to resolve security issues.

[0776] Example 2

[0777] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0778] Conventional systems had issues such as being unable to respond in real time when anomalies occurred in users' transaction history data, and difficulty in responding appropriately and quickly to safety-related inquiries from users. Furthermore, they were unable to respond in a way that took users' feelings into consideration, which led to a decline in user satisfaction and a sense of security. It was necessary to solve these issues.

[0779] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring user account information and transaction history data, means for analyzing the acquired transaction history data in real time using a generative AI model and detecting abnormal patterns, means for notifying the user when an abnormal pattern is detected, and means for accepting safety-related inquiries from users, analyzing the inquiry content using the generative AI model and an emotion engine, and providing an appropriate response. This makes it possible to detect abnormalities in user transaction data in real time and quickly notify the user, and to respond to user inquiries appropriately and in accordance with their emotions.

[0780] "Account Information" means information used to identify and authenticate a user, including user ID, password, contact information, etc.

[0781] "Transaction history data" refers to detailed information about transactions conducted by a user, including the transaction date and time, transaction amount, transaction location, and payment method.

[0782] A "generative AI model" is a model that uses artificial intelligence algorithms to analyze and process data to generate new insights and patterns.

[0783] "Real-time analysis" means processing and analyzing data immediately after it is generated or acquired.

[0784] An "abnormal pattern" is a transaction that significantly deviates from normal transaction patterns, such as a deviation from normal trading hours or locations, or a high value transaction.

[0785] "Notification" means a means of informing a User of anomaly detection or other important information, which may take the form of a push notification, text message, electronic message, etc.

[0786] A "security inquiry" is an inquiry made by a user to raise questions or concerns about the security of their account or unusual transactions.

[0787] The "emotion engine" is an algorithm that analyzes the user's emotional state (anxiety, anger, relief, etc.) from their text and voice, and generates countermeasures based on the results.

[0788] The present invention is a system that acquires user account information and transaction history data, analyzes them in real time using a generative AI model and an emotion engine to detect abnormal patterns, and notifies users of any abnormalities. It also has the function of accepting safety-related inquiries from users, analyzing them, and taking appropriate action.

[0789] System program generation

[0790] The system's program is built around the interaction between a server, a device, and a user. The server is responsible for the main data processing, while the device is responsible for receiving user input and notifications. These roles are realized by integrating a generative AI model and an emotion engine.

[0791] Hardware and software used

[0792] Server: Uses cloud computing services (e.g., AWS, Google Cloud) and uses a database management system (e.g., MySQL).

[0793] Terminal: A mobile device such as a smartphone or tablet is used, and a dedicated payment application is run on it.

[0794] Generative AI models: Use machine learning frameworks such as TensorFlow and PyTorch.

[0795] Emotion engine: Uses NLP libraries (e.g. spaCy, NLTK) and speech analysis tools (e.g. Google Speech-to-Text API).

[0796] What the program does

[0797] The server periodically retrieves user account information and transaction history data and analyzes it in real time using a generative AI model. The retrieved data is stored in a database. If an abnormal trading pattern is detected, the server will notify the user. Notification methods include push notifications, text messages, and electronic messages.

[0798] When a user makes a safety inquiry, the inquiry is sent from the device to the server, which uses a generative AI model and emotion engine to analyze the inquiry and generate an appropriate response, such as locking the account, resetting the password, or confirming the transaction.

[0799] Specific examples

[0800] 1. Anomaly detection example:

[0801] User A's usual area of ​​use is domestic, and a high-value transaction is made from overseas late at night.

[0802] The server's generated AI model analyzes the transaction data in real time and identifies these anomalous transactions.

[0803] The server sends a push notification to User A, informing him of the details of the abnormal transaction.

[0804] User A checks the notification and changes the account password to prevent unauthorized use.

[0805] 2. Example of how to respond to an inquiry:

[0806] User B becomes concerned about his recent transaction history and contacts support via a dedicated application.

[0807] The server receives the query and analyzes the content and user sentiment using a generative AI model and emotion engine.

[0808] It confirms that there are no abnormalities and automatically notifies User B of this information and that they can continue trading with confidence.

[0809] User B reads the response and is relieved of their concerns.

[0810] Prompt Sentence Examples

[0811] 1. Detecting abnormal patterns:

[0812] "Please create a program to detect abnormal patterns in user transaction history data. Anomalies include high-value transactions from locations significantly different from the usual area, or transactions late at night."

[0813] 2. Security inquiry analysis:

[0814] "Develop a program that uses generative AI models and an emotion engine to generate appropriate responses to user security inquiries. If the user's emotion is anxiety or anger, generate a response that also provides reassurance."

[0815] The above is an embodiment of the present invention, which makes it possible to detect anomalies in user transaction data in real time, to promptly notify the user, and to respond appropriately to user inquiries.

[0816] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0817] Step 1:

[0818] The server periodically retrieves the user's account information and transaction history data.

[0819] Input: User ID, transaction date and time, transaction amount, transaction location, etc.

[0820] Data processing: Normalize the acquired data and format it to be saved in the database.

[0821] Output: Save the formatted transaction data to the database.

[0822] Specific operation: The server retrieves transaction data through the API and stores it in a MySQL database using SQL queries.

[0823] Step 2:

[0824] Each time a user makes a payment, the terminal transmits the transaction data to the server in real time.

[0825] Input: User transaction data generated on the device.

[0826] Data processing: The transaction data is converted into JSON format and sent to the server using a secure communication method.

[0827] Output: Transaction data in JSON format as sent to the server.

[0828] Specific operation: When payment is completed, the terminal generates transaction data and sends a POST request to the server using HTTPS communication.

[0829] Step 3:

[0830] The server stores the received transaction data in a database.

[0831] Input: Transaction data sent from the terminal in JSON format.

[0832] Data processing: Parse JSON data and convert it into a format suitable for the database.

[0833] Output: Transaction data stored in a database.

[0834] Specific operation: The server parses the received transaction data and stores it in the database using a MySQL INSERT query.

[0835] Step 4:

[0836] The server uses generative AI models to analyze trading data in real time and detect anomalous patterns.

[0837] Input: Transaction data stored in the database.

[0838] Data computation: Based on the generative AI model, stored transaction data is input into anomaly detection algorithms to identify abnormal patterns.

[0839] Output: Details of the detected anomalous transactions (date, time, location, amount, etc.).

[0840] How it works: The server retrieves transaction data from the database, inputs it into the AI ​​model, and analyzes abnormal patterns in real time. The output of the AI ​​model is details of abnormal transactions.

[0841] Step 5:

[0842] If the server detects an abnormal pattern, it notifies the user.

[0843] Input: Transaction data that is determined to be anomalous.

[0844] Data processing: Generation of notification messages (including details of abnormal transactions).

[0845] Output: Notification to the user (push notification, text message, email, etc.).

[0846] Specific operation: The server generates a notification message based on the details of the abnormal transaction and calls an API to send the notification to the user's device.

[0847] Step 6:

[0848] The device receives the notification from the server and displays an alert to the user.

[0849] Input: The notification message sent by the server.

[0850] Data processing: Parsing notification messages.

[0851] Output: The alert that appears on the user's screen.

[0852] Specific operation: The device analyzes the received notification message and displays an alert through the user interface, allowing the user to receive the alert and respond appropriately.

[0853] Step 7:

[0854] If a user has a safety inquiry, the inquiry is sent from the device to the support desk.

[0855] Input: The query entered by the user.

[0856] Data processing: Creating and sending query messages.

[0857] Output: The query message sent to the server.

[0858] Specific operation: The terminal receives the user's input, generates a message to send it to the server, and sends it.

[0859] Step 8:

[0860] The server receives queries from users and analyzes them using generative AI models and emotion engines.

[0861] Input: The query message sent by the user.

[0862] Data calculation: Analyzing the query content and identifying user sentiment using an emotion engine.

[0863] Output: Analysis results and appropriate action plans.

[0864] Specific operation: The server inputs the received inquiry into the generative AI model and analyzes the inquiry content. At the same time, it uses the emotion engine to analyze the user's emotional state. As a result, it generates an appropriate response.

[0865] Step 9:

[0866] The server sends the generated response / solution to the user.

[0867] Input: Analysis results and countermeasures.

[0868] Data processing: Generating response messages (including content based on user sentiment).

[0869] Output: The response message sent to the user's terminal.

[0870] Specific operation: The server generates a response message based on the analysis results and countermeasures and sends it to the user's device.

[0871] Step 10:

[0872] The terminal displays the received response message to the user.

[0873] Input: The response message sent by the server.

[0874] Data processing: Parsing the response message.

[0875] Output: The response that is displayed on the user's screen.

[0876] Specific operation: The terminal analyzes the received response message and displays it through the user interface. The user reads the response and responds appropriately.

[0877] This allows us to detect anomalies in users' transaction data in real time, notify them quickly, and respond appropriately to user inquiries.

[0878] (Application example 2)

[0879] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0880] Conventional security systems lack the means to not only monitor user account information and payment history data, but also to perform real-time analysis to detect abnormal transactions and respond quickly and appropriately to user inquiries. Furthermore, they respond without taking user emotions into consideration, which leaves users unable to fully alleviate their anxiety and dissatisfaction. The present invention aims to solve these problems by maintaining a high level of security for user transactions while enabling detailed responses tailored to user emotions.

[0881] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring user account information and payment history data, means for analyzing the acquired payment history data in real time using a generative AI model to detect abnormal patterns, means for notifying the user when an abnormal pattern is detected, means for accepting security-related inquiries from users, analyzing the inquiries using a generative AI model, and taking appropriate measures, and means for analyzing user emotions using an emotion engine and generating responses based on the analysis results. This enables rapid detection and notification of abnormal transactions, as well as detailed responses tailored to user emotions.

[0882] "User Account Information" means information used to personally identify a User and related authentication data, including, but not limited to, User ID, password, and email address.

[0883] "Payment History Data" refers to information regarding the history of transactions made by a User, including transaction dates, transaction amounts, and transaction locations.

[0884] A "generative AI model" refers to an artificial intelligence model that is trained to analyze large amounts of data and detect specific patterns or anomalies.

[0885] "Real-time analytics" refers to the process of processing acquired data and generating results almost immediately.

[0886] "Abnormal Pattern" refers to a pattern of suspicious or fraudulent activity that differs from normal transactions.

[0887] "Emotion engine" refers to software or a system for recognizing a user's emotions through speech or text analysis.

[0888] "Security inquiries from users" refers to questions or inquiries sent by users to resolve their security-related doubts or concerns.

[0889] "Notification" means any action taken to warn or inform a User when an anomalous pattern is detected, including push notification, SMS, or email.

[0890] "Appropriate response" refers to actions taken in response to a user's inquiry to resolve the issue or provide reassurance, such as locking the account or resetting the password.

[0891] The system of the present invention acquires and analyzes user account information and payment history data in real time, and performs abnormal pattern detection and sentiment analysis to provide users with safe and reliable security. Detailed embodiments of the present invention will be described below.

[0892] System Overview

[0893] Data collection

[0894] The server periodically obtains the user's account information and payment history data, including the user ID, transaction date and time, transaction amount, transaction location, etc. In addition, the terminal (e.g., smartphone) sends the data to the server in real time every time the user makes a payment.

[0895] Real-time analysis of data

[0896] The server uses a generative AI model to analyze the acquired payment history data in real time and detect abnormal patterns. Specifically, it compares it with normal transaction patterns (e.g., trading time, trading location, transaction amount) to identify abnormal transactions. This allows the server to continuously monitor users' transaction patterns and immediately detect any abnormalities.

[0897] notification

[0898] If the server detects an abnormal pattern, it will immediately notify the user via push notification, SMS, or email. When the device receives the notification, it will display an alert to the user, urging them to take immediate action.

[0899] Inquiry response

[0900] When a user has a security question or wants to consult, they send an inquiry from their device to the support desk. The server analyzes the inquiry using the generative AI model and emotion engine and generates an appropriate response. Specific responses include locking the account, resetting the password, and confirming the transaction. The emotion engine then analyzes the user's emotions and generates a response that provides reassurance if the user is feeling anxious, for example.

[0901] Use of emotion engine

[0902] The emotion engine can recognize a user's emotions through voice or text analysis. When a user makes a text-based inquiry, it analyzes the text to identify emotions (e.g., anxiety, anger, relief, etc.) and generates an appropriate response. When a user makes a voice-based inquiry, it analyzes the tone of the voice and the phrasing to recognize emotions and reflect them in the response accordingly.

[0903] Specific examples

[0904] Anomaly detection example

[0905] 1. The area that User A normally uses is domestic.

[0906] 2. Large amounts of money are paid from overseas late at night.

[0907] 3. The server's generative AI model uses an anomaly detection algorithm to identify this anomalous transaction.

[0908] 4. The server sends a push notification to User A informing him of the abnormal transaction.

[0909] 5. User A checks the notification and changes their account password to prevent unauthorized use.

[0910] Examples of responding to inquiries

[0911] 1. User B becomes concerned about their recent transaction history and contacts support within the app.

[0912] 2. The server receives the query and analyzes the content and user sentiment using a generative AI model and emotion engine.

[0913] 3. If no abnormalities are found, User B is automatically notified of this information and informed that they can continue trading with confidence.

[0914] 4. User B reads the answer and resolves their concerns. If the emotion engine recognizes the user's concerns, it provides additional information or support to further reassure them.

[0915] Prompt Sentence Examples

[0916] 1. Enter the prompt: "I'm concerned about my recent transaction history. Is this transaction safe?"

[0917] 2. Emotion analysis result: "Anxiety"

[0918] 3. Produces response: "No anomalies detected. Enjoy your day."

[0919] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0920] Step 1: Data collection

[0921] The server periodically obtains the user's account information and payment history data, including the user ID, transaction date and time, transaction amount, and transaction location. In addition, the terminal (e.g., smartphone) sends the data to the server in real time every time the user makes a payment. The input is the user's payment event, and the output is the payment data stored on the server.

[0922] Step 2: Analyzing data in real time

[0923] The server uses a generative AI model to analyze the acquired payment history data in real time. Specifically, the payment history data is used as input and analyzed to detect anomalous patterns. The generative AI model compares it with normal transaction patterns (e.g., trading time, trading location, transaction amount) to identify anomalous transactions. The output is the detection result of anomalous transactions.

[0924] Step 3: Notification of abnormal transactions

[0925] If the server detects an abnormal pattern, it immediately notifies the user. Notification methods include push notification, SMS, and / or email. The input is the result of detecting an abnormal transaction, and the output is a notification sent to the user. The terminal receives the notification and performs specific operations such as displaying an alert to the user.

[0926] Step 4: Receiving an inquiry

[0927] When a user has a question or wants to consult about security, they send an inquiry from their terminal to the support desk. The user's inquiry is sent to the terminal as input, and the inquiry is sent to the server as output.

[0928] Step 5: Query analysis

[0929] The server uses a generative AI model and an emotion engine to analyze the inquiry and generate an appropriate response. Specifically, the generative AI model analyzes the inquiry using the user's inquiry text as input, and the emotion engine recognizes the user's emotion. The output is the user's emotion analysis results and a response.

[0930] Step 6: Response Generation

[0931] The server generates a response to the user based on the analysis results. For example, if it confirms that there are no abnormalities, it automatically notifies the user of that information and tells them that they can continue trading with peace of mind. The input includes the emotion analysis results and countermeasures, and the output is a response to the user.

[0932] Step 7: Notification of response

[0933] The server notifies the user of the generated response. Specifically, the response is sent to the device by at least one of push notification, SMS, and email. The input is the response to the user, and the output is the user receiving the response.

[0934] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0935] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0936] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0937] [Third embodiment]

[0938] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0939] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0940] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0941] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0942] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0943] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0944] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0945] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0946] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0947] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0948] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0949] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0950] The present invention is a system that acquires user account information and payment history data, analyzes it in real time using a generative AI model to detect abnormal patterns, and notifies users of the abnormalities. It also has the function of accepting security-related inquiries from users, analyzing the inquiries using a generative AI model, and responding appropriately.

[0951] System Overview

[0952] The server is responsible for collecting data from the user's smartphone device, detecting anomalies, sending notifications, and responding to inquiries, allowing users to safely and efficiently manage their accounts and payments.

[0953] What the program does

[0954] Data collection

[0955] The server periodically obtains user account information and payment history data, including user ID, transaction date and time, transaction amount, and transaction location. The terminal transmits the data to the server in real time every time the user makes a payment on their smartphone.

[0956] Real-time analysis of data

[0957] The server uses the generative AI model to analyze the acquired payment history data in real time and detect abnormal patterns. Specifically, it identifies abnormal transactions based on payment patterns (e.g., trading time, trading location, and transaction amount).

[0958] notification

[0959] If the server detects an abnormal pattern, it will immediately notify the user via push notification, SMS, email, etc. When the device receives the notification, it will display an alert to the user, helping them to take prompt action.

[0960] Inquiry response

[0961] When a user has a security question or wants to consult, they send an inquiry from their device to the support desk. The server then uses a generative AI model to analyze the inquiry and take appropriate action. Specific actions include locking the account, resetting the password, and confirming transactions.

[0962] Specific examples

[0963] Anomaly detection example

[0964] 1. The area that User A normally uses is assumed to be within Japan.

[0965] 2. A large payment is made from overseas late at night due to unauthorized access.

[0966] 3. The server's generative AI model uses an anomaly detection algorithm to identify this anomalous transaction.

[0967] 4. The server sends a push notification to User A informing him of the abnormal transaction.

[0968] 5. User A checks the notification and changes the account password to prevent unauthorized use.

[0969] Examples of responding to inquiries

[0970] 1. User B becomes concerned about their recent transaction history and contacts support within the app.

[0971] 2. The server receives the query and analyzes the content using a generative AI model.

[0972] 3. If no abnormalities are found, User B is automatically notified of this information and informed that he or she can continue trading with confidence.

[0973] 4. User B reads the answer and has his / her concerns resolved.

[0974] As described above, the system of the present invention effectively protects the security of smartphone payments for users and provides functions for rapid response. By using this system, users can create an environment in which they can use smartphone payments with peace of mind.

[0975] The processing flow will be explained below.

[0976] Step 1:

[0977] The terminal processes the user's payment and generates payment data (user ID, transaction date and time, transaction amount, transaction location, etc.).

[0978] Step 2:

[0979] The terminal transmits the generated payment data to the server in real time.

[0980] Step 3:

[0981] The server stores the received payment data in a database.

[0982] Step 4:

[0983] The server uses the generated AI model to analyze payment data in real time and detect abnormal patterns.

[0984] Step 5:

[0985] The generative AI model compares a user's past payment history and identifies anomalous patterns based on the time of day, location, and amount of the transaction.

[0986] Step 6:

[0987] If the server detects an abnormal pattern, it generates a message to notify the user of the anomaly detection result.

[0988] Step 7:

[0989] The server generates a notification message and sends it to the device via push notification, SMS, or email.

[0990] Step 8:

[0991] The device receives the notification message and displays an alert to the user.

[0992] Step 9:

[0993] The user checks the notification and takes appropriate action, such as changing the account password, if necessary.

[0994] Step 10:

[0995] If users have any security questions or concerns, they can submit an inquiry from within the app.

[0996] Step 11:

[0997] The server receives a query from the user and passes the query to the generative AI model.

[0998] Step 12:

[0999] The generative AI model analyzes the inquiry content and generates an appropriate response.

[1000] Step 13:

[1001] The server generates a reply message to the user based on the generated countermeasure and sends it to the terminal.

[1002] Step 14:

[1003] The device receives the reply message and displays it to the user.

[1004] Step 15:

[1005] Based on the information provided by the user, necessary measures are taken to resolve security issues.

[1006] Example 1

[1007] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1008] The conventional system had insufficient security measures for user account information and payment history data, making it difficult to detect fraudulent transactions early and respond appropriately. Notifications after anomalies were detected and responses to user inquiries were delayed, making it difficult to prevent fraudulent transactions. Furthermore, there was a lack of support for users to respond quickly when they received notifications.

[1009] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1010] In this invention, the server includes means for acquiring user account information and payment history data, means for analyzing the acquired payment history data in real time using a generative AI model to detect abnormal patterns, means for notifying the user when an abnormal pattern is detected, means for accepting security-related inquiries from users, analyzing the inquiries using the generative AI model, and taking appropriate action, and means for supporting users who receive notifications so that they can respond quickly. This enables early detection of abnormal payment patterns and immediate response, and supports users in responding quickly when they receive notifications.

[1011] "User account information" refers to data necessary for personal authentication of a user and information related to account management.

[1012] "Payment History Data" means data that includes detailed records of payments made by a User.

[1013] A "generative AI model" is an artificial intelligence model that has been trained using machine learning algorithms to automatically perform specific tasks.

[1014] "Real-time analysis" refers to processing and analyzing data as soon as it is generated.

[1015] An "anomalous pattern" is a pattern that indicates an abnormal transaction that deviates from normal transactions.

[1016] "Notifications" are messages or alerts intended to inform users of unusual transactions or security-related information.

[1017] "Security Inquiry" means a user's inquiry or consultation regarding a security issue or concern regarding the system or a transaction.

[1018] "Analysis" means examining data in detail to clarify its content and meaning.

[1019] "Appropriate response" means taking the most appropriate action to resolve the user's security issue based on the analysis results.

[1020] "Support" means providing advice and assistance necessary for users to use the system.

[1021] The present invention is a system that acquires and analyzes user account information and payment history data, detects abnormal transactions, and notifies users. It also includes a function that uses a generative AI model to respond appropriately to user security inquiries.

[1022] Hardware and software used

[1023] The server plays a central role in this system. Specifically, the following hardware and software are used:

[1024] Database management systems (e.g. MySQL, PostgreSQL)

[1025] Execution environment for generative AI models (e.g., TensorFlow, PyTorch)

[1026] Notification systems (e.g., Firebase Cloud Messaging, Twilio)

[1027] API server (e.g. Node.js, Django)

[1028] The device is the user's smartphone, which is compatible with both Android and iOS.

[1029] Specific operation of the system

[1030] The server periodically obtains the user's account information and payment history data. This includes information sent from the terminal using the API. For example, if a user makes a payment of 1,000 yen, the transaction data (user ID, transaction date and time, transaction amount, transaction location, etc.) is sent to the server in real time.

[1031] The server uses a generative AI model to analyze the acquired payment history data in real time and detect abnormal transaction patterns. The generative AI model takes into account the user's usual trading hours, trading locations, and transaction amounts. For example, if a user's account normally only trades domestically during the day, and a large overseas transaction is made late at night, the model will determine that this transaction is anomalous.

[1032] If an abnormal pattern is detected, the server immediately notifies the device. The user is notified of the abnormal transaction via push notification, SMS, or email. When the device receives the notification, an alert is displayed to the user. For example, if a user detects a fraudulent transaction overseas, the information is immediately sent to the user via push notification.

[1033] When a user makes a security inquiry, the app sends the inquiry to the support desk. The device then sends the inquiry to the server. The server uses a generative AI model to analyze the inquiry and determine the appropriate response. For example, if a user requests a password reset, the server guides the user through the procedure and notifies the user.

[1034] Specific examples

[1035] Anomaly detection example

[1036] 1. The area that User A normally uses is assumed to be within Japan.

[1037] 2. A large payment is made from overseas late at night due to unauthorized access.

[1038] 3. The server's generative AI model detects this anomalous transaction.

[1039] 4. The server immediately sends a push notification to User A informing him of the abnormal transaction.

[1040] 5. User A checks the notification and changes the account password to prevent unauthorized use.

[1041] Examples of responding to inquiries

[1042] 1. User B becomes concerned about their recent transaction history and contacts support within the app.

[1043] 2. The server receives the query and analyzes the content using a generative AI model.

[1044] 3. If no abnormalities are found, User B is automatically notified of this information and informed that he or she can continue trading with confidence.

[1045] 4. User B reads the answer and has his / her concerns resolved.

[1046] Example prompt sentence:

[1047] "I'm concerned about my recent transaction history. I'd like to contact support."

[1048] "There is a large amount of payment from overseas, please confirm."

[1049] The above is a specific embodiment for carrying out the present invention.

[1050] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1051] Step 1: Data collection

[1052] The server periodically obtains the user's account information and payment history data. Every time the terminal (smartphone) application makes a payment, it generates data such as the user ID, transaction date and time, transaction amount, and transaction location, and sends this data to the server in real time.

[1053] Input: Payment data generated when a user makes a payment on their smartphone

[1054] Data processing: The terminal sends the payment data to the server as an API request

[1055] Output: Payment data stored on the server

[1056] Step 2: Analyzing data in real time

[1057] The server uses a generative AI model to analyze the acquired payment history data in real time to detect abnormal transaction patterns. The generative AI model takes into account normal trading hours, trading locations, and transaction amounts to identify abnormal transactions.

[1058] Input: Payment data stored on the server

[1059] Data processing: Analyze data using generative AI models to detect anomalous patterns

[1060] Output: Alert data when abnormal transactions occur

[1061] Step 3: Notification of anomaly detection

[1062] If the server detects an abnormal pattern, it immediately notifies the device, informing the user of the details of the abnormal transaction using at least one of push notification, SMS, and email.

[1063] Input: Abnormal transaction alert data

[1064] Data processing: generating and sending notification messages

[1065] Output: A notification message that will be displayed on the user's terminal.

[1066] Step 4: User response

[1067] The user receives a notification, checks the alert, and takes appropriate action (e.g., change password) through the app if necessary.

[1068] Input: Notification message

[1069] Data processing: Check the notification content and take measures

[1070] Output: User response data sent to the server

[1071] Step 5: Handling inquiries

[1072] The user submits a security inquiry from the app. The device sends the inquiry to the server, which analyzes it using the generative AI model. An appropriate countermeasure is determined and notified to the user.

[1073] Input: User message

[1074] Data processing: Analyzing inquiries and determining responses using generative AI models

[1075] Output: The workaround message sent to the user's device

[1076] Specific behavior:

[1077] When User C makes a payment of 500 yen using his / her smartphone, the device sends the transaction data (user ID, transaction date and time, transaction amount, transaction location, etc.) to the server in real time (Step 1).

[1078] The server inputs the data into the generated AI model, analyzes transaction patterns in real time, and detects an anomaly, for example, if a large payment is made overseas late at night (Step 2).

[1079] The server sends a push notification to User C based on the abnormal transaction data, and the device receives the notification and displays an alert to the user (Step 3).

[1080] User C sees the alert, selects an action within the app, and sends a response to the server (step 4).

[1081] If User C has any questions or concerns, they can contact support through the app, and the device will send the inquiry to the server. The server will analyze the inquiry using the generated AI model and notify the user of the appropriate response (Step 5).

[1082] (Application example 1)

[1083] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1084] In recent years, the spread of electronic payments using smartphones has led to an increase in cybercrime attempts to fraudulently obtain users' payment information. However, current electronic payment systems are sometimes slow to detect and respond to payment anomalies, making it difficult to fully ensure user security. There is also a need for systems to respond quickly and appropriately to security-related inquiries from users. This has led to an urgent need to build a system that allows users to use electronic payments with peace of mind.

[1085] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1086] In this invention, the server includes means for acquiring user account information and payment history data, means for analyzing the acquired payment history data in real time using a generative AI model and detecting abnormal patterns, means for notifying the user when an abnormal pattern is detected, means for accepting security-related inquiries from users, analyzing the inquiries using a generative AI model, and taking appropriate measures, means for continuously monitoring user payment information, means for analyzing abnormal transactions in real time based on the monitored data, and means for immediately issuing an alert and encouraging further safety measures when an abnormal transaction occurs. This makes it possible to monitor user payment information in real time, quickly detect abnormal transactions, and take immediate countermeasures.

[1087] "Account information" refers to data including identification information and authentication information required when a user uses a service.

[1088] "Payment history data" refers to information about all transactions conducted by a user, specifically including transaction date and time, transaction amount, transaction location, transaction ID, etc.

[1089] A "generative AI model" is an artificial intelligence model designed to perform pattern recognition and anomaly detection using machine learning and deep learning.

[1090] "Means of real-time analysis" refers to technology that processes data instantly and provides analysis results instantly.

[1091] An "anomalous pattern" refers to an irregular transaction that deviates from normal transaction patterns and may indicate fraud or error.

[1092] "Notification methods" refer to communication methods used to notify users of abnormal transactions and important information, and specifically include push notifications, SMS, email, etc.

[1093] "Means for analyzing inquiries" refers to technology that automatically understands the content of inquiries from users and provides appropriate answers and countermeasures.

[1094] "Means for continuously monitoring payment information" refers to technology that constantly monitors users' transaction activities and detects suspicious transactions in real time.

[1095] "Means for analyzing abnormal transactions in real time based on monitoring data" refers to technology that instantly processes data acquired during monitoring and detects abnormal transactions.

[1096] "Means for issuing warnings" refers to technology that issues warnings to users when abnormal transactions are detected, encouraging them to take prompt action.

[1097] "Safety measures prompting" refers to technology that prompts users to take additional security measures when abnormal transactions or security threats are detected.

[1098] The present invention is a security system for maintaining the safety of users' electronic payments. A specific embodiment of this system is described below.

[1099] System Overview

[1100] The server plays a key role in collecting data from users' smartphones, detecting anomalies, sending notifications, and responding to inquiries, allowing users to safely and efficiently manage their accounts and payments.

[1101] Hardware / Software used

[1102] server

[1103] The server is responsible for collecting data, analyzing abnormal patterns in real time, sending notifications, and analyzing inquiries.

[1104] Install a generative AI model (e.g., Isolation Forest model) to perform anomaly detection.

[1105] Send notification emails using an SMTP server.

[1106] Terminal

[1107] When a user makes a transaction using their smartphone, the data is sent to the server.

[1108] Notify users via push notification, SMS, email, etc.

[1109] Program processing explanation

[1110] 1. Data Collection

[1111] The terminal sends payment data (user ID, transaction date and time, transaction amount, transaction location, etc.) to the server.

[1112] The server periodically retrieves this data and stores it in a database.

[1113] 2. Real-time analysis

[1114] The server analyzes the acquired payment history data in real time using a generative AI model (Isolation Forest model) and detects abnormal patterns.

[1115] Specifically, it identifies abnormal transactions based on trading time, trading location, and transaction amount.

[1116] 3. Notification

[1117] If the server detects an abnormal pattern, it will immediately notify the user.

[1118] Notification methods include push notification, SMS, and email.

[1119] The device receives these notifications and displays an alert to the user.

[1120] 4. Response to inquiries

[1121] When a user has a question or wants to consult about security, the user sends an inquiry from the terminal to the support desk.

[1122] The server uses a generative AI model to analyze the inquiry and take appropriate action, such as locking the account, resetting the password, or confirming the transaction.

[1123] Specific examples

[1124] Anomaly detection example

[1125] 1. The area that User A normally uses is assumed to be within Japan.

[1126] 2. A large payment is made from overseas late at night due to unauthorized access.

[1127] 3. The server's generative AI model uses an anomaly detection algorithm to identify this anomalous transaction.

[1128] 4. The server sends a push notification to User A informing him of the abnormal transaction.

[1129] 5. User A checks the notification and changes the account password to prevent unauthorized use.

[1130] Examples of responding to inquiries

[1131] 1. User B becomes concerned about their recent transaction history and contacts support within the app.

[1132] 2. The server receives the query and analyzes the content using a generative AI model.

[1133] 3. If no abnormalities are found, User B is automatically notified of this information and informed that he or she can continue trading with confidence.

[1134] 4. User B reads the answer and has his / her concerns resolved.

[1135] Prompt Sentence Examples

[1136] Determine whether the following transactions are unusual:

[1137] Transaction ID: 1234

[1138] Date: 2023-11-01

[1139] Price: 10,000 yen

[1140] Location: Tokyo

[1141] Analyze whether there is an abnormality based on the following items.

[1142] Trading Area

[1143] Trading Hours

[1144] Transaction amount

[1145] The above is a specific example of the embodiment of the present invention. By using this system, users can make electronic payments more safely.

[1146] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1147] Step 1:

[1148] Data collection

[1149] Each time a user makes an electronic payment, the terminal generates payment data, such as the user ID, transaction date and time, transaction amount, and transaction location. This data is sent in real time to the server, which stores the received data in a database and stores it for continuous monitoring.

[1150] Input: User payment data generated during electronic payment (user ID, transaction date and time, transaction amount, transaction location, etc.)

[1151] Output: Payment data records stored in a database

[1152] Step 2:

[1153] Real-time analytics

[1154] The server monitors the payment data stored in the database in real time and analyzes anomalous patterns using a generative AI model (Isolation Forest model), identifying anomalous transactions based on factors such as the time of day, place of transaction, and transaction amount.

[1155] Input: Records of payment data stored in the database

[1156] Output: Flags for abnormal transactions (transactions that are determined to be abnormal are flagged)

[1157] Step 3:

[1158] notification

[1159] If the server detects an abnormal transaction, it will immediately notify the user via push notification, SMS, email, etc. The device will receive the notification and display an alert to the user.

[1160] Input: Transaction data identified as abnormal by real-time analysis

[1161] Output: Notification to user (push notification, SMS, email)

[1162] Step 4:

[1163] Inquiry response

[1164] When a user makes a security inquiry, they send it to the support desk from their device. The server receives it and analyzes the inquiry using a generative AI model. Based on the analysis results, the server takes appropriate action. This can include locking the account, resetting the password, or confirming transactions.

[1165] Input: Security inquiry from user

[1166] Output: The server responds appropriately and notifies the user

[1167] Step 5:

[1168] Continuous monitoring

[1169] The server continuously monitors users' payment information and detects and responds to any abnormalities as necessary, thereby ensuring the safety of users' payment information at all times.

[1170] Input: New payment data collected automatically

[1171] Output: Real-time updated payment database and record of anomalous transactions

[1172] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1173] System Overview

[1174] The present invention is a system that acquires user account information and payment history data, detects abnormal patterns by combining a generative AI model and an emotion engine for real-time analysis, and notifies users of the abnormalities. It also has a function to accept security-related inquiries from users, analyze the content of the inquiry and the user's emotions using the generative AI model and the emotion engine, and respond appropriately.

[1175] What the program does

[1176] Data collection

[1177] The server periodically obtains the user's account information and payment history data, including the user ID, transaction date and time, transaction amount, transaction location, etc. The terminal transmits the data to the server in real time every time the user makes a payment on their smartphone.

[1178] Real-time analysis of data

[1179] The server uses the generative AI model to analyze the acquired payment history data in real time and detect abnormal patterns. Specifically, it identifies abnormal transactions based on payment patterns (e.g., trading time, trading location, and transaction amount).

[1180] notification

[1181] If the server detects an abnormal pattern, it will immediately notify the user via push notification, SMS, email, etc. When the device receives the notification, it will display an alert to the user, helping them to take prompt action.

[1182] Inquiry response

[1183] When a user has a question or inquiry about security, they send it to the support desk from their device. The server then analyzes the inquiry using a generative AI model and emotion engine, and generates an appropriate response. Specific responses include locking the account, resetting the password, and confirming transactions, and the response is based on the user's emotions analyzed by the emotion engine.

[1184] Use of emotion engine

[1185] The emotion engine can recognize a user's emotions through voice or text analysis. For example, if a user makes a text-based inquiry, the engine analyzes the text to identify emotions (anxiety, anger, relief, etc.) and generates an appropriate response. For voice-based inquiries, the engine analyzes the tone of the voice and the phrasing to recognize emotions and reflect them in the response.

[1186] Specific examples

[1187] Anomaly detection example

[1188] 1. The area that User A normally uses is assumed to be within Japan.

[1189] 2. A large payment is made from overseas late at night due to unauthorized access.

[1190] 3. The server's generative AI model uses an anomaly detection algorithm to identify this anomalous transaction.

[1191] 4. The server sends a push notification to User A informing him of the abnormal transaction.

[1192] 5. User A checks the notification and changes the account password to prevent unauthorized use.

[1193] Examples of responding to inquiries

[1194] 1. User B becomes concerned about their recent transaction history and contacts support within the app.

[1195] 2. The server receives the query and analyzes the content and user sentiment using a generative AI model and emotion engine.

[1196] 3. If no abnormalities are found, User B is automatically notified of this information and informed that he or she can continue trading with confidence.

[1197] 4. User B reads the answer and resolves their concerns. If the emotion engine recognizes the user's concerns, it provides additional information or support to further reassure them.

[1198] As described above, the system of the present invention provides a high level of security for smartphone payments and functions for quick and appropriate responses. In particular, by combining it with an emotion engine, it becomes possible to respond in a detailed manner according to the emotions of each individual user, greatly improving user satisfaction and peace of mind.

[1199] The processing flow will be explained below.

[1200] Step 1:

[1201] The terminal processes the user's payment and generates payment data (user ID, transaction date and time, transaction amount, transaction location, etc.).

[1202] Step 2:

[1203] The terminal transmits the generated payment data to the server in real time.

[1204] Step 3:

[1205] The server stores the received payment data in a database.

[1206] Step 4:

[1207] The server uses the generated AI model to analyze payment data in real time and detect abnormal patterns.

[1208] Step 5:

[1209] The generative AI model compares a user's past payment history and identifies anomalous patterns based on the time of day, location, and amount of the transaction.

[1210] Step 6:

[1211] If the server detects an abnormality, it generates a message to notify the user based on the results of the abnormality detection.

[1212] Step 7:

[1213] The server generates a notification message and sends it to the device via push notification, SMS, or email.

[1214] Step 8:

[1215] The device receives the notification message and displays an alert to the user.

[1216] Step 9:

[1217] The user checks the notification and takes appropriate action, such as changing the account password, if necessary.

[1218] Step 10:

[1219] If users have any security questions or concerns, they can submit an inquiry from within the app.

[1220] Step 11:

[1221] The server receives a query from the user and passes the query to the generative AI model.

[1222] Step 12:

[1223] The generative AI model analyzes the inquiry content and generates an appropriate response.

[1224] Step 13:

[1225] The emotion engine analyzes the content of the user's inquiry and recognizes the user's emotions (anxiety, anger, relief, etc.).

[1226] Step 14:

[1227] The server generates an optimal reply message for the user based on the generated countermeasure and the user's emotions recognized by the emotion engine, and sends it to the device.

[1228] Step 15:

[1229] The device receives the reply message and displays it to the user.

[1230] Step 16:

[1231] Based on the information provided by the user, necessary measures are taken to resolve security issues.

[1232] Example 2

[1233] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1234] Conventional systems had issues such as being unable to respond in real time when anomalies occurred in users' transaction history data, and difficulty in responding appropriately and quickly to safety-related inquiries from users. Furthermore, they were unable to respond in a way that took users' feelings into consideration, which led to a decline in user satisfaction and a sense of security. It was necessary to solve these issues.

[1235] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring user account information and transaction history data, means for analyzing the acquired transaction history data in real time using a generative AI model and detecting abnormal patterns, means for notifying the user when an abnormal pattern is detected, and means for accepting safety-related inquiries from users, analyzing the inquiry content using the generative AI model and an emotion engine, and providing an appropriate response. This makes it possible to detect abnormalities in user transaction data in real time and quickly notify the user, and to respond to user inquiries appropriately and in accordance with their emotions.

[1236] "Account Information" means information used to identify and authenticate a user, including user ID, password, contact information, etc.

[1237] "Transaction history data" refers to detailed information about transactions conducted by a user, including the transaction date and time, transaction amount, transaction location, and payment method.

[1238] A "generative AI model" is a model that uses artificial intelligence algorithms to analyze and process data to generate new insights and patterns.

[1239] "Real-time analysis" means processing and analyzing data immediately after it is generated or acquired.

[1240] An "abnormal pattern" is a transaction that significantly deviates from normal transaction patterns, such as a deviation from normal trading hours or locations, or a high value transaction.

[1241] "Notification" means a means of informing a User of anomaly detection or other important information, which may take the form of a push notification, text message, electronic message, etc.

[1242] A "security inquiry" is an inquiry made by a user to raise questions or concerns about the security of their account or unusual transactions.

[1243] The "emotion engine" is an algorithm that analyzes the user's emotional state (anxiety, anger, relief, etc.) from their text and voice, and generates countermeasures based on the results.

[1244] The present invention is a system that acquires user account information and transaction history data, analyzes them in real time using a generative AI model and an emotion engine to detect abnormal patterns, and notifies users of any abnormalities. It also has the function of accepting safety-related inquiries from users, analyzing them, and taking appropriate action.

[1245] System program generation

[1246] The system's program is built around the interaction between a server, a device, and a user. The server is responsible for the main data processing, while the device is responsible for receiving user input and notifications. These roles are realized by integrating a generative AI model and an emotion engine.

[1247] Hardware and software used

[1248] Server: Uses cloud computing services (e.g., AWS, Google Cloud) and uses a database management system (e.g., MySQL).

[1249] Terminal: A mobile device such as a smartphone or tablet is used, and a dedicated payment application is run on it.

[1250] Generative AI models: Use machine learning frameworks such as TensorFlow and PyTorch.

[1251] Emotion engine: Uses NLP libraries (e.g. spaCy, NLTK) and speech analysis tools (e.g. Google Speech-to-Text API).

[1252] What the program does

[1253] The server periodically retrieves user account information and transaction history data and analyzes it in real time using a generative AI model. The retrieved data is stored in a database. If an abnormal trading pattern is detected, the server will notify the user. Notification methods include push notifications, text messages, and electronic messages.

[1254] When a user makes a safety inquiry, the inquiry is sent from the device to the server, which uses a generative AI model and emotion engine to analyze the inquiry and generate an appropriate response, such as locking the account, resetting the password, or confirming the transaction.

[1255] Specific examples

[1256] 1. Anomaly detection example:

[1257] User A's usual area of ​​use is domestic, and a high-value transaction is made from overseas late at night.

[1258] The server's generated AI model analyzes the transaction data in real time and identifies these anomalous transactions.

[1259] The server sends a push notification to User A, informing him of the details of the abnormal transaction.

[1260] User A checks the notification and changes the account password to prevent unauthorized use.

[1261] 2. Example of how to respond to an inquiry:

[1262] User B becomes concerned about his recent transaction history and contacts support via a dedicated application.

[1263] The server receives the query and analyzes the content and user sentiment using a generative AI model and emotion engine.

[1264] It confirms that there are no abnormalities and automatically notifies User B of this information and that they can continue trading with confidence.

[1265] User B reads the response and is relieved of their concerns.

[1266] Prompt Sentence Examples

[1267] 1. Detecting abnormal patterns:

[1268] "Please create a program to detect abnormal patterns in user transaction history data. Anomalies include high-value transactions from locations significantly different from the usual area, or transactions late at night."

[1269] 2. Security inquiry analysis:

[1270] "Develop a program that uses generative AI models and an emotion engine to generate appropriate responses to user security inquiries. If the user's emotion is anxiety or anger, generate a response that also provides reassurance."

[1271] The above is an embodiment of the present invention, which makes it possible to detect anomalies in user transaction data in real time, to promptly notify the user, and to respond appropriately to user inquiries.

[1272] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1273] Step 1:

[1274] The server periodically retrieves the user's account information and transaction history data.

[1275] Input: User ID, transaction date and time, transaction amount, transaction location, etc.

[1276] Data processing: Normalize the acquired data and format it to be saved in the database.

[1277] Output: Save the formatted transaction data to the database.

[1278] Specific operation: The server retrieves transaction data through the API and stores it in a MySQL database using SQL queries.

[1279] Step 2:

[1280] Each time a user makes a payment, the terminal transmits the transaction data to the server in real time.

[1281] Input: User transaction data generated on the device.

[1282] Data processing: The transaction data is converted into JSON format and sent to the server using a secure communication method.

[1283] Output: Transaction data in JSON format as sent to the server.

[1284] Specific operation: When payment is completed, the terminal generates transaction data and sends a POST request to the server using HTTPS communication.

[1285] Step 3:

[1286] The server stores the received transaction data in a database.

[1287] Input: Transaction data sent from the terminal in JSON format.

[1288] Data processing: Parse JSON data and convert it into a format suitable for the database.

[1289] Output: Transaction data stored in a database.

[1290] Specific operation: The server parses the received transaction data and stores it in the database using a MySQL INSERT query.

[1291] Step 4:

[1292] The server uses generative AI models to analyze trading data in real time and detect anomalous patterns.

[1293] Input: Transaction data stored in the database.

[1294] Data computation: Based on the generative AI model, stored transaction data is input into anomaly detection algorithms to identify abnormal patterns.

[1295] Output: Details of the detected anomalous transactions (date, time, location, amount, etc.).

[1296] How it works: The server retrieves transaction data from the database, inputs it into the AI ​​model, and analyzes abnormal patterns in real time. The output of the AI ​​model is details of abnormal transactions.

[1297] Step 5:

[1298] If the server detects an abnormal pattern, it notifies the user.

[1299] Input: Transaction data that is determined to be anomalous.

[1300] Data processing: Generation of notification messages (including details of abnormal transactions).

[1301] Output: Notification to the user (push notification, text message, email, etc.).

[1302] Specific operation: The server generates a notification message based on the details of the abnormal transaction and calls an API to send the notification to the user's device.

[1303] Step 6:

[1304] The device receives the notification from the server and displays an alert to the user.

[1305] Input: The notification message sent by the server.

[1306] Data processing: Parsing notification messages.

[1307] Output: The alert that appears on the user's screen.

[1308] Specific operation: The device analyzes the received notification message and displays an alert through the user interface, allowing the user to receive the alert and respond appropriately.

[1309] Step 7:

[1310] If a user has a safety inquiry, the inquiry is sent from the device to the support desk.

[1311] Input: The query entered by the user.

[1312] Data processing: Creating and sending query messages.

[1313] Output: The query message sent to the server.

[1314] Specific operation: The terminal receives the user's input, generates a message to send it to the server, and sends it.

[1315] Step 8:

[1316] The server receives queries from users and analyzes them using generative AI models and emotion engines.

[1317] Input: The query message sent by the user.

[1318] Data calculation: Analyzing the query content and identifying user sentiment using an emotion engine.

[1319] Output: Analysis results and appropriate action plans.

[1320] Specific operation: The server inputs the received inquiry into the generative AI model and analyzes the inquiry content. At the same time, it uses the emotion engine to analyze the user's emotional state. As a result, it generates an appropriate response.

[1321] Step 9:

[1322] The server sends the generated response / solution to the user.

[1323] Input: Analysis results and countermeasures.

[1324] Data processing: Generating response messages (including content based on user sentiment).

[1325] Output: The response message sent to the user's terminal.

[1326] Specific operation: The server generates a response message based on the analysis results and countermeasures and sends it to the user's device.

[1327] Step 10:

[1328] The terminal displays the received response message to the user.

[1329] Input: The response message sent by the server.

[1330] Data processing: Parsing the response message.

[1331] Output: The response that is displayed on the user's screen.

[1332] Specific operation: The terminal analyzes the received response message and displays it through the user interface. The user reads the response and responds appropriately.

[1333] This allows us to detect anomalies in users' transaction data in real time, notify them quickly, and respond appropriately to user inquiries.

[1334] (Application example 2)

[1335] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1336] Conventional security systems lack the means to not only monitor user account information and payment history data, but also to perform real-time analysis to detect abnormal transactions and respond quickly and appropriately to user inquiries. Furthermore, they respond without taking user emotions into consideration, which leaves users unable to fully alleviate their anxiety and dissatisfaction. The present invention aims to solve these problems by maintaining a high level of security for user transactions while enabling detailed responses tailored to user emotions.

[1337] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring user account information and payment history data, means for analyzing the acquired payment history data in real time using a generative AI model to detect abnormal patterns, means for notifying the user when an abnormal pattern is detected, means for accepting security-related inquiries from users, analyzing the inquiries using a generative AI model, and taking appropriate measures, and means for analyzing user emotions using an emotion engine and generating responses based on the analysis results. This enables rapid detection and notification of abnormal transactions, as well as detailed responses tailored to user emotions.

[1338] "User Account Information" means information used to personally identify a User and related authentication data, including, but not limited to, User ID, password, and email address.

[1339] "Payment History Data" refers to information regarding the history of transactions made by a User, including transaction dates, transaction amounts, and transaction locations.

[1340] A "generative AI model" refers to an artificial intelligence model that is trained to analyze large amounts of data and detect specific patterns or anomalies.

[1341] "Real-time analytics" refers to the process of processing acquired data and generating results almost immediately.

[1342] "Abnormal Pattern" refers to a pattern of suspicious or fraudulent activity that differs from normal transactions.

[1343] "Emotion engine" refers to software or a system for recognizing a user's emotions through speech or text analysis.

[1344] "Security inquiries from users" refers to questions or inquiries sent by users to resolve their security-related doubts or concerns.

[1345] "Notification" means any action taken to warn or inform a User when an anomalous pattern is detected, including push notification, SMS, or email.

[1346] "Appropriate response" refers to actions taken in response to a user's inquiry to resolve the issue or provide reassurance, such as locking the account or resetting the password.

[1347] The system of the present invention acquires and analyzes user account information and payment history data in real time, and performs abnormal pattern detection and sentiment analysis to provide users with safe and reliable security. Detailed embodiments of the present invention will be described below.

[1348] System Overview

[1349] Data collection

[1350] The server periodically obtains the user's account information and payment history data, including the user ID, transaction date and time, transaction amount, transaction location, etc. In addition, the terminal (e.g., smartphone) sends the data to the server in real time every time the user makes a payment.

[1351] Real-time analysis of data

[1352] The server uses a generative AI model to analyze the acquired payment history data in real time and detect abnormal patterns. Specifically, it compares it with normal transaction patterns (e.g., trading time, trading location, transaction amount) to identify abnormal transactions. This allows the server to continuously monitor users' transaction patterns and immediately detect any abnormalities.

[1353] notification

[1354] If the server detects an abnormal pattern, it will immediately notify the user via push notification, SMS, or email. When the device receives the notification, it will display an alert to the user, urging them to take immediate action.

[1355] Inquiry response

[1356] When a user has a security question or wants to consult, they send an inquiry from their device to the support desk. The server analyzes the inquiry using the generative AI model and emotion engine and generates an appropriate response. Specific responses include locking the account, resetting the password, and confirming the transaction. The emotion engine then analyzes the user's emotions and generates a response that provides reassurance if the user is feeling anxious, for example.

[1357] Use of emotion engine

[1358] The emotion engine can recognize a user's emotions through voice or text analysis. When a user makes a text-based inquiry, it analyzes the text to identify emotions (e.g., anxiety, anger, relief, etc.) and generates an appropriate response. When a user makes a voice-based inquiry, it analyzes the tone of the voice and the phrasing to recognize emotions and reflect them in the response accordingly.

[1359] Specific examples

[1360] Anomaly detection example

[1361] 1. The area that User A normally uses is domestic.

[1362] 2. Large amounts of money are paid from overseas late at night.

[1363] 3. The server's generative AI model uses an anomaly detection algorithm to identify this anomalous transaction.

[1364] 4. The server sends a push notification to User A informing him of the abnormal transaction.

[1365] 5. User A checks the notification and changes their account password to prevent unauthorized use.

[1366] Examples of responding to inquiries

[1367] 1. User B becomes concerned about their recent transaction history and contacts support within the app.

[1368] 2. The server receives the query and analyzes the content and user sentiment using a generative AI model and emotion engine.

[1369] 3. If no abnormalities are found, User B is automatically notified of this information and informed that they can continue trading with confidence.

[1370] 4. User B reads the answer and resolves their concerns. If the emotion engine recognizes the user's concerns, it provides additional information or support to further reassure them.

[1371] Prompt Sentence Examples

[1372] 1. Enter the prompt: "I'm concerned about my recent transaction history. Is this transaction safe?"

[1373] 2. Emotion analysis result: "Anxiety"

[1374] 3. Produces response: "No anomalies detected. Enjoy your day."

[1375] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1376] Step 1: Data collection

[1377] The server periodically obtains the user's account information and payment history data, including the user ID, transaction date and time, transaction amount, and transaction location. In addition, the terminal (e.g., smartphone) sends the data to the server in real time every time the user makes a payment. The input is the user's payment event, and the output is the payment data stored on the server.

[1378] Step 2: Analyzing data in real time

[1379] The server uses a generative AI model to analyze the acquired payment history data in real time. Specifically, the payment history data is used as input and analyzed to detect anomalous patterns. The generative AI model compares it with normal transaction patterns (e.g., trading time, trading location, transaction amount) to identify anomalous transactions. The output is the detection result of anomalous transactions.

[1380] Step 3: Notification of abnormal transactions

[1381] If the server detects an abnormal pattern, it immediately notifies the user. Notification methods include push notification, SMS, and / or email. The input is the result of detecting an abnormal transaction, and the output is a notification sent to the user. The terminal receives the notification and performs specific operations such as displaying an alert to the user.

[1382] Step 4: Receiving an inquiry

[1383] When a user has a question or wants to consult about security, they send an inquiry from their terminal to the support desk. The user's inquiry is sent to the terminal as input, and the inquiry is sent to the server as output.

[1384] Step 5: Query analysis

[1385] The server uses a generative AI model and an emotion engine to analyze the inquiry and generate an appropriate response. Specifically, the generative AI model analyzes the inquiry using the user's inquiry text as input, and the emotion engine recognizes the user's emotion. The output is the user's emotion analysis results and a response.

[1386] Step 6: Response Generation

[1387] The server generates a response to the user based on the analysis results. For example, if it confirms that there are no abnormalities, it automatically notifies the user of that information and tells them that they can continue trading with peace of mind. The input includes the emotion analysis results and countermeasures, and the output is a response to the user.

[1388] Step 7: Notification of response

[1389] The server notifies the user of the generated response. Specifically, the response is sent to the device by at least one of push notification, SMS, and email. The input is the response to the user, and the output is the user receiving the response.

[1390] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1391] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1392] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1393] [Fourth embodiment]

[1394] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1395] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1396] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1397] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1398] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1399] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1400] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1401] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1402] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1403] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1404] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1405] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1406] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1407] The present invention is a system that acquires user account information and payment history data, analyzes it in real time using a generative AI model to detect abnormal patterns, and notifies users of the abnormalities. It also has the function of accepting security-related inquiries from users, analyzing the inquiries using a generative AI model, and responding appropriately.

[1408] System Overview

[1409] The server is responsible for collecting data from the user's smartphone device, detecting anomalies, sending notifications, and responding to inquiries, allowing users to safely and efficiently manage their accounts and payments.

[1410] What the program does

[1411] Data collection

[1412] The server periodically obtains user account information and payment history data, including user ID, transaction date and time, transaction amount, and transaction location. The terminal transmits the data to the server in real time every time the user makes a payment on their smartphone.

[1413] Real-time analysis of data

[1414] The server uses the generative AI model to analyze the acquired payment history data in real time and detect abnormal patterns. Specifically, it identifies abnormal transactions based on payment patterns (e.g., trading time, trading location, and transaction amount).

[1415] notification

[1416] If the server detects an abnormal pattern, it will immediately notify the user via push notification, SMS, email, etc. When the device receives the notification, it will display an alert to the user, helping them to take prompt action.

[1417] Inquiry response

[1418] When a user has a security question or wants to consult, they send an inquiry from their device to the support desk. The server then uses a generative AI model to analyze the inquiry and take appropriate action. Specific actions include locking the account, resetting the password, and confirming transactions.

[1419] Specific examples

[1420] Anomaly detection example

[1421] 1. The area that User A normally uses is assumed to be within Japan.

[1422] 2. A large payment is made from overseas late at night due to unauthorized access.

[1423] 3. The server's generative AI model uses an anomaly detection algorithm to identify this anomalous transaction.

[1424] 4. The server sends a push notification to User A informing him of the abnormal transaction.

[1425] 5. User A checks the notification and changes the account password to prevent unauthorized use.

[1426] Examples of responding to inquiries

[1427] 1. User B becomes concerned about their recent transaction history and contacts support within the app.

[1428] 2. The server receives the query and analyzes the content using a generative AI model.

[1429] 3. If no abnormalities are found, User B is automatically notified of this information and informed that he or she can continue trading with confidence.

[1430] 4. User B reads the answer and has his / her concerns resolved.

[1431] As described above, the system of the present invention effectively protects the security of smartphone payments for users and provides functions for rapid response. By using this system, users can create an environment in which they can use smartphone payments with peace of mind.

[1432] The processing flow will be explained below.

[1433] Step 1:

[1434] The terminal processes the user's payment and generates payment data (user ID, transaction date and time, transaction amount, transaction location, etc.).

[1435] Step 2:

[1436] The terminal transmits the generated payment data to the server in real time.

[1437] Step 3:

[1438] The server stores the received payment data in a database.

[1439] Step 4:

[1440] The server uses the generated AI model to analyze payment data in real time and detect abnormal patterns.

[1441] Step 5:

[1442] The generative AI model compares a user's past payment history and identifies anomalous patterns based on the time of day, location, and amount of the transaction.

[1443] Step 6:

[1444] If the server detects an abnormal pattern, it generates a message to notify the user of the anomaly detection result.

[1445] Step 7:

[1446] The server generates a notification message and sends it to the device via push notification, SMS, or email.

[1447] Step 8:

[1448] The device receives the notification message and displays an alert to the user.

[1449] Step 9:

[1450] The user checks the notification and takes appropriate action, such as changing the account password, if necessary.

[1451] Step 10:

[1452] If users have any security questions or concerns, they can submit an inquiry from within the app.

[1453] Step 11:

[1454] The server receives a query from the user and passes the query to the generative AI model.

[1455] Step 12:

[1456] The generative AI model analyzes the inquiry content and generates an appropriate response.

[1457] Step 13:

[1458] The server generates a reply message to the user based on the generated countermeasure and sends it to the terminal.

[1459] Step 14:

[1460] The device receives the reply message and displays it to the user.

[1461] Step 15:

[1462] Based on the information provided by the user, necessary measures are taken to resolve security issues.

[1463] Example 1

[1464] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1465] The conventional system had insufficient security measures for user account information and payment history data, making it difficult to detect fraudulent transactions early and respond appropriately. Notifications after anomalies were detected and responses to user inquiries were delayed, making it difficult to prevent fraudulent transactions. Furthermore, there was a lack of support for users to respond quickly when they received notifications.

[1466] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1467] In this invention, the server includes means for acquiring user account information and payment history data, means for analyzing the acquired payment history data in real time using a generative AI model to detect abnormal patterns, means for notifying the user when an abnormal pattern is detected, means for accepting security-related inquiries from users, analyzing the inquiries using the generative AI model, and taking appropriate action, and means for supporting users who receive notifications so that they can respond quickly. This enables early detection of abnormal payment patterns and immediate response, and supports users in responding quickly when they receive notifications.

[1468] "User account information" refers to data necessary for personal authentication of a user and information related to account management.

[1469] "Payment History Data" means data that includes detailed records of payments made by a User.

[1470] A "generative AI model" is an artificial intelligence model that has been trained using machine learning algorithms to automatically perform specific tasks.

[1471] "Real-time analysis" refers to processing and analyzing data as soon as it is generated.

[1472] An "anomalous pattern" is a pattern that indicates an abnormal transaction that deviates from normal transactions.

[1473] "Notifications" are messages or alerts intended to inform users of unusual transactions or security-related information.

[1474] "Security Inquiry" means a user's inquiry or consultation regarding a security issue or concern regarding the system or a transaction.

[1475] "Analysis" means examining data in detail to clarify its content and meaning.

[1476] "Appropriate response" means taking the most appropriate action to resolve the user's security issue based on the analysis results.

[1477] "Support" means providing advice and assistance necessary for users to use the system.

[1478] The present invention is a system that acquires and analyzes user account information and payment history data, detects abnormal transactions, and notifies users. It also includes a function that uses a generative AI model to respond appropriately to user security inquiries.

[1479] Hardware and software used

[1480] The server plays a central role in this system. Specifically, the following hardware and software are used:

[1481] Database management systems (e.g. MySQL, PostgreSQL)

[1482] Execution environment for generative AI models (e.g., TensorFlow, PyTorch)

[1483] Notification systems (e.g., Firebase Cloud Messaging, Twilio)

[1484] API server (e.g. Node.js, Django)

[1485] The device is the user's smartphone, which is compatible with both Android and iOS.

[1486] Specific operation of the system

[1487] The server periodically obtains the user's account information and payment history data. This includes information sent from the terminal using the API. For example, if a user makes a payment of 1,000 yen, the transaction data (user ID, transaction date and time, transaction amount, transaction location, etc.) is sent to the server in real time.

[1488] The server uses a generative AI model to analyze the acquired payment history data in real time and detect abnormal transaction patterns. The generative AI model takes into account the user's usual trading hours, trading locations, and transaction amounts. For example, if a user's account normally only trades domestically during the day, and a large overseas transaction is made late at night, the model will determine that this transaction is anomalous.

[1489] If an abnormal pattern is detected, the server immediately notifies the device. The user is notified of the abnormal transaction via push notification, SMS, or email. When the device receives the notification, an alert is displayed to the user. For example, if a user detects a fraudulent transaction overseas, the information is immediately sent to the user via push notification.

[1490] When a user makes a security inquiry, the app sends the inquiry to the support desk. The device then sends the inquiry to the server. The server uses a generative AI model to analyze the inquiry and determine the appropriate response. For example, if a user requests a password reset, the server guides the user through the procedure and notifies the user.

[1491] Specific examples

[1492] Anomaly detection example

[1493] 1. The area that User A normally uses is assumed to be within Japan.

[1494] 2. A large payment is made from overseas late at night due to unauthorized access.

[1495] 3. The server's generative AI model detects this anomalous transaction.

[1496] 4. The server immediately sends a push notification to User A informing him of the abnormal transaction.

[1497] 5. User A checks the notification and changes the account password to prevent unauthorized use.

[1498] Examples of responding to inquiries

[1499] 1. User B becomes concerned about their recent transaction history and contacts support within the app.

[1500] 2. The server receives the query and analyzes the content using a generative AI model.

[1501] 3. If no abnormalities are found, User B is automatically notified of this information and informed that he or she can continue trading with confidence.

[1502] 4. User B reads the answer and has his / her concerns resolved.

[1503] Example prompt sentence:

[1504] "I'm concerned about my recent transaction history. I'd like to contact support."

[1505] "There is a large amount of payment from overseas, please confirm."

[1506] The above is a specific embodiment for carrying out the present invention.

[1507] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1508] Step 1: Data collection

[1509] The server periodically obtains the user's account information and payment history data. Every time the terminal (smartphone) application makes a payment, it generates data such as the user ID, transaction date and time, transaction amount, and transaction location, and sends this data to the server in real time.

[1510] Input: Payment data generated when a user makes a payment on their smartphone

[1511] Data processing: The terminal sends the payment data to the server as an API request

[1512] Output: Payment data stored on the server

[1513] Step 2: Analyzing data in real time

[1514] The server uses a generative AI model to analyze the acquired payment history data in real time to detect abnormal transaction patterns. The generative AI model takes into account normal trading hours, trading locations, and transaction amounts to identify abnormal transactions.

[1515] Input: Payment data stored on the server

[1516] Data processing: Analyze data using generative AI models to detect anomalous patterns

[1517] Output: Alert data when abnormal transactions occur

[1518] Step 3: Notification of anomaly detection

[1519] If the server detects an abnormal pattern, it immediately notifies the device, informing the user of the details of the abnormal transaction using at least one of push notification, SMS, and email.

[1520] Input: Abnormal transaction alert data

[1521] Data processing: generating and sending notification messages

[1522] Output: A notification message that will be displayed on the user's terminal.

[1523] Step 4: User response

[1524] The user receives a notification, checks the alert, and takes appropriate action (e.g., change password) through the app if necessary.

[1525] Input: Notification message

[1526] Data processing: Check the notification content and take measures

[1527] Output: User response data sent to the server

[1528] Step 5: Handling inquiries

[1529] The user submits a security inquiry from the app. The device sends the inquiry to the server, which analyzes it using the generative AI model. An appropriate countermeasure is determined and notified to the user.

[1530] Input: User message

[1531] Data processing: Analyzing inquiries and determining responses using generative AI models

[1532] Output: The workaround message sent to the user's device

[1533] Specific behavior:

[1534] When User C makes a payment of 500 yen using his / her smartphone, the device sends the transaction data (user ID, transaction date and time, transaction amount, transaction location, etc.) to the server in real time (Step 1).

[1535] The server inputs the data into the generated AI model, analyzes transaction patterns in real time, and detects an anomaly, for example, if a large payment is made overseas late at night (Step 2).

[1536] The server sends a push notification to User C based on the abnormal transaction data, and the device receives the notification and displays an alert to the user (Step 3).

[1537] User C sees the alert, selects an action within the app, and sends a response to the server (step 4).

[1538] If User C has any questions or concerns, they can contact support through the app, and the device will send the inquiry to the server. The server will analyze the inquiry using the generated AI model and notify the user of the appropriate response (Step 5).

[1539] (Application example 1)

[1540] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1541] In recent years, the spread of electronic payments using smartphones has led to an increase in cybercrime attempts to fraudulently obtain users' payment information. However, current electronic payment systems are sometimes slow to detect and respond to payment anomalies, making it difficult to fully ensure user security. There is also a need for systems to respond quickly and appropriately to security-related inquiries from users. This has led to an urgent need to build a system that allows users to use electronic payments with peace of mind.

[1542] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1543] In this invention, the server includes means for acquiring user account information and payment history data, means for analyzing the acquired payment history data in real time using a generative AI model and detecting abnormal patterns, means for notifying the user when an abnormal pattern is detected, means for accepting security-related inquiries from users, analyzing the inquiries using a generative AI model, and taking appropriate measures, means for continuously monitoring user payment information, means for analyzing abnormal transactions in real time based on the monitored data, and means for immediately issuing an alert and encouraging further safety measures when an abnormal transaction occurs. This makes it possible to monitor user payment information in real time, quickly detect abnormal transactions, and take immediate countermeasures.

[1544] "Account information" refers to data including identification information and authentication information required when a user uses a service.

[1545] "Payment history data" refers to information about all transactions conducted by a user, specifically including transaction date and time, transaction amount, transaction location, transaction ID, etc.

[1546] A "generative AI model" is an artificial intelligence model designed to perform pattern recognition and anomaly detection using machine learning and deep learning.

[1547] "Means of real-time analysis" refers to technology that processes data instantly and provides analysis results instantly.

[1548] An "anomalous pattern" refers to an irregular transaction that deviates from normal transaction patterns and may indicate fraud or error.

[1549] "Notification methods" refer to communication methods used to notify users of abnormal transactions and important information, and specifically include push notifications, SMS, email, etc.

[1550] "Means for analyzing inquiries" refers to technology that automatically understands the content of inquiries from users and provides appropriate answers and countermeasures.

[1551] "Means for continuously monitoring payment information" refers to technology that constantly monitors users' transaction activities and detects suspicious transactions in real time.

[1552] "Means for analyzing abnormal transactions in real time based on monitoring data" refers to technology that instantly processes data acquired during monitoring and detects abnormal transactions.

[1553] "Means for issuing warnings" refers to technology that issues warnings to users when abnormal transactions are detected, encouraging them to take prompt action.

[1554] "Safety measures prompting" refers to technology that prompts users to take additional security measures when abnormal transactions or security threats are detected.

[1555] The present invention is a security system for maintaining the safety of users' electronic payments. A specific embodiment of this system is described below.

[1556] System Overview

[1557] The server plays a key role in collecting data from users' smartphones, detecting anomalies, sending notifications, and responding to inquiries, allowing users to safely and efficiently manage their accounts and payments.

[1558] Hardware / Software used

[1559] server

[1560] The server is responsible for collecting data, analyzing abnormal patterns in real time, sending notifications, and analyzing inquiries.

[1561] Install a generative AI model (e.g., Isolation Forest model) to perform anomaly detection.

[1562] Send notification emails using an SMTP server.

[1563] Terminal

[1564] When a user makes a transaction using their smartphone, the data is sent to the server.

[1565] Notify users via push notification, SMS, email, etc.

[1566] Program processing explanation

[1567] 1. Data Collection

[1568] The terminal sends payment data (user ID, transaction date and time, transaction amount, transaction location, etc.) to the server.

[1569] The server periodically retrieves this data and stores it in a database.

[1570] 2. Real-time analysis

[1571] The server analyzes the acquired payment history data in real time using a generative AI model (Isolation Forest model) and detects abnormal patterns.

[1572] Specifically, it identifies abnormal transactions based on trading time, trading location, and transaction amount.

[1573] 3. Notification

[1574] If the server detects an abnormal pattern, it will immediately notify the user.

[1575] Notification methods include push notification, SMS, and email.

[1576] The device receives these notifications and displays an alert to the user.

[1577] 4. Response to inquiries

[1578] When a user has a question or wants to consult about security, the user sends an inquiry from the terminal to the support desk.

[1579] The server uses a generative AI model to analyze the inquiry and take appropriate action, such as locking the account, resetting the password, or confirming the transaction.

[1580] Specific examples

[1581] Anomaly detection example

[1582] 1. The area that User A normally uses is assumed to be within Japan.

[1583] 2. A large payment is made from overseas late at night due to unauthorized access.

[1584] 3. The server's generative AI model uses an anomaly detection algorithm to identify this anomalous transaction.

[1585] 4. The server sends a push notification to User A informing him of the abnormal transaction.

[1586] 5. User A checks the notification and changes the account password to prevent unauthorized use.

[1587] Examples of responding to inquiries

[1588] 1. User B becomes concerned about their recent transaction history and contacts support within the app.

[1589] 2. The server receives the query and analyzes the content using a generative AI model.

[1590] 3. If no abnormalities are found, User B is automatically notified of this information and informed that he or she can continue trading with confidence.

[1591] 4. User B reads the answer and has his / her concerns resolved.

[1592] Prompt Sentence Examples

[1593] Determine whether the following transactions are unusual:

[1594] Transaction ID: 1234

[1595] Date: 2023-11-01

[1596] Price: 10,000 yen

[1597] Location: Tokyo

[1598] Analyze whether there is an abnormality based on the following items.

[1599] Trading Area

[1600] Trading Hours

[1601] Transaction amount

[1602] The above is a specific example of the embodiment of the present invention. By using this system, users can make electronic payments more safely.

[1603] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1604] Step 1:

[1605] Data collection

[1606] Each time a user makes an electronic payment, the terminal generates payment data, such as the user ID, transaction date and time, transaction amount, and transaction location. This data is sent in real time to the server, which stores the received data in a database and stores it for continuous monitoring.

[1607] Input: User payment data generated during electronic payment (user ID, transaction date and time, transaction amount, transaction location, etc.)

[1608] Output: Payment data records stored in a database

[1609] Step 2:

[1610] Real-time analytics

[1611] The server monitors the payment data stored in the database in real time and analyzes anomalous patterns using a generative AI model (Isolation Forest model), identifying anomalous transactions based on factors such as the time of day, place of transaction, and transaction amount.

[1612] Input: Records of payment data stored in the database

[1613] Output: Flags for abnormal transactions (transactions that are determined to be abnormal are flagged)

[1614] Step 3:

[1615] notification

[1616] If the server detects an abnormal transaction, it will immediately notify the user via push notification, SMS, email, etc. The device will receive the notification and display an alert to the user.

[1617] Input: Transaction data identified as abnormal by real-time analysis

[1618] Output: Notification to user (push notification, SMS, email)

[1619] Step 4:

[1620] Inquiry response

[1621] When a user makes a security inquiry, they send it to the support desk from their device. The server receives it and analyzes the inquiry using a generative AI model. Based on the analysis results, the server takes appropriate action. This can include locking the account, resetting the password, or confirming transactions.

[1622] Input: Security inquiry from user

[1623] Output: The server responds appropriately and notifies the user

[1624] Step 5:

[1625] Continuous monitoring

[1626] The server continuously monitors users' payment information and detects and responds to any abnormalities as necessary, thereby ensuring the safety of users' payment information at all times.

[1627] Input: New payment data collected automatically

[1628] Output: Real-time updated payment database and record of anomalous transactions

[1629] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1630] System Overview

[1631] The present invention is a system that acquires user account information and payment history data, detects abnormal patterns by combining a generative AI model and an emotion engine for real-time analysis, and notifies users of the abnormalities. It also has a function to accept security-related inquiries from users, analyze the content of the inquiry and the user's emotions using the generative AI model and the emotion engine, and respond appropriately.

[1632] What the program does

[1633] Data collection

[1634] The server periodically obtains the user's account information and payment history data, including the user ID, transaction date and time, transaction amount, transaction location, etc. The terminal transmits the data to the server in real time every time the user makes a payment on their smartphone.

[1635] Real-time analysis of data

[1636] The server uses the generative AI model to analyze the acquired payment history data in real time and detect abnormal patterns. Specifically, it identifies abnormal transactions based on payment patterns (e.g., trading time, trading location, and transaction amount).

[1637] notification

[1638] If the server detects an abnormal pattern, it will immediately notify the user via push notification, SMS, email, etc. When the device receives the notification, it will display an alert to the user, helping them to take prompt action.

[1639] Inquiry response

[1640] When a user has a question or inquiry about security, they send it to the support desk from their device. The server then analyzes the inquiry using a generative AI model and emotion engine, and generates an appropriate response. Specific responses include locking the account, resetting the password, and confirming transactions, and the response is based on the user's emotions analyzed by the emotion engine.

[1641] Use of emotion engine

[1642] The emotion engine can recognize a user's emotions through voice or text analysis. For example, if a user makes a text-based inquiry, the engine analyzes the text to identify emotions (anxiety, anger, relief, etc.) and generates an appropriate response. For voice-based inquiries, the engine analyzes the tone of the voice and the phrasing to recognize emotions and reflect them in the response.

[1643] Specific examples

[1644] Anomaly detection example

[1645] 1. The area that User A normally uses is assumed to be within Japan.

[1646] 2. A large payment is made from overseas late at night due to unauthorized access.

[1647] 3. The server's generative AI model uses an anomaly detection algorithm to identify this anomalous transaction.

[1648] 4. The server sends a push notification to User A informing him of the abnormal transaction.

[1649] 5. User A checks the notification and changes the account password to prevent unauthorized use.

[1650] Examples of responding to inquiries

[1651] 1. User B becomes concerned about their recent transaction history and contacts support within the app.

[1652] 2. The server receives the query and analyzes the content and user sentiment using a generative AI model and emotion engine.

[1653] 3. If no abnormalities are found, User B is automatically notified of this information and informed that he or she can continue trading with confidence.

[1654] 4. User B reads the answer and resolves their concerns. If the emotion engine recognizes the user's concerns, it provides additional information or support to further reassure them.

[1655] As described above, the system of the present invention provides a high level of security for smartphone payments and functions for quick and appropriate responses. In particular, by combining it with an emotion engine, it becomes possible to respond in a detailed manner according to the emotions of each individual user, greatly improving user satisfaction and peace of mind.

[1656] The processing flow will be explained below.

[1657] Step 1:

[1658] The terminal processes the user's payment and generates payment data (user ID, transaction date and time, transaction amount, transaction location, etc.).

[1659] Step 2:

[1660] The terminal transmits the generated payment data to the server in real time.

[1661] Step 3:

[1662] The server stores the received payment data in a database.

[1663] Step 4:

[1664] The server uses the generated AI model to analyze payment data in real time and detect abnormal patterns.

[1665] Step 5:

[1666] The generative AI model compares a user's past payment history and identifies anomalous patterns based on the time of day, location, and amount of the transaction.

[1667] Step 6:

[1668] If the server detects an abnormality, it generates a message to notify the user based on the results of the abnormality detection.

[1669] Step 7:

[1670] The server generates a notification message and sends it to the device via push notification, SMS, or email.

[1671] Step 8:

[1672] The device receives the notification message and displays an alert to the user.

[1673] Step 9:

[1674] The user checks the notification and takes appropriate action, such as changing the account password, if necessary.

[1675] Step 10:

[1676] If users have any security questions or concerns, they can submit an inquiry from within the app.

[1677] Step 11:

[1678] The server receives a query from the user and passes the query to the generative AI model.

[1679] Step 12:

[1680] The generative AI model analyzes the inquiry content and generates an appropriate response.

[1681] Step 13:

[1682] The emotion engine analyzes the content of the user's inquiry and recognizes the user's emotions (anxiety, anger, relief, etc.).

[1683] Step 14:

[1684] The server generates an optimal reply message for the user based on the generated countermeasure and the user's emotions recognized by the emotion engine, and sends it to the device.

[1685] Step 15:

[1686] The device receives the reply message and displays it to the user.

[1687] Step 16:

[1688] Based on the information provided by the user, necessary measures are taken to resolve security issues.

[1689] Example 2

[1690] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1691] Conventional systems had issues such as being unable to respond in real time when anomalies occurred in users' transaction history data, and difficulty in responding appropriately and quickly to safety-related inquiries from users. Furthermore, they were unable to respond in a way that took users' feelings into consideration, which led to a decline in user satisfaction and a sense of security. It was necessary to solve these issues.

[1692] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring user account information and transaction history data, means for analyzing the acquired transaction history data in real time using a generative AI model and detecting abnormal patterns, means for notifying the user when an abnormal pattern is detected, and means for accepting safety-related inquiries from users, analyzing the inquiry content using the generative AI model and an emotion engine, and providing an appropriate response. This makes it possible to detect abnormalities in user transaction data in real time and quickly notify the user, and to respond to user inquiries appropriately and in accordance with their emotions.

[1693] "Account Information" means information used to identify and authenticate a user, including user ID, password, contact information, etc.

[1694] "Transaction history data" refers to detailed information about transactions conducted by a user, including the transaction date and time, transaction amount, transaction location, and payment method.

[1695] A "generative AI model" is a model that uses artificial intelligence algorithms to analyze and process data to generate new insights and patterns.

[1696] "Real-time analysis" means processing and analyzing data immediately after it is generated or acquired.

[1697] An "abnormal pattern" is a transaction that significantly deviates from normal transaction patterns, such as a deviation from normal trading hours or locations, or a high value transaction.

[1698] "Notification" means a means of informing a User of anomaly detection or other important information, which may take the form of a push notification, text message, electronic message, etc.

[1699] A "security inquiry" is an inquiry made by a user to raise questions or concerns about the security of their account or unusual transactions.

[1700] The "emotion engine" is an algorithm that analyzes the user's emotional state (anxiety, anger, relief, etc.) from their text and voice, and generates countermeasures based on the results.

[1701] The present invention is a system that acquires user account information and transaction history data, analyzes them in real time using a generative AI model and an emotion engine to detect abnormal patterns, and notifies users of any abnormalities. It also has the function of accepting safety-related inquiries from users, analyzing them, and taking appropriate action.

[1702] System program generation

[1703] The system's program is built around the interaction between a server, a device, and a user. The server is responsible for the main data processing, while the device is responsible for receiving user input and notifications. These roles are realized by integrating a generative AI model and an emotion engine.

[1704] Hardware and software used

[1705] Server: Uses cloud computing services (e.g., AWS, Google Cloud) and uses a database management system (e.g., MySQL).

[1706] Terminal: A mobile device such as a smartphone or tablet is used, and a dedicated payment application is run on it.

[1707] Generative AI models: Use machine learning frameworks such as TensorFlow and PyTorch.

[1708] Emotion engine: Uses NLP libraries (e.g. spaCy, NLTK) and speech analysis tools (e.g. Google Speech-to-Text API).

[1709] What the program does

[1710] The server periodically retrieves user account information and transaction history data and analyzes it in real time using a generative AI model. The retrieved data is stored in a database. If an abnormal trading pattern is detected, the server will notify the user. Notification methods include push notifications, text messages, and electronic messages.

[1711] When a user makes a safety inquiry, the inquiry is sent from the device to the server, which uses a generative AI model and emotion engine to analyze the inquiry and generate an appropriate response, such as locking the account, resetting the password, or confirming the transaction.

[1712] Specific examples

[1713] 1. Anomaly detection example:

[1714] User A's usual area of ​​use is domestic, and a high-value transaction is made from overseas late at night.

[1715] The server's generated AI model analyzes the transaction data in real time and identifies these anomalous transactions.

[1716] The server sends a push notification to User A, informing him of the details of the abnormal transaction.

[1717] User A checks the notification and changes the account password to prevent unauthorized use.

[1718] 2. Example of how to respond to an inquiry:

[1719] User B becomes concerned about his recent transaction history and contacts support via a dedicated application.

[1720] The server receives the query and analyzes the content and user sentiment using a generative AI model and emotion engine.

[1721] It confirms that there are no abnormalities and automatically notifies User B of this information and that they can continue trading with confidence.

[1722] User B reads the response and is relieved of their concerns.

[1723] Prompt Sentence Examples

[1724] 1. Detecting abnormal patterns:

[1725] "Please create a program to detect abnormal patterns in user transaction history data. Anomalies include high-value transactions from locations significantly different from the usual area, or transactions late at night."

[1726] 2. Security inquiry analysis:

[1727] "Develop a program that uses generative AI models and an emotion engine to generate appropriate responses to user security inquiries. If the user's emotion is anxiety or anger, generate a response that also provides reassurance."

[1728] The above is an embodiment of the present invention, which makes it possible to detect anomalies in user transaction data in real time, to promptly notify the user, and to respond appropriately to user inquiries.

[1729] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1730] Step 1:

[1731] The server periodically retrieves the user's account information and transaction history data.

[1732] Input: User ID, transaction date and time, transaction amount, transaction location, etc.

[1733] Data processing: Normalize the acquired data and format it to be saved in the database.

[1734] Output: Save the formatted transaction data to the database.

[1735] Specific operation: The server retrieves transaction data through the API and stores it in a MySQL database using SQL queries.

[1736] Step 2:

[1737] Each time a user makes a payment, the terminal transmits the transaction data to the server in real time.

[1738] Input: User transaction data generated on the device.

[1739] Data processing: The transaction data is converted into JSON format and sent to the server using a secure communication method.

[1740] Output: Transaction data in JSON format as sent to the server.

[1741] Specific operation: When payment is completed, the terminal generates transaction data and sends a POST request to the server using HTTPS communication.

[1742] Step 3:

[1743] The server stores the received transaction data in a database.

[1744] Input: Transaction data sent from the terminal in JSON format.

[1745] Data processing: Parse JSON data and convert it into a format suitable for the database.

[1746] Output: Transaction data stored in a database.

[1747] Specific operation: The server parses the received transaction data and stores it in the database using a MySQL INSERT query.

[1748] Step 4:

[1749] The server uses generative AI models to analyze trading data in real time and detect anomalous patterns.

[1750] Input: Transaction data stored in the database.

[1751] Data computation: Based on the generative AI model, stored transaction data is input into anomaly detection algorithms to identify abnormal patterns.

[1752] Output: Details of the detected anomalous transactions (date, time, location, amount, etc.).

[1753] How it works: The server retrieves transaction data from the database, inputs it into the AI ​​model, and analyzes abnormal patterns in real time. The output of the AI ​​model is details of abnormal transactions.

[1754] Step 5:

[1755] If the server detects an abnormal pattern, it notifies the user.

[1756] Input: Transaction data that is determined to be anomalous.

[1757] Data processing: Generation of notification messages (including details of abnormal transactions).

[1758] Output: Notification to the user (push notification, text message, email, etc.).

[1759] Specific operation: The server generates a notification message based on the details of the abnormal transaction and calls an API to send the notification to the user's device.

[1760] Step 6:

[1761] The device receives the notification from the server and displays an alert to the user.

[1762] Input: The notification message sent by the server.

[1763] Data processing: Parsing notification messages.

[1764] Output: The alert that appears on the user's screen.

[1765] Specific operation: The device analyzes the received notification message and displays an alert through the user interface, allowing the user to receive the alert and respond appropriately.

[1766] Step 7:

[1767] If a user has a safety inquiry, the inquiry is sent from the device to the support desk.

[1768] Input: The query entered by the user.

[1769] Data processing: Creating and sending query messages.

[1770] Output: The query message sent to the server.

[1771] Specific operation: The terminal receives the user's input, generates a message to send it to the server, and sends it.

[1772] Step 8:

[1773] The server receives queries from users and analyzes them using generative AI models and emotion engines.

[1774] Input: The query message sent by the user.

[1775] Data calculation: Analyzing the query content and identifying user sentiment using an emotion engine.

[1776] Output: Analysis results and appropriate action plans.

[1777] Specific operation: The server inputs the received inquiry into the generative AI model and analyzes the inquiry content. At the same time, it uses the emotion engine to analyze the user's emotional state. As a result, it generates an appropriate response.

[1778] Step 9:

[1779] The server sends the generated response / solution to the user.

[1780] Input: Analysis results and countermeasures.

[1781] Data processing: Generating response messages (including content based on user sentiment).

[1782] Output: The response message sent to the user's terminal.

[1783] Specific operation: The server generates a response message based on the analysis results and countermeasures and sends it to the user's device.

[1784] Step 10:

[1785] The terminal displays the received response message to the user.

[1786] Input: The response message sent by the server.

[1787] Data processing: Parsing the response message.

[1788] Output: The response that is displayed on the user's screen.

[1789] Specific operation: The terminal analyzes the received response message and displays it through the user interface. The user reads the response and responds appropriately.

[1790] This allows us to detect anomalies in users' transaction data in real time, notify them quickly, and respond appropriately to user inquiries.

[1791] (Application example 2)

[1792] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1793] Conventional security systems lack the means to not only monitor user account information and payment history data, but also to perform real-time analysis to detect abnormal transactions and respond quickly and appropriately to user inquiries. Furthermore, they respond without taking user emotions into consideration, which leaves users unable to fully alleviate their anxiety and dissatisfaction. The present invention aims to solve these problems by maintaining a high level of security for user transactions while enabling detailed responses tailored to user emotions.

[1794] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring user account information and payment history data, means for analyzing the acquired payment history data in real time using a generative AI model to detect abnormal patterns, means for notifying the user when an abnormal pattern is detected, means for accepting security-related inquiries from users, analyzing the inquiries using a generative AI model, and taking appropriate measures, and means for analyzing user emotions using an emotion engine and generating responses based on the analysis results. This enables rapid detection and notification of abnormal transactions, as well as detailed responses tailored to user emotions.

[1795] "User Account Information" means information used to personally identify a User and related authentication data, including, but not limited to, User ID, password, and email address.

[1796] "Payment History Data" refers to information regarding the history of transactions made by a User, including transaction dates, transaction amounts, and transaction locations.

[1797] A "generative AI model" refers to an artificial intelligence model that is trained to analyze large amounts of data and detect specific patterns or anomalies.

[1798] "Real-time analytics" refers to the process of processing acquired data and generating results almost immediately.

[1799] "Abnormal Pattern" refers to a pattern of suspicious or fraudulent activity that differs from normal transactions.

[1800] "Emotion engine" refers to software or a system for recognizing a user's emotions through speech or text analysis.

[1801] "Security inquiries from users" refers to questions or inquiries sent by users to resolve their security-related doubts or concerns.

[1802] "Notification" means any action taken to warn or inform a User when an anomalous pattern is detected, including push notification, SMS, or email.

[1803] "Appropriate response" refers to actions taken in response to a user's inquiry to resolve the issue or provide reassurance, such as locking the account or resetting the password.

[1804] The system of the present invention acquires and analyzes user account information and payment history data in real time, and performs abnormal pattern detection and sentiment analysis to provide users with safe and reliable security. Detailed embodiments of the present invention will be described below.

[1805] System Overview

[1806] Data collection

[1807] The server periodically obtains the user's account information and payment history data, including the user ID, transaction date and time, transaction amount, transaction location, etc. In addition, the terminal (e.g., smartphone) sends the data to the server in real time every time the user makes a payment.

[1808] Real-time analysis of data

[1809] The server uses a generative AI model to analyze the acquired payment history data in real time and detect abnormal patterns. Specifically, it compares it with normal transaction patterns (e.g., trading time, trading location, transaction amount) to identify abnormal transactions. This allows the server to continuously monitor users' transaction patterns and immediately detect any abnormalities.

[1810] notification

[1811] If the server detects an abnormal pattern, it will immediately notify the user via push notification, SMS, or email. When the device receives the notification, it will display an alert to the user, urging them to take immediate action.

[1812] Inquiry response

[1813] When a user has a security question or wants to consult, they send an inquiry from their device to the support desk. The server analyzes the inquiry using the generative AI model and emotion engine and generates an appropriate response. Specific responses include locking the account, resetting the password, and confirming the transaction. The emotion engine then analyzes the user's emotions and generates a response that provides reassurance if the user is feeling anxious, for example.

[1814] Use of emotion engine

[1815] The emotion engine can recognize a user's emotions through voice or text analysis. When a user makes a text-based inquiry, it analyzes the text to identify emotions (e.g., anxiety, anger, relief, etc.) and generates an appropriate response. When a user makes a voice-based inquiry, it analyzes the tone of the voice and the phrasing to recognize emotions and reflect them in the response accordingly.

[1816] Specific examples

[1817] Anomaly detection example

[1818] 1. The area that User A normally uses is domestic.

[1819] 2. Large amounts of money are paid from overseas late at night.

[1820] 3. The server's generative AI model uses an anomaly detection algorithm to identify this anomalous transaction.

[1821] 4. The server sends a push notification to User A informing him of the abnormal transaction.

[1822] 5. User A checks the notification and changes their account password to prevent unauthorized use.

[1823] Examples of responding to inquiries

[1824] 1. User B becomes concerned about their recent transaction history and contacts support within the app.

[1825] 2. The server receives the query and analyzes the content and user sentiment using a generative AI model and emotion engine.

[1826] 3. If no abnormalities are found, User B is automatically notified of this information and informed that they can continue trading with confidence.

[1827] 4. User B reads the answer and resolves their concerns. If the emotion engine recognizes the user's concerns, it provides additional information or support to further reassure them.

[1828] Prompt Sentence Examples

[1829] 1. Enter the prompt: "I'm concerned about my recent transaction history. Is this transaction safe?"

[1830] 2. Emotion analysis result: "Anxiety"

[1831] 3. Produces response: "No anomalies detected. Enjoy your day."

[1832] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1833] Step 1: Data collection

[1834] The server periodically obtains the user's account information and payment history data, including the user ID, transaction date and time, transaction amount, and transaction location. In addition, the terminal (e.g., smartphone) sends the data to the server in real time every time the user makes a payment. The input is the user's payment event, and the output is the payment data stored on the server.

[1835] Step 2: Analyzing data in real time

[1836] The server uses a generative AI model to analyze the acquired payment history data in real time. Specifically, the payment history data is used as input and analyzed to detect anomalous patterns. The generative AI model compares it with normal transaction patterns (e.g., trading time, trading location, transaction amount) to identify anomalous transactions. The output is the detection result of anomalous transactions.

[1837] Step 3: Notification of abnormal transactions

[1838] If the server detects an abnormal pattern, it immediately notifies the user. Notification methods include push notification, SMS, and / or email. The input is the result of detecting an abnormal transaction, and the output is a notification sent to the user. The terminal receives the notification and performs specific operations such as displaying an alert to the user.

[1839] Step 4: Receiving an inquiry

[1840] When a user has a question or wants to consult about security, they send an inquiry from their terminal to the support desk. The user's inquiry is sent to the terminal as input, and the inquiry is sent to the server as output.

[1841] Step 5: Query analysis

[1842] The server uses a generative AI model and an emotion engine to analyze the inquiry and generate an appropriate response. Specifically, the generative AI model analyzes the inquiry using the user's inquiry text as input, and the emotion engine recognizes the user's emotion. The output is the user's emotion analysis results and a response.

[1843] Step 6: Response Generation

[1844] The server generates a response to the user based on the analysis results. For example, if it confirms that there are no abnormalities, it automatically notifies the user of that information and tells them that they can continue trading with peace of mind. The input includes the emotion analysis results and countermeasures, and the output is a response to the user.

[1845] Step 7: Notification of response

[1846] The server notifies the user of the generated response. Specifically, the response is sent to the device by at least one of push notification, SMS, and email. The input is the response to the user, and the output is the user receiving the response.

[1847] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1848] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1849] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1850] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1851] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1852] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1853] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1854] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1855] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1856] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1857] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1858] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1859] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1860] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1861] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1862] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1863] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1864] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1865] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1866] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1867] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1868] The following is further disclosed regarding the above embodiment.

[1869] (Claim 1)

[1870] A means for obtaining user account information and payment history data;

[1871] A means of analyzing the acquired payment history data in real time using a generative AI model to detect abnormal patterns;

[1872] a means for notifying a user when an abnormal pattern is detected;

[1873] A means of accepting security-related inquiries from users, analyzing the inquiries using a generative AI model, and providing appropriate responses.

[1874] A system including:

[1875] (Claim 2)

[1876] 10. The system of claim 1, further comprising means for the generative AI model to consider a user's usual trading hours, trading locations, and transaction amounts when analyzing the user's payment history data and detecting anomalous patterns.

[1877] (Claim 3)

[1878] 10. The system of claim 1, wherein the means for notifying the user uses at least one of push notification, SMS, and email.

[1879] "Example 1"

[1880] (Claim 1)

[1881] A means for obtaining user account information and payment history data;

[1882] A means of analyzing the acquired payment history data in real time using a generative AI model to detect abnormal patterns;

[1883] a means for notifying a user when an abnormal pattern is detected;

[1884] A means of accepting security-related inquiries from users, analyzing the inquiries using a generative AI model, and providing appropriate responses.

[1885] Provide support for users who receive notifications so they can respond quickly, and

[1886] A system including:

[1887] (Claim 2)

[1888] 10. The system of claim 1, further comprising means for the generative AI model to consider a user's usual trading hours, trading locations, and transaction amounts when analyzing the user's payment history data and detecting anomalous patterns.

[1889] (Claim 3)

[1890] 10. The system of claim 1, wherein the means for notifying the user comprises means for notifying the user using at least one of a push notification, an SMS, and an email.

[1891] "Application Example 1"

[1892] (Claim 1)

[1893] A means for obtaining user account information and payment history data;

[1894] A means of analyzing the acquired payment history data in real time using a generative AI model to detect abnormal patterns;

[1895] a means for notifying a user when an abnormal pattern is detected;

[1896] A means of accepting security-related inquiries from users, analyzing the inquiries using a generative AI model, and providing appropriate responses.

[1897] A means of continuously monitoring users' payment information;

[1898] A means of analyzing abnormal transactions in real time based on monitoring data;

[1899] A means to immediately issue a warning in the event of an abnormal transaction and prompt further safety measures;

[1900] A system including:

[1901] (Claim 2)

[1902] 10. The system of claim 1, further comprising means for the generative AI model to consider a user's usual trading hours, trading locations, and transaction amounts when analyzing the user's payment history data and detecting anomalous patterns.

[1903] (Claim 3)

[1904] 10. The system of claim 1, wherein the means for notifying the user uses at least one of push notification, SMS, and email.

[1905] "Example 2: Combining Emotion Engines"

[1906] (Claim 1)

[1907] A means of obtaining user account information and transaction history data;

[1908] A means for analyzing transaction history data obtained using a generative AI model in real time to detect abnormal patterns;

[1909] a means for notifying a user when an abnormal pattern is detected;

[1910] A means of accepting safety-related inquiries from users, analyzing the inquiries using a generative AI model and an emotion engine, and providing appropriate responses;

[1911] A system including:

[1912] (Claim 2)

[1913] 10. The system of claim 1, further comprising means for the generative AI model to consider a user's usual trading hours, trading locations, and transaction amounts when analyzing the user's trading history data and detecting anomalous patterns.

[1914] (Claim 3)

[1915] 10. The system of claim 1, wherein the means for notifying the user uses at least one of a push notification, a text message, and an electronic message.

[1916] "Application example 2 when combining emotion engines"

[1917] (Claim 1)

[1918] A means for obtaining user account information and payment history data;

[1919] A means of analyzing the acquired payment history data in real time using a generative AI model to detect abnormal patterns;

[1920] a means for notifying a user when an abnormal pattern is detected;

[1921] A means of accepting security-related inquiries from users, analyzing the inquiries using a generative AI model, and providing appropriate responses.

[1922] A means for analyzing the user's emotions using an emotion engine and generating response content based on the analysis result;

[1923] A system including:

[1924] (Claim 2)

[1925] 10. The system of claim 1, further comprising means for the generative AI model to consider a user's usual trading hours, trading locations, and transaction amounts when analyzing the user's payment history data and detecting anomalous patterns.

[1926] (Claim 3)

[1927] 10. The system of claim 1, wherein the means for notifying the user uses at least one of push notification, SMS, and email. [Explanation of symbols]

[1928] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for obtaining user account information and payment history data; A means of analyzing the acquired payment history data in real time using a generative AI model to detect abnormal patterns; a means for notifying a user when an abnormal pattern is detected; A means of accepting security-related inquiries from users, analyzing the inquiries using a generative AI model, and providing appropriate responses. A system including:

2. The system of claim 1, further comprising means for the generative AI model to consider the user's usual trading hours, trading locations, and transaction amounts when analyzing the user's payment history data and detecting abnormal patterns.

3. The system of claim 1 , wherein the means for notifying the user uses at least one of push notification, SMS, and email.

Images