System

Abstract

A system is provided.SOLUTION: A system including application means for detecting a fraud application, transmission means for transmitting detected fraud application information to a server in real time, storage means for storing the transmitted fraud application information in a database, visualization means for displaying the stored fraud application information on a map using a geographic information system, alert means for automatically transmitting an alert to other stores located around a store where the fraud application has occurred, and analysis means for aggregating and analyzing past fraud application data and outputting the data as a report.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] Currently, fraudulent applications for mobile phones and contract lines, particularly by foreigners, are becoming a problem. While there is a system in place for store staff to apply for the S Mark when suspicious contract applications are received, if the application is rejected, the group often reapplies at a different nearby store. The lack of a means to quickly detect such trends and alert nearby stores is an issue. Furthermore, the current system makes it difficult to analyze and respond to cases where fraudulent applications occur on an ongoing basis. As a result, the prevention of fraudulent contracts has not been fully achieved. [Means for solving the problem]

[0005] The present invention solves the above problem by providing a system that includes an application means for detecting fraudulent applications, a transmission means for transmitting detected fraudulent application information to a server in real time, a storage means for saving the transmitted fraudulent application information in a database, a visualization means for displaying the saved fraudulent application information on a map using a geographic information system, an alert means for automatically sending alerts to other stores located around the store where the fraudulent application occurred, and an analysis means for compiling and analyzing past fraudulent application data and outputting it as a report.

[0006] With this system, if a suspicious application is detected at one store, the information is immediately shared with other stores, and nearby stores are alerted.In addition, by compiling and analyzing past application data, it is possible to visualize trends in fraudulent applications and take continuous measures.This will make it possible to more effectively prevent fraudulent contracts for mobile phones and contract lines.

[0007] A "fraudulent application" refers to a contract application made using false information without following proper procedures.

[0008] "Application means" refers to a device or program that detects fraudulent applications and enters the information into the system in a specific format.

[0009] "Transmission means" refers to a device or program for transmitting fraudulent application information detected by the application means to the server in real time.

[0010] "Storage means" refers to a database or storage system for securely storing fraudulent application information transmitted via transmission means.

[0011] "Visualization means" refers to a system or program for visually displaying fraudulent application information stored in storage means using a geographic information system (GIS) or the like.

[0012] "Alert means" refers to a system or program for automatically sending warning notices to other stores located around the store where the fraudulent application occurred.

[0013] "Analysis means" refers to a system or program that compiles past fraudulent application data, performs statistical analysis, and outputs the data in report format.

[0014] "Geographic information system" refers to a system for collecting, managing, analyzing, and displaying geographic information. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

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

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

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

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

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

[0030] 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.

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

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] This invention relates to a system for effectively detecting fraudulent applications and quickly responding to them. This system is composed of functions including fraudulent application detection, real-time information transmission, visualization using a geographic information system (GIS), alert notification to nearby stores, and analysis of past data.

[0037] As a specific embodiment for implementing the present invention, a flow from detecting a fraudulent application to sharing information, issuing an alert, and analyzing the information will be described.

[0038] Detecting and recording fraudulent applications

[0039] 1. When a user (shop crew member) detects a fraudulent application, they use a dedicated interface to enter the suspicious contract application information into the system, including the application date and time, applicant information, and details of the suspicious behavior.

[0040] 2. The device receives the entered information, first stores it in a local database, and then validates it to ensure that required fields are filled in properly and that the data format is correct.

[0041] 3. The terminal sends the information that has passed validation to the server, where it is stored in a secure database.

[0042] Real-time processing and visualization of information

[0043] 1. The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS). Using GIS, the location of the store can be accurately displayed.

[0044] 2. In order to visually display information about fraudulent applications, the server obtains the latitude and longitude information of the store and displays the location of the fraudulent application on a map with a red icon or a specific color, making it clear where the fraudulent application occurred.

[0045] Alert notifications to nearby stores

[0046] 1. The server runs a database query to identify other stores located within 1 km of the store where the fraudulent claim was detected.

[0047] 2. The server automatically generates a warning message and sends an alert to the identified nearby stores. The alert includes the store where the fraudulent application occurred, the date and time, and points to note.

[0048] 3. The terminal receives the alert and displays it to the user (shop crew) as a pop-up notification, allowing them to immediately become alert to any suspicious applications.

[0049] Historical data analysis

[0050] 1. The server aggregates past fraudulent application data from the database and calculates the number of fraudulent applications within a specified period (for example, one year).

[0051] 2. The server performs statistical analysis based on the collected data to determine which stores are experiencing fraudulent applications and how frequently.

[0052] 3. The server generates and visually displays the analysis results as dashboards and reports, allowing administrators to understand trends and patterns in fraudulent applications and obtain information to take effective measures.

[0053] Specific examples

[0054] 1. A user (shop crew member) detects a suspicious contract application by a foreigner at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into a dedicated system.

[0055] 2. The device receives this input information, validates it, and then sends it to the server, which stores it in a database and displays it on a map using GIS.

[0056] 3. The server identifies five stores within 1 km of the store in question, generates an alert, and sends it. The device displays the received alert as a pop-up, and the user can confirm the notification.

[0057] 4. The server compiles application data from the past year and displays the analysis results on the dashboard, showing that 10 fraudulent applications occurred in October.

[0058] This series of processes enables fraudulent contracts to be detected quickly and dealt with effectively.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] A user (shop crew member) detects a suspicious contract application and enters the suspicious contract application information into the system through a dedicated interface. The information entered includes the application date and time, applicant information, and details of the suspicious behavior.

[0062] Step 2:

[0063] The device receives the entered information and temporarily stores it in a local database, while simultaneously validating the information to ensure that required fields are filled in properly and that the data format is correct.

[0064] Step 3:

[0065] The terminal sends the information that has passed validation to the server, where it is stored in a secure database.

[0066] Step 4:

[0067] The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS). Here, the latitude and longitude information of the store is acquired, and by linking with the GIS API, the location of the fraudulent application is clearly displayed by showing it on the map with a red icon or a specific color.

[0068] Step 5:

[0069] The server uses a database query to identify other stores within 1 km of the store where the fraudulent claim was detected. The query returns a list of nearby stores.

[0070] Step 6:

[0071] The server automatically generates a warning message and sends an alert to the identified nearby stores, which includes the store where the fraudulent application occurred, the date and time, and points to note.

[0072] Step 7:

[0073] The terminal receives the alert and displays it to the user (shop crew) as a pop-up notification, allowing the user to immediately become alert to suspicious applications and take appropriate measures.

[0074] Step 8:

[0075] The server aggregates past fraudulent application data from the database and calculates the number of fraudulent applications within a specified period (e.g., one year). This is achieved by performing statistical data processing.

[0076] Step 9:

[0077] The server performs statistical analysis on the aggregated data to identify which stores are experiencing fraudulent applications and how frequently they occur, and generates the results as dashboards and reports.

[0078] Step 10:

[0079] The analysis results generated by the server are sent to the device and displayed visually on a dashboard, allowing users (administrators and shop crew) to understand trends and patterns in fraudulent applications and use this information to take future countermeasures.

[0080] Example 1

[0081] 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."

[0082] The problem to be solved by this invention is to provide a system for effectively detecting fraudulent applications and responding quickly. Specifically, the object is to provide a system that can efficiently and in real time detect fraudulent applications, share information, issue alerts, and analyze past data.

[0083] 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.

[0084] In this invention, the server includes: application means for detecting fraudulent applications; transmission means for transmitting detected fraudulent application information to the server in real time; storage means for saving the sent fraudulent application information in a database; visualization means for displaying the saved fraudulent application information on a map using a geographic information system; alert means for automatically sending alerts to other stores located around the store where the fraudulent application occurred; analysis means for compiling and analyzing past fraudulent application data and outputting it as a report; validation means for validating input data when fraudulent application information is entered and checking required fields and data format; warning generation means for generating and sending warning messages to multiple identified surrounding stores; and visualization means for acquiring latitude and longitude information of stores and displaying them on a map with specific colors and icons to visually display the fraudulent application status. This enables rapid detection of fraudulent applications, information sharing, and warnings to surrounding stores.

[0085] A "fraudulent application" is an application made using unauthorized or fraudulent information.

[0086] The "application means" is a means for detecting fraudulent applications, and includes an interface for users to input information.

[0087] The "transmission means" is a means for transmitting detected fraudulent application information to the server in real time.

[0088] The "storage means" is a means for storing the transmitted fraudulent application information in a database.

[0089] The "visualization means" is a means for displaying the stored fraudulent application information on a map using a geographic information system.

[0090] The "alert means" is a means for automatically sending an alert to other stores located around the store where the fraudulent application occurred.

[0091] "Analysis methods" are means for compiling and analyzing past fraudulent application data and outputting it as a report.

[0092] "Validation means" refers to a means for validating input data and checking required fields and data format when fraudulent application information is entered.

[0093] The "warning generation means" is a means for generating and transmitting a warning message to the identified surrounding stores.

[0094] The "visualization means" is a means for obtaining the latitude and longitude information of the store and showing it on a map with a specific color or icon in order to visually display the fraudulent application status.

[0095] This invention relates to a system for effectively detecting fraudulent applications and quickly responding to them. This system is composed of functions including fraudulent application detection, real-time information transmission, visualization using a geographic information system (GIS), alert notification to nearby stores, and analysis of past data.

[0096] Detecting and recording fraudulent applications

[0097] A user (shop crew member) uses a dedicated interface to enter information about suspicious contract applications into the system, including the date and time of the application, applicant information, and details of suspicious behavior.

[0098] The terminal receives information entered by the user and temporarily stores it in a local database. A lightweight database such as SQLite is used for the local database. The saved data is then validated to ensure the input format and required fields are entered correctly. Information that passes validation is sent to the server via secure communication using the HTTPS protocol. The server stores the received data in a secure database (for example, PostgreSQL).

[0099] Real-time processing and visualization of information

[0100] The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS). GIS tools include Google Maps API and ESRI ArcGIS. The server periodically runs a script to detect new data and obtains new fraudulent application information. Based on the obtained information, the GIS tool is called, the latitude and longitude information of the store is obtained, and a red marker is placed at a specific location on the map to visually indicate the location of the fraudulent application.

[0101] Alert notifications to nearby stores

[0102] The server executes a database query (SQL query) to identify other stores within 1 km of the store where the fraudulent application was detected. A warning message is generated and sent to the identified stores via email or a push notification system (e.g., Firebase Cloud Messaging). The warning message includes the store where the fraudulent application occurred, the date and time, and important points to note.

[0103] The terminal receives the alert and displays it to the user (shop crew) as a pop-up notification. The application running on the terminal receives notifications from the server on a specific port and displays the received message on the screen in a pop-up format.

[0104] Historical data analysis

[0105] The server aggregates data on fraudulent applications from the past database and calculates the number of fraudulent applications within a specified period (for example, one year). A calculation script is run periodically on the server to extract fraudulent application information from the database for the past year and count the number of cases within the period. A statistical analysis of the extracted data is performed using a data analysis library such as Pandas or NumPy to calculate how frequently fraudulent applications occur at each store. Based on the analysis results, a dashboard is created in the form of graphs and charts using a data visualization tool such as Tableau or Power BI. For example, it displays information such as "fluctuations in the number of fraudulent applications by month" and "frequency of fraudulent applications by store."

[0106] Specific examples

[0107] 1. A user (shop crew member) detects a suspicious contract application at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into a dedicated system.

[0108] 2. The device receives this input information, temporarily stores it, validates it, and then sends it to the server, which stores it in a database and displays it on a map using GIS.

[0109] 3. The server identifies five stores within 1 km of the store in question, generates an alert, and sends it. The device displays the received alert as a pop-up, and the user can confirm the notification.

[0110] 4. The server compiles application data from the past year and displays the analysis results on the dashboard, showing that 10 fraudulent applications occurred in October.

[0111] Prompt Sentence Examples

[0112] "At 1:45 PM on October 15th, a suspicious contract application by a foreigner was detected in the store. The applicant was behaving strangely. Please send alerts to surrounding stores as well."

[0113] This will enable the creation of a system that can quickly detect fraudulent applications, share information, and issue warnings to surrounding stores.

[0114] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0115] Step 1:

[0116] A user (shop crew member) enters suspicious contract application information into a dedicated interface.

[0117] Input: Application date and time, applicant information, details of suspicious behavior (e.g., "October 15th, 13:45", "Foreigner", "Suspicious behavior").

[0118] Specific actions: Enter the required information into the input screen of a web form or dedicated application and click the "Submit" button.

[0119] Step 2:

[0120] The terminal receives the information input by the user and temporarily stores it in a local database.

[0121] Input: Application information entered by the user.

[0122] Data processing: Validate the data format in a local database to ensure consistency and that required fields are entered correctly.

[0123] Output: Data that passes validation is temporarily saved.

[0124] What happens: The data is temporarily stored in a lightweight database such as SQLite and validation is performed.

[0125] Step 3:

[0126] The terminal sends the information that has passed the validation to the server.

[0127] Input: Application information that has passed validation.

[0128] Data processing: Secure communication using the HTTPS protocol.

[0129] Output: The server receives the data via secure communication.

[0130] What happens: If validation is successful, the data is sent to the server using HTTPS.

[0131] Step 4:

[0132] The server stores the received fraudulent application information in a database.

[0133] Input: Application information sent from the terminal.

[0134] Data processing: Store the received data in a secure database (e.g., PostgreSQL).

[0135] Output: The data is saved to a database.

[0136] Specific operation: Stores the received data in a secure database.

[0137] Step 5:

[0138] The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS).

[0139] Input: Fraudulent application information retrieved from the database.

[0140] Data processing: Call GIS tools (Google Maps API; ESRI ArcGIS) to obtain store latitude and longitude information and convert it into a display format.

[0141] Output: The locations of fraudulent claims are displayed on a map.

[0142] Specific operation: Using a GIS tool, place a red marker on the map based on the acquired latitude and longitude information.

[0143] Step 6:

[0144] The server runs a database query to identify other stores located within 1 km of the store where the fraudulent claim was detected.

[0145] Input: Latitude and longitude information of the store where the fraudulent application occurred, and data of surrounding stores.

[0146] Data processing: Search for stores within 1km using an SQL query.

[0147] Output: List of other stores within 1km radius.

[0148] Specific operation: The server periodically executes queries to identify nearby stores.

[0149] Step 7:

[0150] The server generates a warning message and sends an alert to the identified surrounding stores.

[0151] Input: List of surrounding stores, fraudulent application information.

[0152] Data processing: Generate a warning message (e.g., "A fraudulent application occurred on October 15th at 1:45 PM. Please be careful") and send it via a notification service (e.g., Firebase Cloud Messaging).

[0153] Output: A warning message is sent to each store.

[0154] Specific behavior: After generating a message, an alert will be sent via email or push notification.

[0155] Step 8:

[0156] The device receives the alert and displays it to the user (shop crew) as a pop-up notification.

[0157] Input: The warning message sent by the server.

[0158] Data processing: Process received messages into popup format.

[0159] Output: Show a popup notification on the device.

[0160] What it does: When a notification is received on a specific port, the application displays a pop-up notification on the screen.

[0161] Step 9:

[0162] The server aggregates fraudulent application data from past databases and calculates the number of fraudulent applications within a specified period (for example, one year).

[0163] Input: Past fraudulent application data.

[0164] Data processing: Run the data aggregation script and count the number of items within the specified period.

[0165] Output: Number of fraudulent applications within a specified period.

[0166] Specific operation: Executes the aggregation script periodically and aggregates the results.

[0167] Step 10:

[0168] The server performs statistical analysis based on the aggregated data.

[0169] Input: Aggregated fraudulent application data.

[0170] Data processing: Perform statistical analysis using data analysis libraries such as Pandas and NumPy.

[0171] Output: Results of the statistical analysis.

[0172] Specific actions: Runs analysis scripts and calculates statistical indicators.

[0173] Step 11:

[0174] The server generates and visually displays the analysis results as dashboards and reports.

[0175] Input: Results of the statistical analysis.

[0176] Data processing: Create graphs and charts using Tableau and Power BI.

[0177] Output: Display as a dashboard or report.

[0178] Specific action: Convert the data into a format that is easy to visualize using a data visualization tool.

[0179] The above are the specific processing steps of the program of this system.

[0180] (Application example 1)

[0181] 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."

[0182] Conventional fraudulent application detection systems lack the ability to quickly notify nearby stores of fraudulent application information, making it difficult to take immediate action to prevent the spread of fraud. Furthermore, because there is no mechanism for real-time notifications using smart devices, notifications can be overlooked or responses delayed. Furthermore, there is insufficient visualization of trends based on pattern analysis of past fraudulent application data, resulting in a lack of information to take effective countermeasures.

[0183] 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.

[0184] In this invention, the server includes detection means for detecting fraudulent applications, transmission means for transmitting detected fraudulent application information to the server in real time, storage means for saving the transmitted fraudulent application information in a database, visualization means for displaying the saved fraudulent application information on a map using a geographic information system, alert means for automatically sending alerts to other stores located around the store where the fraudulent application occurred, analysis means for compiling and analyzing past fraudulent application data and outputting it as a report, and reception means for other stores that have received the fraudulent application information to receive the same as a pop-up notification via their smartphones or head-mounted displays. This makes it possible to quickly and reliably notify nearby stores of fraudulent application information and encourage them to take immediate action, and furthermore, by analyzing fraudulent application patterns based on past data, it is possible to provide information for taking effective countermeasures.

[0185] "Fraudulent application" refers to an application made with fraudulent content that violates normal procedures and standards.

[0186] "Detection means" refers to a device or part of a system for detecting fraudulent applications.

[0187] "Transmission means" refers to a device or part of a system that has the function of transmitting detected fraudulent application information to a server in real time.

[0188] "Storage means" refers to a device or part of a system that has the function of storing transmitted fraudulent application information in a database.

[0189] "Visualization means" refers to a device or part of a system that has the function of displaying stored fraudulent application information on a map using a geographic information system.

[0190] "Alert means" refers to a device or part of a system that has the function of automatically sending an alert to other stores located around the store where the fraudulent application occurred.

[0191] "Analysis means" refers to a device or part of a system that has the function of compiling and analyzing past fraudulent application data and outputting it as a report.

[0192] "Receiving means" refers to a device or part of a system that has the function of allowing other stores that receive the fraudulent application information to receive it as a pop-up notification via their smartphones or head-mounted displays.

[0193] "Geographic information system" is a general term for software and hardware used to collect and analyze geographic data and display it on a map.

[0194] A "smartphone" is a mobile device that has the same functions as a computer, despite being a mobile phone.

[0195] A "head-mounted display" refers to a device that is worn on the user's head and displays visual information.

[0196] A "pop-up notification" refers to a short message displayed on an application to immediately notify the user of important information.

[0197] A "generative AI model" refers to a mathematical model generated by artificial intelligence technology for analysis and prediction.

[0198] A "prompt" refers to a textual instruction or question that is input into a generative AI model.

[0199] This invention relates to a system that uses a smartphone or head-mounted display (HMD) to quickly detect fraudulent applications and notify nearby stores in real time. It also includes the aggregation and analysis of past fraudulent application data, and the visualization and provision of the results.

[0200] 1. Program Generation

[0201] The system mainly consists of the following components:

[0202] Detection methods for detecting fraudulent applications

[0203] A means for transmitting detected fraudulent application information to a server.

[0204] A means of storing submitted information in a database

[0205] A visualization method for displaying stored information on a map using GIS

[0206] An alerting method that automatically sends alerts to nearby stores

[0207] The store that receives the fraudulent application information receives it on their smartphone or HMD.

[0208] Analysis tool that aggregates and analyzes past data and outputs the results

[0209] 2. Explain the program's processing in natural language

[0210] The server includes the following hardware and software:

[0211] Hardware: Cloud Server

[0212] Software: Python, Flask (backend), GIS software (e.g., Folium), data analysis library (Pandas)

[0213] A smartphone and HMD are installed on the terminal side and function as follows.

[0214] Detection Method

[0215] When a user detects a fraudulent application, they enter information about the fraudulent application using a dedicated interface, including the date and time of the application, information about the applicant, and details of any suspicious behavior.

[0216] Transmission and storage methods

[0217] The device receives this input information, validates it, and then sends it to the server, which then stores it in a secure database.

[0218] Visualization tools

[0219] The server uses GIS to display the saved fraudulent application information on a map. Specifically, it obtains the location information of the store where the fraudulent application occurred and displays it as a marker on the map.

[0220] Alert and Receipt Methods

[0221] When a fraudulent application is detected, the server automatically generates an alert to nearby stores and notifies them on smartphones or HMDs, allowing users to immediately take precautions.

[0222] analytical means

[0223] The server aggregates past fraudulent application data and performs statistical analysis, and the results of this analysis are displayed visually in the form of dashboards and reports.

[0224] 3. Adding concrete examples and prompts

[0225] Specific examples

[0226] Users can enter information such as "foreigner," "October 15th, 13:45," and "suspicious behavior" on their smartphones, and an alert is instantly sent to other stores within a 1km radius. At the same time, the server analyzes fraudulent application data from the past year and displays the results on a dashboard.

[0227] Prompt Sentence Examples

[0228] Based on the information below, please design a system that notifies other nearby stores in real time when a fraudulent application is detected and analyzes past fraudulent application data.

[0229] Date and time of fraudulent application: October 15th, 13:45

[0230] Applicant information: Foreigner

[0231] Fraudulent Activity Details: Suspicious Activity

[0232] This system, configured in this way, quickly detects fraudulent applications, notifies relevant parties in real time, and provides analytical information using past data to take effective countermeasures, thereby preventing the spread of fraudulent activity and accelerating response.

[0233] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0234] Step 1:

[0235] When a user detects a fraudulent application, they use a smartphone or head-mounted display to enter the application date and time, applicant information, and details of suspicious behavior into a dedicated interface. The entered information is saved in temporary memory on the device. Input data includes the application date and time, applicant information, and details of suspicious behavior. The application information saved in temporary memory is obtained as output data.

[0236] Step 2:

[0237] The terminal validates the entered information. Specifically, it checks whether all required fields in the input data are filled in and whether the data format is correct. For example, it checks the date format and the format of the applicant information. If validation is successful, it proceeds to the next step. The input data is data in temporary memory, and the output data is the result of validation.

[0238] Step 3:

[0239] The terminal sends the information that has passed validation to the server. The transmission is done using an HTTP request (POST method). The input data is the application information on the terminal side, and the output data is the application information saved on the server side.

[0240] Step 4:

[0241] The server stores the received information in a secure database. The database is an RDBMS (Relational Database Management System) and the information is inserted into tables. The input data is the application information received by the server and the output data are the records stored in the database.

[0242] Step 5:

[0243] The server obtains latitude and longitude information based on the fraudulent application information stored in the database. This information is then displayed on a map using a geographic information system (GIS). GIS software such as Folium is used. The input data is the latitude and longitude information in the database, and the output data is the location of the fraudulent application displayed on the map.

[0244] Step 6:

[0245] The server executes a database query to identify other stores located within a certain distance (e.g., 1 km) around the store where the fraudulent claim was detected. The query results in a list of identified stores. The input data is the location information of the fraudulent claim and the surrounding stores, and the output data is a list of identified surrounding stores.

[0246] Step 7:

[0247] The server generates a warning message for the identified stores and sends an alert. The warning message includes the name of the store where the fraudulent application occurred, the date and time, and important points to note. This is sent to the smartphone or HMD. The input data is a list of identified stores, and the output data is the sent warning message.

[0248] Step 8:

[0249] The terminal receives the alert and displays it to the user as a pop-up notification. The pop-up notification contains a warning message that the user can view and respond to immediately. The input data is the warning message sent from the server, and the output data is the pop-up notification displayed to the user.

[0250] Step 9:

[0251] The server aggregates past fraudulent application data from a database and calculates the number of fraudulent applications within a specified period. Libraries such as Pandas are used for data analysis. The input data is past application information, and the output data is aggregated statistical information.

[0252] Step 10:

[0253] The server performs statistical analysis based on the aggregated data. It uses a generative AI model to analyze patterns in fraudulent application data and displays the results as a dashboard. Specific software operations include data filtering, clustering, and trend analysis. The input data is the aggregated application information, and the output data is a dashboard of the analysis results.

[0254] Through the above steps, the system of the present invention can quickly detect fraudulent applications, immediately notify relevant parties, and provide information using past data to take effective measures.

[0255] 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.

[0256] This invention relates to a system for effectively detecting and quickly responding to fraudulent applications. This system enhances risk assessment of fraudulent applications by combining fraudulent application detection, real-time information transmission, visualization using a geographic information system (GIS), alert notifications to nearby stores, analysis of past data, and an emotion engine that recognizes user emotions.

[0257] As a specific embodiment for implementing the present invention, a flow from detecting a fraudulent application to sharing information, issuing an alert, and analyzing using an emotion engine will be described.

[0258] Detecting and recording fraudulent applications

[0259] 1. When a user (shop crew member) detects a suspicious contract application, they use a dedicated interface to enter the suspicious contract application information into the system. This includes the application date and time, applicant information, and details of the suspicious behavior. The emotion engine also analyzes the user's emotional state in real time and records this information.

[0260] 2. The device receives the entered information, first stores it in a local database, and then validates it to ensure that required fields are filled in properly and that the data format is correct.

[0261] 3. The terminal sends the information that has passed validation to the server, where it is stored in a secure database.

[0262] Real-time processing and visualization of information

[0263] 1. The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS). Here, the server obtains the latitude and longitude information of the store and, in conjunction with the GIS API, displays the location of the fraudulent application on the map with a red icon or a specific color, clearly showing the location of the fraudulent application.

[0264] 2. The emotion engine analyzes the user's emotional data when a fraudulent application is made, and integrates and displays the results in a visualization tool. This allows users to visually confirm the risk assessment of fraudulent applications.

[0265] Alert notifications to nearby stores

[0266] 1. The server uses a database query to identify other stores within 1 km of the store where the fraudulent claim was detected. The query returns a list of nearby stores.

[0267] 2. The server automatically generates a warning message and sends an alert to the identified nearby stores. The alert includes the store where the fraudulent application occurred, the date and time, and points to note.

[0268] 3. The terminal receives the alert and displays it to the user (shop crew) as a pop-up notification, allowing the user to immediately become alert to suspicious applications and take appropriate measures.

[0269] Historical data analysis

[0270] 1. The server aggregates past fraudulent application data from the database and calculates the number of fraudulent applications within a specified period (for example, one year). This is achieved by performing statistical data processing.

[0271] 2. The server performs statistical analysis on the aggregated data to identify which stores have experienced fraudulent applications and how frequently. The results are then generated as a dashboard or report.

[0272] 3. The emotion engine analyzes past application data and user emotional data to identify patterns of fraudulent applications, improving the accuracy of detecting subtle fraudulent behavior.

[0273] 4. The analysis results generated by the server are sent to the device and displayed visually on a dashboard, allowing users (administrators and shop crew) to understand trends and patterns in fraudulent applications and use this information to take future countermeasures.

[0274] Specific examples

[0275] 1. A user (shop crew member) detects a suspicious contract application from a foreigner at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into the dedicated system. At the same time, the emotion engine analyzes the user's facial expression and tone of voice, and records their emotional state, such as "tension" or "anxiety."

[0276] 2. The device receives this input information, validates it, and then sends it to the server, which stores it in a database and displays it on a map, integrating GIS and emotion data.

[0277] 3. The server identifies five stores within 1 km of the store in question, generates an alert, and sends it. The device displays the received alert as a pop-up, and the user can confirm the notification.

[0278] 4. The server aggregates application data and emotion data from the past year, and displays the analysis results on the dashboard, showing that 10 fraudulent applications occurred in October. The emotion engine also evaluates the risk of fraudulent applications based on the emotion data, and reflects this in the analysis results.

[0279] This series of processes, combined with emotional data, strengthens risk assessment of contract fraud, enabling swift and effective response.

[0280] The processing flow will be explained below.

[0281] Step 1:

[0282] A user (shop crew member) detects a suspicious contract application and enters the suspicious contract application information into the system through a dedicated interface. The information entered includes the date and time of the application, applicant information, and details of suspicious behavior. An emotion engine also analyzes the user's facial expressions and tone of voice in real time, and records emotional data such as "tension" and "anxiety."

[0283] Step 2:

[0284] The device receives this information, temporarily stores it in a local database, and then validates the information to ensure that required fields are filled in properly and that the data format is correct.

[0285] Step 3:

[0286] The terminal sends the information that has passed validation to the server, where it is stored in a secure database.

[0287] Step 4:

[0288] The server processes the fraudulent application information and emotion data stored in the database in real time and displays it on a map using a geographic information system (GIS). It obtains the latitude and longitude information of stores and, by linking with the GIS API, shows the locations of fraudulent applications visually by displaying them on the map with red icons or specific colors. At the same time, it performs a risk assessment using emotion data and visualizes the results.

[0289] Step 5:

[0290] The server uses a database query to identify other stores within 1 km of the store where the fraudulent claim was detected, and the stores listed by the query are then automatically targeted for alert notifications.

[0291] Step 6:

[0292] The server automatically generates a warning message and sends an alert to the identified surrounding stores. This alert includes the store where the fraudulent application occurred, the date and time, points to be careful about, and the risk assessment results based on the emotion engine.

[0293] Step 7:

[0294] The terminal receives the alert and displays it to the user (shop crew) as a pop-up notification, allowing the user to immediately become alert to suspicious applications and take appropriate measures.

[0295] Step 8:

[0296] The server aggregates past fraudulent application data and emotion data from the database and calculates the number of fraudulent applications and emotion trends within a specified period (e.g., one year). This is achieved by performing statistical data processing.

[0297] Step 9:

[0298] The server performs statistical analysis based on the aggregated data to determine which stores have experienced fraudulent applications and how frequently they have occurred, as well as the associated emotional data to determine risk assessment results. These results are then generated as dashboards and reports.

[0299] Step 10:

[0300] The analysis results generated by the server are sent to the terminal and displayed visually on a dashboard, allowing users (administrators and shop crew) to understand trends and patterns of fraudulent applications and user emotional tendencies, and use this information to help with future countermeasures.

[0301] Specific examples

[0302] 1. A user (shop crew member) detects a suspicious contract application from a foreigner at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into the dedicated system. At the same time, the emotion engine analyzes the user's facial expression and tone of voice, and records their emotional state, such as "tension" or "anxiety."

[0303] 2. The device receives this input information, validates it, and then sends it to the server, which stores it in a database and displays it on a map, integrating GIS and emotion data.

[0304] 3. The server identifies five stores within 1 km of the store in question, generates an alert, and sends it. The device displays the received alert as a pop-up, and the user can confirm the notification.

[0305] 4. The server aggregates application data and emotion data from the past year, and displays the analysis results on the dashboard, showing that 10 fraudulent applications occurred in October. The emotion engine also evaluates the risk of fraudulent applications based on the emotion data, and reflects this in the analysis results.

[0306] This series of processes, combined with emotional data, strengthens risk assessment of contract fraud, enabling swift and effective response.

[0307] Example 2

[0308] 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."

[0309] Conventional fraudulent application detection systems have had issues with delayed response after detecting fraudulent applications and providing only limited information. Furthermore, risk assessment is insufficient because the system does not take into account the user's emotional state. As a result, early detection of fraudulent applications and effective implementation of preventative measures are sometimes ineffective. Furthermore, there is a lack of a way to visually grasp the location of fraudulent applications and the surrounding situation.

[0310] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0311] In this invention, the server includes application means for detecting fraudulent applications, transmission means for transmitting detected fraudulent application information to the server in real time, storage means for saving the transmitted fraudulent application information in a database, visualization means for displaying the saved fraudulent application information on a map using a geographic information system, emotion analysis means for analyzing the emotional state of users at the location where the fraudulent application occurred and recording the information in real time, alert means for automatically sending alerts to other locations located in the vicinity of the location where the fraudulent application occurred, and analysis means for compiling and analyzing the information based on past fraudulent application information and the emotional state of users and outputting it as a report. This significantly improves risk assessment of fraudulent applications and enables quick and effective response.

[0312] "Fraudulent application" refers to an application or attempted contract made with fraudulent intent.

[0313] "Application method" refers to the interface or mechanism for detecting fraudulent applications.

[0314] "Transmission means" refers to the method or technology for transmitting detected fraudulent application information to a server in real time.

[0315] "Storage means" refers to a mechanism for safely storing submitted fraudulent application information in a database.

[0316] "Visualization means" refers to technology that displays stored fraudulent application information on a map using a geographic information system.

[0317] "Emotion analysis means" refers to technology that analyzes the emotional state of users at the location where fraudulent applications occur and records that information in real time.

[0318] "Alert method" refers to a mechanism that automatically sends a warning to other locations located in the vicinity of the location where the fraudulent application occurred.

[0319] "Analysis methods" refers to technology for compiling and analyzing information based on past fraudulent application information and the user's emotional state, and outputting it as a report.

[0320] A "geographic information system" refers to a system that handles geospatial information and visualizes data on a map.

[0321] "User" refers to an individual or person with a role who uses this system to detect, record, and address fraudulent applications.

[0322] "Server" refers to a computer device that manages the processing of the entire system and collects, stores, and processes fraudulent application information and emotion analysis data.

[0323] "Database" refers to an information management system for organizing and storing fraudulent application information and related data.

[0324] The present invention provides a system for effectively detecting and quickly responding to fraudulent claims, which enhances risk assessment of fraudulent claims by combining fraudulent claim detection, real-time information transmission, visualization using a geographic information system (GIS), alert notification to other locations in the vicinity, analysis of historical data, and user sentiment analysis.

[0325] Detecting and recording fraudulent applications

[0326] First, when a user (shop crew member) detects a suspicious contract application, they use a dedicated interface to enter the date and time of the application, applicant information, and details of the suspicious behavior into the system. As this information is entered, an emotion engine analyzes the user's emotional state (e.g., tension, anxiety) in real time, and this information is also recorded. This analysis uses technology that analyzes facial expressions and tone of voice using a camera and microphone.

[0327] The device then temporarily stores this information in a local database and performs validation, such as checking for missing required fields and checking the date format. If the information passes validation, it is sent from the device to the server, where it is stored in a secure database.

[0328] Real-time processing and visualization of information

[0329] The server processes the stored fraudulent application information in real time and displays it on a map using a geographic information system (GIS), such as Google Maps API, to clearly indicate the location of fraudulent applications using, for example, a red icon.

[0330] The emotion engine also integrates the analyzed emotion data into visualization tools and displays them on a map. Emotional states are displayed as appropriate icons (e.g., emoji faces), allowing users to visually assess the risk of fraudulent applications.

[0331] Alert notifications to nearby stores

[0332] The server uses a database query to identify other locations within 1 km of the location where the fraudulent claim was detected. It uses SQL queries to compile a list of nearby locations and then generates and sends out an alert. The alert includes the location, date, and time of the fraudulent claim, as well as any important points to note.

[0333] The terminal receives this alert and displays it to the user (shop crew) as a pop-up notification, allowing the user to immediately check the information and take necessary measures.

[0334] Historical data analysis

[0335] The server aggregates past fraudulent application data from the database and calculates the number of fraudulent applications within a specified period (e.g., the past year). This process involves extracting the data using SQL queries and performing statistical processing and visualization using Python tools such as Pandas and Matplotlib.

[0336] The emotion engine combines and analyzes past fraudulent application data with user emotion data to identify patterns of fraudulent applications. It uses a clustering algorithm to extract specific behavioral and emotional patterns. The server visually displays the results of this analysis on a dashboard, allowing users (administrators and shop crew) to understand trends and patterns in fraudulent applications and develop preventative measures.

[0337] Specific examples

[0338] For example, a user (shop crew member) detects a suspicious contract application made by a foreigner at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into the dedicated system. At the same time, the emotion engine analyzes the user's facial expressions and tone of voice, and records their emotional state, such as "tension" or "anxiety."

[0339] The device receives this information, validates it, and then sends it to the server, which stores it in a database and displays it on a map, integrating GIS and emotion data.

[0340] The server identifies five other locations within 1 km of the location and generates and sends an alert, which the device displays as a pop-up for the user to confirm.

[0341] The server aggregates application data and emotion data from the past year, and displays the analysis results on the dashboard, showing that 10 fraudulent applications occurred in October. The emotion engine also evaluates the risk of fraudulent applications based on the emotion data, and reflects this in the analysis results.

[0342] When using a generative AI model, you might use prompts like the following:

[0343] "At 13:45 on October 15th, a foreigner exhibited suspicious behavior. The user's emotional state was 'tension' and 'anxiety'."

[0344] The comprehensive operation of the system as described above will strengthen risk assessment of fraudulent applications and enable swift and effective responses.

[0345] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0346] Program processing steps

[0347] Detecting and recording fraudulent applications

[0348] Step 1:

[0349] A user (shop crew member) detects a suspicious contract application. Using a dedicated interface, the user enters the application date and time, applicant information, and details of suspicious behavior. The entered data is in text format and separated into specific fields. This input information is sent directly to the next processing step, while the emotion engine simultaneously analyzes the user's emotional state. This analysis uses a camera and microphone to evaluate facial expressions and tone of voice in real time.

[0350] Step 2:

[0351] The terminal receives the information entered by the user. The entered data is temporarily stored in a local database and validated. Specific validation details include whether all required fields (e.g., application date and time, applicant information) are filled in, whether the date format is correct, and whether the details of suspicious activity are 50 characters or more. Information that passes validation is sent to the next process as a new data structure.

[0352] Step 3:

[0353] The device sends the information that has passed validation to the server. The data is encrypted during transmission. The transmitted data includes the application date and time, applicant information, details of suspicious behavior, and emotion analysis results. The server receives this data and stores it in a secure database.

[0354] Real-time processing and visualization of information

[0355] Step 4:

[0356] The server retrieves the fraudulent application information stored in the database and begins processing it in real time. The input data here is detailed information about the fraudulent application and the results of sentiment analysis. The server retrieves the latitude and longitude information of the store from a GIS API (e.g., Google Maps API) and displays the location of the fraudulent application on a map with a red icon. This display data is generated in real time through requests to the GIS API.

[0357] Step 5:

[0358] The emotion engine takes the analyzed emotion data and integrates the results into a visualization method. Specifically, it adds icons (e.g., emoji faces) indicating the emotional state to the locations of fraudulent claims on a map. The input data includes the emotion analysis results, and the output data consists of the visual display information of the GIS.

[0359] Alert notifications to nearby stores

[0360] Step 6:

[0361] The server uses a database query to identify other locations within 1 km of the location where the fraudulent claim was detected. The input data for this process includes the latitude and longitude of the fraudulent claim, and uses an SQL query to list other nearby locations. The output data is a list of the identified nearby locations.

[0362] Step 7:

[0363] The server generates a warning message for the identified nearby locations and sends an alert. The alert contains the location, date, and time of the fraudulent application, as well as points to note, and this information is generated automatically. The input data is the list of identified nearby locations and the fraudulent application information, and the output data is the alert message and its transmission status.

[0364] Step 8:

[0365] The alert received by the terminal is displayed to the user (shop crew) as a pop-up notification. Specifically, the user is immediately notified of the warning through desktop or mobile notifications. The input data of this process is the alert message sent from the server, and the output data is the notification confirmation status sent to the user.

[0366] Historical data analysis

[0367] Step 9:

[0368] The server aggregates past fraudulent application data from the database. It uses an SQL query to extract data to calculate the number of fraudulent applications for a specified period (e.g., the past year). The input data is detailed information about fraudulent applications, and the output data is the number of fraudulent applications for the specified period.

[0369] Step 10:

[0370] The server performs statistical analysis based on the collected data. Python's Pandas and Matplotlib are used to generate graphs and heat maps to visualize the number and location of fraudulent applications. The input data is the number of fraudulent applications within a specified period, and the output data is visualized data of the analysis results.

[0371] Step 11:

[0372] The emotion engine combines and analyzes past fraudulent application data with user emotion data. It uses a clustering algorithm to extract specific behavioral and emotional patterns. The input data is fraudulent application information and emotion data, and the output data is the extracted behavioral and emotional patterns.

[0373] Step 12:

[0374] The analysis results generated by the server are sent to the terminal and displayed visually on a dashboard. This allows users (administrators and shop crew) to understand trends and patterns of fraudulent applications and use them to develop future countermeasures. The input data is the analysis results sent from the server, and the output data is the visual display information on the dashboard.

[0375] This series of processing steps significantly strengthens the risk assessment of fraudulent applications and enables a fast and effective response.

[0376] (Application example 2)

[0377] 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."

[0378] Conventional fraudulent application detection systems can detect fraudulent applications and issue warnings, but they ignore the user's emotional state and lack information to better understand fraudulent behavior. Furthermore, they lack the ability to visualize fraudulent application information or send alerts to nearby stores in real time, making it difficult to respond immediately. Furthermore, analysis of past fraudulent application data is insufficient, making it difficult to assess the risk of recurrence.

[0379] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0380] In this invention, the server includes application means for detecting fraudulent applications, transmission means for transmitting detected fraudulent application information to the server in real time, storage means for saving the transmitted fraudulent application information in a database, visualization means for displaying the saved fraudulent application information on a map using a geographic information system, alert means for automatically sending alerts to other stores located around the store where the fraudulent application occurred, analysis means for aggregating and analyzing past fraudulent application data and outputting it as a report, emotion analysis means for analyzing the user's emotional state from application data, and means for integrating the user's emotional state into the fraudulent application information and displaying it on the visualization means. This improves the accuracy of fraudulent application detection and enables quick and effective response.

[0381] "Fraudulent application" refers to an act of violating prescribed procedures and attempting to obtain unfair benefits.

[0382] "Application Method" means the method for detecting fraudulent applications and entering information into the system.

[0383] "Transmission means" refers to a means for transmitting detected fraudulent application information to a server in real time.

[0384] "Storage Means" refers to the means for storing submitted fraudulent application information in a database.

[0385] The "visualization means" is a means for displaying the stored fraudulent application information on a map using a geographic information system.

[0386] "Alert means" refers to a means for automatically issuing a warning to other stores located around the store where the fraudulent application occurred.

[0387] "Analysis methods" refers to the means for compiling and analyzing past fraudulent application data and outputting it as a report.

[0388] "Emotion analysis means" means means for analyzing the user's emotional state from application data.

[0389] "Integration means" refers to a means for integrating and displaying a user's emotional state with fraudulent application information.

[0390] The system for implementing this invention combines multiple means for effectively detecting fraudulent applications and quickly responding to them. The specific flow and the hardware and software used are described below.

[0391] Overall system overview

[0392] 1. Detecting fraudulent applications

[0393] When a user (store staff member) detects a fraudulent application, they enter the fraudulent application information into the system using a dedicated interface.

[0394] The emotion analysis means analyzes the user's emotional state at the time of input in real time and adds that information.

[0395] 2. Real-time processing and information transmission

[0396] The terminal receives the input information and first temporarily stores it in a local database.

[0397] Validate information to ensure required fields are filled in properly and that data is formatted correctly.

[0398] The terminal sends the information that has passed the validation to the server.

[0399] The server receives the information and stores it in a database.

[0400] 3. Visualization

[0401] The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS).

[0402] The locations of fraudulent applications are clearly displayed on a map, and emotional states are also integrated and visualized.

[0403] 4. Store-to-store alerts

[0404] The server automatically identifies other stores within a certain distance of the store where the fraudulent application was detected and sends an alert.

[0405] The terminal displays the received alert to the user in a pop-up notification.

[0406] 5. Historical Data Analysis

[0407] The server compiles and analyzes past fraudulent application data from the database and calculates the number of fraudulent applications for a specified period.

[0408] The analysis results are output as dashboards and reports so that users can view them.

[0409] Hardware and software used

[0410] EmotionEngine: A library for analyzing a user's emotional state. This library analyzes emotions from voice and facial expressions in real time.

[0411] GISMap: A library for displaying the locations of fraudulent applications on a map using a geographic information system.

[0412] NotificationManager: A library for generating cross-store alerts and notifying other stores.

[0413] DatabaseManager: A library for managing the storage and retrieval of fraudulent application data.

[0414] Specific examples

[0415] A user (store staff member) detects a suspicious contract application from a foreigner at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into a dedicated interface. At the same time, an emotion analysis tool analyzes the user's emotional state and records it as "tension" or "anxiety."

[0416] The device receives this input information, validates it, and then sends it to the server, which stores it in a database and displays it on a map, integrating GIS and emotion data.

[0417] The server identifies five stores within a certain distance of the store in question, generates an alert, and sends it out. The alert is received by the device and displayed as a pop-up, allowing the user to confirm the notification.

[0418] The server compiles application data and emotion data from the past year, and displays on the dashboard that 10 fraudulent applications occurred in October. In addition, the emotion analysis means evaluates the risk of fraudulent applications based on the emotion data, and reflects this in the analysis results.

[0419] Prompt Sentence Examples

[0420] Data for fraudulent application warning system

[0421] User Input: I'm nervous

[0422] Applicant information: Foreigners

[0423] Suspicious Activity: Suspicious activity

[0424] Location information: (35.6895, 139.6917)

[0425] In this way, a system embodying the present invention is constructed, which improves the accuracy of detecting fraudulent applications and enables prompt and effective responses.

[0426] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0427] Step 1:

[0428] When a user detects a fraudulent application, they use a dedicated interface to input information about the fraudulent application into the system. Based on the input, the date and time of the application, applicant information, details of suspicious behavior, and the user's emotional state are collected. Using an emotion analysis means, the user's emotional state is analyzed and recorded together with the application information.

[0429] Step 2:

[0430] The terminal receives the information entered by the user and temporarily stores it in a local database. At the same time, the terminal validates the input information to ensure that required fields are entered properly and that the data format is correct.

[0431] Step 3:

[0432] The terminal sends the information that has passed validation to the server. The input is the user's fraudulent application information and emotion data. After transmission, the server receives the information and stores it in a secure database. At this point, the server rechecks the integrity of the information.

[0433] Step 4:

[0434] The server processes the fraudulent application information stored in the database in real time. To display the locations of fraudulent applications on a map using a geographic information system (GIS), the location data of the fraudulent application information is sent to a GIS API, and the locations of the fraudulent applications are displayed on the map.

[0435] Step 5:

[0436] The server visualizes the emotional data obtained using emotion analysis techniques. In addition to the locations of fraudulent applications, the user's emotional state is also integrated and displayed on a map, allowing users to intuitively confirm risk assessment.

[0437] Step 6:

[0438] The server executes a query against the database to automatically identify other stores located within a certain distance of the store where the fraudulent application was detected. The input is the location data of the store where the fraudulent application occurred, and the output is a list of surrounding stores.

[0439] Step 7:

[0440] The server generates a warning message to the identified surrounding stores, which includes the store where the fraudulent application occurred, the date and time, and points to note, and is automatically sent by an alert means.

[0441] Step 8:

[0442] The device displays the received alert as a pop-up notification to the user, allowing the user to check the alert displayed on the screen and take immediate action.

[0443] Step 9:

[0444] The server aggregates and analyzes past fraudulent application data. The input is past fraudulent application data and sentiment data, and statistical data processing is performed to calculate the number of fraudulent applications within a period and a risk assessment. The aggregated results are output to a dashboard or report.

[0445] Step 10:

[0446] The server displays the aggregated results and risk assessments on a dashboard, which users can view to understand trends and patterns in fraudulent applications and obtain information to take appropriate measures.

[0447] The above are the processing steps of the system for carrying out this invention, and the specific operations and inputs / outputs are clearly stated for each step.

[0448] 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.

[0449] 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.

[0450] 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.

[0451] [Second embodiment]

[0452] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0453] 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.

[0454] 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).

[0455] 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.

[0456] 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.

[0457] 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).

[0458] 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.

[0459] 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.

[0460] 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.

[0461] 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.

[0462] 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.

[0463] 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."

[0464] This invention relates to a system for effectively detecting fraudulent applications and quickly responding to them. This system is composed of functions including fraudulent application detection, real-time information transmission, visualization using a geographic information system (GIS), alert notification to nearby stores, and analysis of past data.

[0465] As a specific embodiment for implementing the present invention, a flow from detecting a fraudulent application to sharing information, issuing an alert, and analyzing the information will be described.

[0466] Detecting and recording fraudulent applications

[0467] 1. When a user (shop crew member) detects a fraudulent application, they use a dedicated interface to enter the suspicious contract application information into the system, including the application date and time, applicant information, and details of the suspicious behavior.

[0468] 2. The device receives the entered information, first stores it in a local database, and then validates it to ensure that required fields are filled in properly and that the data format is correct.

[0469] 3. The terminal sends the information that has passed validation to the server, where it is stored in a secure database.

[0470] Real-time processing and visualization of information

[0471] 1. The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS). Using GIS, the location of the store can be accurately displayed.

[0472] 2. In order to visually display information about fraudulent applications, the server obtains the latitude and longitude information of the store and displays the location of the fraudulent application on a map with a red icon or a specific color, making it clear where the fraudulent application occurred.

[0473] Alert notifications to nearby stores

[0474] 1. The server runs a database query to identify other stores located within 1 km of the store where the fraudulent claim was detected.

[0475] 2. The server automatically generates a warning message and sends an alert to the identified nearby stores. The alert includes the store where the fraudulent application occurred, the date and time, and points to note.

[0476] 3. The terminal receives the alert and displays it to the user (shop crew) as a pop-up notification, allowing them to immediately become alert to any suspicious applications.

[0477] Historical data analysis

[0478] 1. The server aggregates past fraudulent application data from the database and calculates the number of fraudulent applications within a specified period (for example, one year).

[0479] 2. The server performs statistical analysis based on the collected data to determine which stores are experiencing fraudulent applications and how frequently.

[0480] 3. The server generates and visually displays the analysis results as dashboards and reports, allowing administrators to understand trends and patterns in fraudulent applications and obtain information to take effective measures.

[0481] Specific examples

[0482] 1. A user (shop crew member) detects a suspicious contract application by a foreigner at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into a dedicated system.

[0483] 2. The device receives this input information, validates it, and then sends it to the server, which stores it in a database and displays it on a map using GIS.

[0484] 3. The server identifies five stores within 1 km of the store in question, generates an alert, and sends it. The device displays the received alert as a pop-up, and the user can confirm the notification.

[0485] 4. The server compiles application data from the past year and displays the analysis results on the dashboard, showing that 10 fraudulent applications occurred in October.

[0486] This series of processes enables fraudulent contracts to be detected quickly and dealt with effectively.

[0487] The processing flow will be explained below.

[0488] Step 1:

[0489] A user (shop crew member) detects a suspicious contract application and enters the suspicious contract application information into the system through a dedicated interface. The information entered includes the application date and time, applicant information, and details of the suspicious behavior.

[0490] Step 2:

[0491] The device receives the entered information and temporarily stores it in a local database, while simultaneously validating the information to ensure that required fields are filled in properly and that the data format is correct.

[0492] Step 3:

[0493] The terminal sends the information that has passed validation to the server, where it is stored in a secure database.

[0494] Step 4:

[0495] The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS). Here, the latitude and longitude information of the store is acquired, and by linking with the GIS API, the location of the fraudulent application is clearly displayed by showing it on the map with a red icon or a specific color.

[0496] Step 5:

[0497] The server uses a database query to identify other stores within 1 km of the store where the fraudulent claim was detected. The query returns a list of nearby stores.

[0498] Step 6:

[0499] The server automatically generates a warning message and sends an alert to the identified nearby stores, which includes the store where the fraudulent application occurred, the date and time, and points to note.

[0500] Step 7:

[0501] The terminal receives the alert and displays it to the user (shop crew) as a pop-up notification, allowing the user to immediately become alert to suspicious applications and take appropriate measures.

[0502] Step 8:

[0503] The server aggregates past fraudulent application data from the database and calculates the number of fraudulent applications within a specified period (e.g., one year). This is achieved by performing statistical data processing.

[0504] Step 9:

[0505] The server performs statistical analysis on the aggregated data to identify which stores are experiencing fraudulent applications and how frequently they occur, and generates the results as dashboards and reports.

[0506] Step 10:

[0507] The analysis results generated by the server are sent to the device and displayed visually on a dashboard, allowing users (administrators and shop crew) to understand trends and patterns in fraudulent applications and use this information to take future countermeasures.

[0508] Example 1

[0509] 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."

[0510] The problem to be solved by this invention is to provide a system for effectively detecting fraudulent applications and responding quickly. Specifically, the object is to provide a system that can efficiently and in real time detect fraudulent applications, share information, issue alerts, and analyze past data.

[0511] 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.

[0512] In this invention, the server includes: application means for detecting fraudulent applications; transmission means for transmitting detected fraudulent application information to the server in real time; storage means for saving the sent fraudulent application information in a database; visualization means for displaying the saved fraudulent application information on a map using a geographic information system; alert means for automatically sending alerts to other stores located around the store where the fraudulent application occurred; analysis means for compiling and analyzing past fraudulent application data and outputting it as a report; validation means for validating input data when fraudulent application information is entered and checking required fields and data format; warning generation means for generating and sending warning messages to multiple identified surrounding stores; and visualization means for acquiring latitude and longitude information of stores and displaying them on a map with specific colors and icons to visually display the fraudulent application status. This enables rapid detection of fraudulent applications, information sharing, and warnings to surrounding stores.

[0513] A "fraudulent application" is an application made using unauthorized or fraudulent information.

[0514] The "application means" is a means for detecting fraudulent applications, and includes an interface for users to input information.

[0515] The "transmission means" is a means for transmitting detected fraudulent application information to the server in real time.

[0516] The "storage means" is a means for storing the transmitted fraudulent application information in a database.

[0517] The "visualization means" is a means for displaying the stored fraudulent application information on a map using a geographic information system.

[0518] The "alert means" is a means for automatically sending an alert to other stores located around the store where the fraudulent application occurred.

[0519] "Analysis methods" are means for compiling and analyzing past fraudulent application data and outputting it as a report.

[0520] "Validation means" refers to a means for validating input data and checking required fields and data format when fraudulent application information is entered.

[0521] The "warning generation means" is a means for generating and transmitting a warning message to the identified surrounding stores.

[0522] The "visualization means" is a means for obtaining the latitude and longitude information of the store and showing it on a map with a specific color or icon in order to visually display the fraudulent application status.

[0523] This invention relates to a system for effectively detecting fraudulent applications and quickly responding to them. This system is composed of functions including fraudulent application detection, real-time information transmission, visualization using a geographic information system (GIS), alert notification to nearby stores, and analysis of past data.

[0524] Detecting and recording fraudulent applications

[0525] A user (shop crew member) uses a dedicated interface to enter information about suspicious contract applications into the system, including the date and time of the application, applicant information, and details of suspicious behavior.

[0526] The terminal receives information entered by the user and temporarily stores it in a local database. A lightweight database such as SQLite is used for the local database. The saved data is then validated to ensure the input format and required fields are entered correctly. Information that passes validation is sent to the server via secure communication using the HTTPS protocol. The server stores the received data in a secure database (for example, PostgreSQL).

[0527] Real-time processing and visualization of information

[0528] The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS). GIS tools include Google Maps API and ESRI ArcGIS. The server periodically runs a script to detect new data and obtains new fraudulent application information. Based on the obtained information, the GIS tool is called, the latitude and longitude information of the store is obtained, and a red marker is placed at a specific location on the map to visually indicate the location of the fraudulent application.

[0529] Alert notifications to nearby stores

[0530] The server executes a database query (SQL query) to identify other stores within 1 km of the store where the fraudulent application was detected. A warning message is generated and sent to the identified stores via email or a push notification system (e.g., Firebase Cloud Messaging). The warning message includes the store where the fraudulent application occurred, the date and time, and important points to note.

[0531] The terminal receives the alert and displays it to the user (shop crew) as a pop-up notification. The application running on the terminal receives notifications from the server on a specific port and displays the received message on the screen in a pop-up format.

[0532] Historical data analysis

[0533] The server aggregates data on fraudulent applications from the past database and calculates the number of fraudulent applications within a specified period (for example, one year). A calculation script is run periodically on the server to extract fraudulent application information from the database for the past year and count the number of cases within the period. A statistical analysis of the extracted data is performed using a data analysis library such as Pandas or NumPy to calculate how frequently fraudulent applications occur at each store. Based on the analysis results, a dashboard is created in the form of graphs and charts using a data visualization tool such as Tableau or Power BI. For example, it displays information such as "fluctuations in the number of fraudulent applications by month" and "frequency of fraudulent applications by store."

[0534] Specific examples

[0535] 1. A user (shop crew member) detects a suspicious contract application at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into a dedicated system.

[0536] 2. The device receives this input information, temporarily stores it, validates it, and then sends it to the server, which stores it in a database and displays it on a map using GIS.

[0537] 3. The server identifies five stores within 1 km of the store in question, generates an alert, and sends it. The device displays the received alert as a pop-up, and the user can confirm the notification.

[0538] 4. The server compiles application data from the past year and displays the analysis results on the dashboard, showing that 10 fraudulent applications occurred in October.

[0539] Prompt Sentence Examples

[0540] "At 1:45 PM on October 15th, a suspicious contract application by a foreigner was detected in the store. The applicant was behaving strangely. Please send alerts to surrounding stores as well."

[0541] This will enable the creation of a system that can quickly detect fraudulent applications, share information, and issue warnings to surrounding stores.

[0542] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0543] Step 1:

[0544] A user (shop crew member) enters suspicious contract application information into a dedicated interface.

[0545] Input: Application date and time, applicant information, details of suspicious behavior (e.g., "October 15th, 13:45", "Foreigner", "Suspicious behavior").

[0546] Specific actions: Enter the required information into the input screen of a web form or dedicated application and click the "Submit" button.

[0547] Step 2:

[0548] The terminal receives the information input by the user and temporarily stores it in a local database.

[0549] Input: Application information entered by the user.

[0550] Data processing: Validate the data format in a local database to ensure consistency and that required fields are entered correctly.

[0551] Output: Data that passes validation is temporarily saved.

[0552] What happens: The data is temporarily stored in a lightweight database such as SQLite and validation is performed.

[0553] Step 3:

[0554] The terminal sends the information that has passed the validation to the server.

[0555] Input: Application information that has passed validation.

[0556] Data processing: Secure communication using the HTTPS protocol.

[0557] Output: The server receives the data via secure communication.

[0558] What happens: If validation is successful, the data is sent to the server using HTTPS.

[0559] Step 4:

[0560] The server stores the received fraudulent application information in a database.

[0561] Input: Application information sent from the terminal.

[0562] Data processing: Store the received data in a secure database (e.g., PostgreSQL).

[0563] Output: The data is saved to a database.

[0564] Specific operation: Stores the received data in a secure database.

[0565] Step 5:

[0566] The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS).

[0567] Input: Fraudulent application information retrieved from the database.

[0568] Data processing: Call GIS tools (Google Maps API; ESRI ArcGIS) to obtain store latitude and longitude information and convert it into a display format.

[0569] Output: The locations of fraudulent claims are displayed on a map.

[0570] Specific operation: Using a GIS tool, place a red marker on the map based on the acquired latitude and longitude information.

[0571] Step 6:

[0572] The server runs a database query to identify other stores located within 1 km of the store where the fraudulent claim was detected.

[0573] Input: Latitude and longitude information of the store where the fraudulent application occurred, and data of surrounding stores.

[0574] Data processing: Search for stores within 1km using an SQL query.

[0575] Output: List of other stores within 1km radius.

[0576] Specific operation: The server periodically executes queries to identify nearby stores.

[0577] Step 7:

[0578] The server generates a warning message and sends an alert to the identified surrounding stores.

[0579] Input: List of surrounding stores, fraudulent application information.

[0580] Data processing: Generate a warning message (e.g., "A fraudulent application occurred on October 15th at 1:45 PM. Please be careful") and send it via a notification service (e.g., Firebase Cloud Messaging).

[0581] Output: A warning message is sent to each store.

[0582] Specific behavior: After generating a message, an alert will be sent via email or push notification.

[0583] Step 8:

[0584] The device receives the alert and displays it to the user (shop crew) as a pop-up notification.

[0585] Input: The warning message sent by the server.

[0586] Data processing: Process received messages into popup format.

[0587] Output: Show a popup notification on the device.

[0588] What it does: When a notification is received on a specific port, the application displays a pop-up notification on the screen.

[0589] Step 9:

[0590] The server aggregates fraudulent application data from past databases and calculates the number of fraudulent applications within a specified period (for example, one year).

[0591] Input: Past fraudulent application data.

[0592] Data processing: Run the data aggregation script and count the number of items within the specified period.

[0593] Output: Number of fraudulent applications within a specified period.

[0594] Specific operation: Executes the aggregation script periodically and aggregates the results.

[0595] Step 10:

[0596] The server performs statistical analysis based on the aggregated data.

[0597] Input: Aggregated fraudulent application data.

[0598] Data processing: Perform statistical analysis using data analysis libraries such as Pandas and NumPy.

[0599] Output: Results of the statistical analysis.

[0600] Specific actions: Runs analysis scripts and calculates statistical indicators.

[0601] Step 11:

[0602] The server generates and visually displays the analysis results as dashboards and reports.

[0603] Input: Results of the statistical analysis.

[0604] Data processing: Create graphs and charts using Tableau and Power BI.

[0605] Output: Display as a dashboard or report.

[0606] Specific action: Convert the data into a format that is easy to visualize using a data visualization tool.

[0607] The above are the specific processing steps of the program of this system.

[0608] (Application example 1)

[0609] 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."

[0610] Conventional fraudulent application detection systems lack the ability to quickly notify nearby stores of fraudulent application information, making it difficult to take immediate action to prevent the spread of fraud. Furthermore, because there is no mechanism for real-time notifications using smart devices, notifications can be overlooked or responses delayed. Furthermore, there is insufficient visualization of trends based on pattern analysis of past fraudulent application data, resulting in a lack of information to take effective countermeasures.

[0611] 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.

[0612] In this invention, the server includes detection means for detecting fraudulent applications, transmission means for transmitting detected fraudulent application information to the server in real time, storage means for saving the transmitted fraudulent application information in a database, visualization means for displaying the saved fraudulent application information on a map using a geographic information system, alert means for automatically sending alerts to other stores located around the store where the fraudulent application occurred, analysis means for compiling and analyzing past fraudulent application data and outputting it as a report, and reception means for other stores that have received the fraudulent application information to receive the same as a pop-up notification via their smartphones or head-mounted displays. This makes it possible to quickly and reliably notify nearby stores of fraudulent application information and encourage them to take immediate action, and furthermore, by analyzing fraudulent application patterns based on past data, it is possible to provide information for taking effective countermeasures.

[0613] "Fraudulent application" refers to an application made with fraudulent content that violates normal procedures and standards.

[0614] "Detection means" refers to a device or part of a system for detecting fraudulent applications.

[0615] "Transmission means" refers to a device or part of a system that has the function of transmitting detected fraudulent application information to a server in real time.

[0616] "Storage means" refers to a device or part of a system that has the function of storing transmitted fraudulent application information in a database.

[0617] "Visualization means" refers to a device or part of a system that has the function of displaying stored fraudulent application information on a map using a geographic information system.

[0618] "Alert means" refers to a device or part of a system that has the function of automatically sending an alert to other stores located around the store where the fraudulent application occurred.

[0619] "Analysis means" refers to a device or part of a system that has the function of compiling and analyzing past fraudulent application data and outputting it as a report.

[0620] "Receiving means" refers to a device or part of a system that has the function of allowing other stores that receive the fraudulent application information to receive it as a pop-up notification via their smartphones or head-mounted displays.

[0621] "Geographic information system" is a general term for software and hardware used to collect and analyze geographic data and display it on a map.

[0622] A "smartphone" is a mobile device that has the same functions as a computer, despite being a mobile phone.

[0623] A "head-mounted display" refers to a device that is worn on the user's head and displays visual information.

[0624] A "pop-up notification" refers to a short message displayed on an application to immediately notify the user of important information.

[0625] A "generative AI model" refers to a mathematical model generated by artificial intelligence technology for analysis and prediction.

[0626] A "prompt" refers to a textual instruction or question that is input into a generative AI model.

[0627] This invention relates to a system that uses a smartphone or head-mounted display (HMD) to quickly detect fraudulent applications and notify nearby stores in real time. It also includes the aggregation and analysis of past fraudulent application data, and the visualization and provision of the results.

[0628] 1. Program Generation

[0629] The system mainly consists of the following components:

[0630] Detection methods for detecting fraudulent applications

[0631] A means for transmitting detected fraudulent application information to a server.

[0632] A means of storing submitted information in a database

[0633] A visualization method for displaying stored information on a map using GIS

[0634] An alerting method that automatically sends alerts to nearby stores

[0635] The store that receives the fraudulent application information receives it on their smartphone or HMD.

[0636] Analysis tool that aggregates and analyzes past data and outputs the results

[0637] 2. Explain the program's processing in natural language

[0638] The server includes the following hardware and software:

[0639] Hardware: Cloud Server

[0640] Software: Python, Flask (backend), GIS software (e.g., Folium), data analysis library (Pandas)

[0641] A smartphone and HMD are installed on the terminal side and function as follows.

[0642] Detection Method

[0643] When a user detects a fraudulent application, they enter information about the fraudulent application using a dedicated interface, including the date and time of the application, information about the applicant, and details of any suspicious behavior.

[0644] Transmission and storage methods

[0645] The device receives this input information, validates it, and then sends it to the server, which then stores it in a secure database.

[0646] Visualization tools

[0647] The server uses GIS to display the saved fraudulent application information on a map. Specifically, it obtains the location information of the store where the fraudulent application occurred and displays it as a marker on the map.

[0648] Alert and Receipt Methods

[0649] When a fraudulent application is detected, the server automatically generates an alert to nearby stores and notifies them on smartphones or HMDs, allowing users to immediately take precautions.

[0650] analytical means

[0651] The server aggregates past fraudulent application data and performs statistical analysis, and the results of this analysis are displayed visually in the form of dashboards and reports.

[0652] 3. Adding concrete examples and prompts

[0653] Specific examples

[0654] Users can enter information such as "foreigner," "October 15th, 13:45," and "suspicious behavior" on their smartphones, and an alert is instantly sent to other stores within a 1km radius. At the same time, the server analyzes fraudulent application data from the past year and displays the results on a dashboard.

[0655] Prompt Sentence Examples

[0656] Based on the information below, please design a system that notifies other nearby stores in real time when a fraudulent application is detected and analyzes past fraudulent application data.

[0657] Date and time of fraudulent application: October 15th, 13:45

[0658] Applicant information: Foreigner

[0659] Fraudulent Activity Details: Suspicious Activity

[0660] This system, configured in this way, quickly detects fraudulent applications, notifies relevant parties in real time, and provides analytical information using past data to take effective countermeasures, thereby preventing the spread of fraudulent activity and accelerating response.

[0661] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0662] Step 1:

[0663] When a user detects a fraudulent application, they use a smartphone or head-mounted display to enter the application date and time, applicant information, and details of suspicious behavior into a dedicated interface. The entered information is saved in temporary memory on the device. Input data includes the application date and time, applicant information, and details of suspicious behavior. The application information saved in temporary memory is obtained as output data.

[0664] Step 2:

[0665] The terminal validates the entered information. Specifically, it checks whether all required fields in the input data are filled in and whether the data format is correct. For example, it checks the date format and the format of the applicant information. If validation is successful, it proceeds to the next step. The input data is data in temporary memory, and the output data is the result of validation.

[0666] Step 3:

[0667] The terminal sends the information that has passed validation to the server. The transmission is done using an HTTP request (POST method). The input data is the application information on the terminal side, and the output data is the application information saved on the server side.

[0668] Step 4:

[0669] The server stores the received information in a secure database. The database is an RDBMS (Relational Database Management System) and the information is inserted into tables. The input data is the application information received by the server and the output data are the records stored in the database.

[0670] Step 5:

[0671] The server obtains latitude and longitude information based on the fraudulent application information stored in the database. This information is then displayed on a map using a geographic information system (GIS). GIS software such as Folium is used. The input data is the latitude and longitude information in the database, and the output data is the location of the fraudulent application displayed on the map.

[0672] Step 6:

[0673] The server executes a database query to identify other stores located within a certain distance (e.g., 1 km) around the store where the fraudulent claim was detected. The query results in a list of identified stores. The input data is the location information of the fraudulent claim and the surrounding stores, and the output data is a list of identified surrounding stores.

[0674] Step 7:

[0675] The server generates a warning message for the identified stores and sends an alert. The warning message includes the name of the store where the fraudulent application occurred, the date and time, and important points to note. This is sent to the smartphone or HMD. The input data is a list of identified stores, and the output data is the sent warning message.

[0676] Step 8:

[0677] The terminal receives the alert and displays it to the user as a pop-up notification. The pop-up notification contains a warning message that the user can view and respond to immediately. The input data is the warning message sent from the server, and the output data is the pop-up notification displayed to the user.

[0678] Step 9:

[0679] The server aggregates past fraudulent application data from a database and calculates the number of fraudulent applications within a specified period. Libraries such as Pandas are used for data analysis. The input data is past application information, and the output data is aggregated statistical information.

[0680] Step 10:

[0681] The server performs statistical analysis based on the aggregated data. It uses a generative AI model to analyze patterns in fraudulent application data and displays the results as a dashboard. Specific software operations include data filtering, clustering, and trend analysis. The input data is the aggregated application information, and the output data is a dashboard of the analysis results.

[0682] Through the above steps, the system of the present invention can quickly detect fraudulent applications, immediately notify relevant parties, and provide information using past data to take effective measures.

[0683] 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.

[0684] This invention relates to a system for effectively detecting and quickly responding to fraudulent applications. This system enhances risk assessment of fraudulent applications by combining fraudulent application detection, real-time information transmission, visualization using a geographic information system (GIS), alert notifications to nearby stores, analysis of past data, and an emotion engine that recognizes user emotions.

[0685] As a specific embodiment for implementing the present invention, a flow from detecting a fraudulent application to sharing information, issuing an alert, and analyzing using an emotion engine will be described.

[0686] Detecting and recording fraudulent applications

[0687] 1. When a user (shop crew member) detects a suspicious contract application, they use a dedicated interface to enter the suspicious contract application information into the system. This includes the application date and time, applicant information, and details of the suspicious behavior. The emotion engine also analyzes the user's emotional state in real time and records this information.

[0688] 2. The device receives the entered information, first stores it in a local database, and then validates it to ensure that required fields are filled in properly and that the data format is correct.

[0689] 3. The terminal sends the information that has passed validation to the server, where it is stored in a secure database.

[0690] Real-time processing and visualization of information

[0691] 1. The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS). Here, the server obtains the latitude and longitude information of the store and, in conjunction with the GIS API, displays the location of the fraudulent application on the map with a red icon or a specific color, clearly showing the location of the fraudulent application.

[0692] 2. The emotion engine analyzes the user's emotional data when a fraudulent application is made, and integrates and displays the results in a visualization tool. This allows users to visually confirm the risk assessment of fraudulent applications.

[0693] Alert notifications to nearby stores

[0694] 1. The server uses a database query to identify other stores within 1 km of the store where the fraudulent claim was detected. The query returns a list of nearby stores.

[0695] 2. The server automatically generates a warning message and sends an alert to the identified nearby stores. The alert includes the store where the fraudulent application occurred, the date and time, and points to note.

[0696] 3. The terminal receives the alert and displays it to the user (shop crew) as a pop-up notification, allowing the user to immediately become alert to suspicious applications and take appropriate measures.

[0697] Historical data analysis

[0698] 1. The server aggregates past fraudulent application data from the database and calculates the number of fraudulent applications within a specified period (for example, one year). This is achieved by performing statistical data processing.

[0699] 2. The server performs statistical analysis on the aggregated data to identify which stores have experienced fraudulent applications and how frequently. The results are then generated as a dashboard or report.

[0700] 3. The emotion engine analyzes past application data and user emotional data to identify patterns of fraudulent applications, improving the accuracy of detecting subtle fraudulent behavior.

[0701] 4. The analysis results generated by the server are sent to the device and displayed visually on a dashboard, allowing users (administrators and shop crew) to understand trends and patterns in fraudulent applications and use this information to take future countermeasures.

[0702] Specific examples

[0703] 1. A user (shop crew member) detects a suspicious contract application from a foreigner at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into the dedicated system. At the same time, the emotion engine analyzes the user's facial expression and tone of voice, and records their emotional state, such as "tension" or "anxiety."

[0704] 2. The device receives this input information, validates it, and then sends it to the server, which stores it in a database and displays it on a map, integrating GIS and emotion data.

[0705] 3. The server identifies five stores within 1 km of the store in question, generates an alert, and sends it. The device displays the received alert as a pop-up, and the user can confirm the notification.

[0706] 4. The server aggregates application data and emotion data from the past year, and displays the analysis results on the dashboard, showing that 10 fraudulent applications occurred in October. The emotion engine also evaluates the risk of fraudulent applications based on the emotion data, and reflects this in the analysis results.

[0707] This series of processes, combined with emotional data, strengthens risk assessment of contract fraud, enabling swift and effective response.

[0708] The processing flow will be explained below.

[0709] Step 1:

[0710] A user (shop crew member) detects a suspicious contract application and enters the suspicious contract application information into the system through a dedicated interface. The information entered includes the date and time of the application, applicant information, and details of suspicious behavior. An emotion engine also analyzes the user's facial expressions and tone of voice in real time, and records emotional data such as "tension" and "anxiety."

[0711] Step 2:

[0712] The device receives this information, temporarily stores it in a local database, and then validates the information to ensure that required fields are filled in properly and that the data format is correct.

[0713] Step 3:

[0714] The terminal sends the information that has passed validation to the server, where it is stored in a secure database.

[0715] Step 4:

[0716] The server processes the fraudulent application information and emotion data stored in the database in real time and displays it on a map using a geographic information system (GIS). It obtains the latitude and longitude information of stores and, by linking with the GIS API, shows the locations of fraudulent applications visually by displaying them on the map with red icons or specific colors. At the same time, it performs a risk assessment using emotion data and visualizes the results.

[0717] Step 5:

[0718] The server uses a database query to identify other stores within 1 km of the store where the fraudulent claim was detected, and the stores listed by the query are then automatically targeted for alert notifications.

[0719] Step 6:

[0720] The server automatically generates a warning message and sends an alert to the identified surrounding stores. This alert includes the store where the fraudulent application occurred, the date and time, points to be careful about, and the risk assessment results based on the emotion engine.

[0721] Step 7:

[0722] The terminal receives the alert and displays it to the user (shop crew) as a pop-up notification, allowing the user to immediately become alert to suspicious applications and take appropriate measures.

[0723] Step 8:

[0724] The server aggregates past fraudulent application data and emotion data from the database and calculates the number of fraudulent applications and emotion trends within a specified period (e.g., one year). This is achieved by performing statistical data processing.

[0725] Step 9:

[0726] The server performs statistical analysis based on the aggregated data to determine which stores have experienced fraudulent applications and how frequently they have occurred, as well as the associated emotional data to determine risk assessment results. These results are then generated as dashboards and reports.

[0727] Step 10:

[0728] The analysis results generated by the server are sent to the terminal and displayed visually on a dashboard, allowing users (administrators and shop crew) to understand trends and patterns of fraudulent applications and user emotional tendencies, and use this information to help with future countermeasures.

[0729] Specific examples

[0730] 1. A user (shop crew member) detects a suspicious contract application from a foreigner at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into the dedicated system. At the same time, the emotion engine analyzes the user's facial expression and tone of voice, and records their emotional state, such as "tension" or "anxiety."

[0731] 2. The device receives this input information, validates it, and then sends it to the server, which stores it in a database and displays it on a map, integrating GIS and emotion data.

[0732] 3. The server identifies five stores within 1 km of the store in question, generates an alert, and sends it. The device displays the received alert as a pop-up, and the user can confirm the notification.

[0733] 4. The server aggregates application data and emotion data from the past year, and displays the analysis results on the dashboard, showing that 10 fraudulent applications occurred in October. The emotion engine also evaluates the risk of fraudulent applications based on the emotion data, and reflects this in the analysis results.

[0734] This series of processes, combined with emotional data, strengthens risk assessment of contract fraud, enabling swift and effective response.

[0735] Example 2

[0736] 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."

[0737] Conventional fraudulent application detection systems have had issues with delayed response after detecting fraudulent applications and providing only limited information. Furthermore, risk assessment is insufficient because the system does not take into account the user's emotional state. As a result, early detection of fraudulent applications and effective implementation of preventative measures are sometimes ineffective. Furthermore, there is a lack of a way to visually grasp the location of fraudulent applications and the surrounding situation.

[0738] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0739] In this invention, the server includes application means for detecting fraudulent applications, transmission means for transmitting detected fraudulent application information to the server in real time, storage means for saving the transmitted fraudulent application information in a database, visualization means for displaying the saved fraudulent application information on a map using a geographic information system, emotion analysis means for analyzing the emotional state of users at the location where the fraudulent application occurred and recording the information in real time, alert means for automatically sending alerts to other locations located in the vicinity of the location where the fraudulent application occurred, and analysis means for compiling and analyzing the information based on past fraudulent application information and the emotional state of users and outputting it as a report. This significantly improves risk assessment of fraudulent applications and enables quick and effective response.

[0740] "Fraudulent application" refers to an application or attempted contract made with fraudulent intent.

[0741] "Application method" refers to the interface or mechanism for detecting fraudulent applications.

[0742] "Transmission means" refers to the method or technology for transmitting detected fraudulent application information to a server in real time.

[0743] "Storage means" refers to a mechanism for safely storing submitted fraudulent application information in a database.

[0744] "Visualization means" refers to technology that displays stored fraudulent application information on a map using a geographic information system.

[0745] "Emotion analysis means" refers to technology that analyzes the emotional state of users at the location where fraudulent applications occur and records that information in real time.

[0746] "Alert method" refers to a mechanism that automatically sends a warning to other locations located in the vicinity of the location where the fraudulent application occurred.

[0747] "Analysis methods" refers to technology for compiling and analyzing information based on past fraudulent application information and the user's emotional state, and outputting it as a report.

[0748] A "geographic information system" refers to a system that handles geospatial information and visualizes data on a map.

[0749] "User" refers to an individual or person with a role who uses this system to detect, record, and address fraudulent applications.

[0750] "Server" refers to a computer device that manages the processing of the entire system and collects, stores, and processes fraudulent application information and emotion analysis data.

[0751] "Database" refers to an information management system for organizing and storing fraudulent application information and related data.

[0752] The present invention provides a system for effectively detecting and quickly responding to fraudulent claims, which enhances risk assessment of fraudulent claims by combining fraudulent claim detection, real-time information transmission, visualization using a geographic information system (GIS), alert notification to other locations in the vicinity, analysis of historical data, and user sentiment analysis.

[0753] Detecting and recording fraudulent applications

[0754] First, when a user (shop crew member) detects a suspicious contract application, they use a dedicated interface to enter the date and time of the application, applicant information, and details of the suspicious behavior into the system. As this information is entered, an emotion engine analyzes the user's emotional state (e.g., tension, anxiety) in real time, and this information is also recorded. This analysis uses technology that analyzes facial expressions and tone of voice using a camera and microphone.

[0755] The device then temporarily stores this information in a local database and performs validation, such as checking for missing required fields and checking the date format. If the information passes validation, it is sent from the device to the server, where it is stored in a secure database.

[0756] Real-time processing and visualization of information

[0757] The server processes the stored fraudulent application information in real time and displays it on a map using a geographic information system (GIS), such as Google Maps API, to clearly indicate the location of fraudulent applications using, for example, a red icon.

[0758] The emotion engine also integrates the analyzed emotion data into visualization tools and displays them on a map. Emotional states are displayed as appropriate icons (e.g., emoji faces), allowing users to visually assess the risk of fraudulent applications.

[0759] Alert notifications to nearby stores

[0760] The server uses a database query to identify other locations within 1 km of the location where the fraudulent claim was detected. It uses SQL queries to compile a list of nearby locations and then generates and sends out an alert. The alert includes the location, date, and time of the fraudulent claim, as well as any important points to note.

[0761] The terminal receives this alert and displays it to the user (shop crew) as a pop-up notification, allowing the user to immediately check the information and take necessary measures.

[0762] Historical data analysis

[0763] The server aggregates past fraudulent application data from the database and calculates the number of fraudulent applications within a specified period (e.g., the past year). This process involves extracting the data using SQL queries and performing statistical processing and visualization using Python tools such as Pandas and Matplotlib.

[0764] The emotion engine combines and analyzes past fraudulent application data with user emotion data to identify patterns of fraudulent applications. It uses a clustering algorithm to extract specific behavioral and emotional patterns. The server visually displays the results of this analysis on a dashboard, allowing users (administrators and shop crew) to understand trends and patterns in fraudulent applications and develop preventative measures.

[0765] Specific examples

[0766] For example, a user (shop crew member) detects a suspicious contract application made by a foreigner at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into the dedicated system. At the same time, the emotion engine analyzes the user's facial expressions and tone of voice, and records their emotional state, such as "tension" or "anxiety."

[0767] The device receives this information, validates it, and then sends it to the server, which stores it in a database and displays it on a map, integrating GIS and emotion data.

[0768] The server identifies five other locations within 1 km of the location and generates and sends an alert, which the device displays as a pop-up for the user to confirm.

[0769] The server aggregates application data and emotion data from the past year, and displays the analysis results on the dashboard, showing that 10 fraudulent applications occurred in October. The emotion engine also evaluates the risk of fraudulent applications based on the emotion data, and reflects this in the analysis results.

[0770] When using a generative AI model, you might use prompts like the following:

[0771] "At 13:45 on October 15th, a foreigner exhibited suspicious behavior. The user's emotional state was 'tension' and 'anxiety'."

[0772] The comprehensive operation of the system as described above will strengthen risk assessment of fraudulent applications and enable swift and effective responses.

[0773] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0774] Program processing steps

[0775] Detecting and recording fraudulent applications

[0776] Step 1:

[0777] A user (shop crew member) detects a suspicious contract application. Using a dedicated interface, the user enters the application date and time, applicant information, and details of suspicious behavior. The entered data is in text format and separated into specific fields. This input information is sent directly to the next processing step, while the emotion engine simultaneously analyzes the user's emotional state. This analysis uses a camera and microphone to evaluate facial expressions and tone of voice in real time.

[0778] Step 2:

[0779] The terminal receives the information entered by the user. The entered data is temporarily stored in a local database and validated. Specific validation details include whether all required fields (e.g., application date and time, applicant information) are filled in, whether the date format is correct, and whether the details of suspicious activity are 50 characters or more. Information that passes validation is sent to the next process as a new data structure.

[0780] Step 3:

[0781] The device sends the information that has passed validation to the server. The data is encrypted during transmission. The transmitted data includes the application date and time, applicant information, details of suspicious behavior, and emotion analysis results. The server receives this data and stores it in a secure database.

[0782] Real-time processing and visualization of information

[0783] Step 4:

[0784] The server retrieves the fraudulent application information stored in the database and begins processing it in real time. The input data here is detailed information about the fraudulent application and the results of sentiment analysis. The server retrieves the latitude and longitude information of the store from a GIS API (e.g., Google Maps API) and displays the location of the fraudulent application on a map with a red icon. This display data is generated in real time through requests to the GIS API.

[0785] Step 5:

[0786] The emotion engine takes the analyzed emotion data and integrates the results into a visualization method. Specifically, it adds icons (e.g., emoji faces) indicating the emotional state to the locations of fraudulent claims on a map. The input data includes the emotion analysis results, and the output data consists of the visual display information of the GIS.

[0787] Alert notifications to nearby stores

[0788] Step 6:

[0789] The server uses a database query to identify other locations within 1 km of the location where the fraudulent claim was detected. The input data for this process includes the latitude and longitude of the fraudulent claim, and uses an SQL query to list other nearby locations. The output data is a list of the identified nearby locations.

[0790] Step 7:

[0791] The server generates a warning message for the identified nearby locations and sends an alert. The alert contains the location, date, and time of the fraudulent application, as well as points to note, and this information is generated automatically. The input data is the list of identified nearby locations and the fraudulent application information, and the output data is the alert message and its transmission status.

[0792] Step 8:

[0793] The alert received by the terminal is displayed to the user (shop crew) as a pop-up notification. Specifically, the user is immediately notified of the warning through desktop or mobile notifications. The input data of this process is the alert message sent from the server, and the output data is the notification confirmation status sent to the user.

[0794] Historical data analysis

[0795] Step 9:

[0796] The server aggregates past fraudulent application data from the database. It uses an SQL query to extract data to calculate the number of fraudulent applications for a specified period (e.g., the past year). The input data is detailed information about fraudulent applications, and the output data is the number of fraudulent applications for the specified period.

[0797] Step 10:

[0798] The server performs statistical analysis based on the collected data. Python's Pandas and Matplotlib are used to generate graphs and heat maps to visualize the number and location of fraudulent applications. The input data is the number of fraudulent applications within a specified period, and the output data is visualized data of the analysis results.

[0799] Step 11:

[0800] The emotion engine combines and analyzes past fraudulent application data with user emotion data. It uses a clustering algorithm to extract specific behavioral and emotional patterns. The input data is fraudulent application information and emotion data, and the output data is the extracted behavioral and emotional patterns.

[0801] Step 12:

[0802] The analysis results generated by the server are sent to the terminal and displayed visually on a dashboard. This allows users (administrators and shop crew) to understand trends and patterns of fraudulent applications and use them to develop future countermeasures. The input data is the analysis results sent from the server, and the output data is the visual display information on the dashboard.

[0803] This series of processing steps significantly strengthens the risk assessment of fraudulent applications and enables a fast and effective response.

[0804] (Application example 2)

[0805] 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."

[0806] Conventional fraudulent application detection systems can detect fraudulent applications and issue warnings, but they ignore the user's emotional state and lack information to better understand fraudulent behavior. Furthermore, they lack the ability to visualize fraudulent application information or send alerts to nearby stores in real time, making it difficult to respond immediately. Furthermore, analysis of past fraudulent application data is insufficient, making it difficult to assess the risk of recurrence.

[0807] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0808] In this invention, the server includes application means for detecting fraudulent applications, transmission means for transmitting detected fraudulent application information to the server in real time, storage means for saving the transmitted fraudulent application information in a database, visualization means for displaying the saved fraudulent application information on a map using a geographic information system, alert means for automatically sending alerts to other stores located around the store where the fraudulent application occurred, analysis means for aggregating and analyzing past fraudulent application data and outputting it as a report, emotion analysis means for analyzing the user's emotional state from application data, and means for integrating the user's emotional state into the fraudulent application information and displaying it on the visualization means. This improves the accuracy of fraudulent application detection and enables quick and effective response.

[0809] "Fraudulent application" refers to an act of violating prescribed procedures and attempting to obtain unfair benefits.

[0810] "Application Method" means the method for detecting fraudulent applications and entering information into the system.

[0811] "Transmission means" refers to a means for transmitting detected fraudulent application information to a server in real time.

[0812] "Storage Means" refers to the means for storing submitted fraudulent application information in a database.

[0813] The "visualization means" is a means for displaying the stored fraudulent application information on a map using a geographic information system.

[0814] "Alert means" refers to a means for automatically issuing a warning to other stores located around the store where the fraudulent application occurred.

[0815] "Analysis methods" refers to the means for compiling and analyzing past fraudulent application data and outputting it as a report.

[0816] "Emotion analysis means" means means for analyzing the user's emotional state from application data.

[0817] "Integration means" refers to a means for integrating and displaying a user's emotional state with fraudulent application information.

[0818] The system for implementing this invention combines multiple means for effectively detecting fraudulent applications and quickly responding to them. The specific flow and the hardware and software used are described below.

[0819] Overall system overview

[0820] 1. Detecting fraudulent applications

[0821] When a user (store staff member) detects a fraudulent application, they enter the fraudulent application information into the system using a dedicated interface.

[0822] The emotion analysis means analyzes the user's emotional state at the time of input in real time and adds that information.

[0823] 2. Real-time processing and information transmission

[0824] The terminal receives the input information and first temporarily stores it in a local database.

[0825] Validate information to ensure required fields are filled in properly and that data is formatted correctly.

[0826] The terminal sends the information that has passed the validation to the server.

[0827] The server receives the information and stores it in a database.

[0828] 3. Visualization

[0829] The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS).

[0830] The locations of fraudulent applications are clearly displayed on a map, and emotional states are also integrated and visualized.

[0831] 4. Store-to-store alerts

[0832] The server automatically identifies other stores within a certain distance of the store where the fraudulent application was detected and sends an alert.

[0833] The terminal displays the received alert to the user in a pop-up notification.

[0834] 5. Historical Data Analysis

[0835] The server compiles and analyzes past fraudulent application data from the database and calculates the number of fraudulent applications for a specified period.

[0836] The analysis results are output as dashboards and reports so that users can view them.

[0837] Hardware and software used

[0838] EmotionEngine: A library for analyzing a user's emotional state. This library analyzes emotions from voice and facial expressions in real time.

[0839] GISMap: A library for displaying the locations of fraudulent applications on a map using a geographic information system.

[0840] NotificationManager: A library for generating cross-store alerts and notifying other stores.

[0841] DatabaseManager: A library for managing the storage and retrieval of fraudulent application data.

[0842] Specific examples

[0843] A user (store staff member) detects a suspicious contract application from a foreigner at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into a dedicated interface. At the same time, an emotion analysis tool analyzes the user's emotional state and records it as "tension" or "anxiety."

[0844] The device receives this input information, validates it, and then sends it to the server, which stores it in a database and displays it on a map, integrating GIS and emotion data.

[0845] The server identifies five stores within a certain distance of the store in question, generates an alert, and sends it out. The alert is received by the device and displayed as a pop-up, allowing the user to confirm the notification.

[0846] The server compiles application data and emotion data from the past year, and displays on the dashboard that 10 fraudulent applications occurred in October. In addition, the emotion analysis means evaluates the risk of fraudulent applications based on the emotion data, and reflects this in the analysis results.

[0847] Prompt Sentence Examples

[0848] Data for fraudulent application warning system

[0849] User Input: I'm nervous

[0850] Applicant information: Foreigners

[0851] Suspicious Activity: Suspicious activity

[0852] Location information: (35.6895, 139.6917)

[0853] In this way, a system embodying the present invention is constructed, which improves the accuracy of detecting fraudulent applications and enables prompt and effective responses.

[0854] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0855] Step 1:

[0856] When a user detects a fraudulent application, they use a dedicated interface to input information about the fraudulent application into the system. Based on the input, the date and time of the application, applicant information, details of suspicious behavior, and the user's emotional state are collected. Using an emotion analysis means, the user's emotional state is analyzed and recorded together with the application information.

[0857] Step 2:

[0858] The terminal receives the information entered by the user and temporarily stores it in a local database. At the same time, the terminal validates the input information to ensure that required fields are entered properly and that the data format is correct.

[0859] Step 3:

[0860] The terminal sends the information that has passed validation to the server. The input is the user's fraudulent application information and emotion data. After transmission, the server receives the information and stores it in a secure database. At this point, the server rechecks the integrity of the information.

[0861] Step 4:

[0862] The server processes the fraudulent application information stored in the database in real time. To display the locations of fraudulent applications on a map using a geographic information system (GIS), the location data of the fraudulent application information is sent to a GIS API, and the locations of the fraudulent applications are displayed on the map.

[0863] Step 5:

[0864] The server visualizes the emotional data obtained using emotion analysis techniques. In addition to the locations of fraudulent applications, the user's emotional state is also integrated and displayed on a map, allowing users to intuitively confirm risk assessment.

[0865] Step 6:

[0866] The server executes a query against the database to automatically identify other stores located within a certain distance of the store where the fraudulent application was detected. The input is the location data of the store where the fraudulent application occurred, and the output is a list of surrounding stores.

[0867] Step 7:

[0868] The server generates a warning message to the identified surrounding stores, which includes the store where the fraudulent application occurred, the date and time, and points to note, and is automatically sent by an alert means.

[0869] Step 8:

[0870] The device displays the received alert as a pop-up notification to the user, allowing the user to check the alert displayed on the screen and take immediate action.

[0871] Step 9:

[0872] The server aggregates and analyzes past fraudulent application data. The input is past fraudulent application data and sentiment data, and statistical data processing is performed to calculate the number of fraudulent applications within a period and a risk assessment. The aggregated results are output to a dashboard or report.

[0873] Step 10:

[0874] The server displays the aggregated results and risk assessments on a dashboard, which users can view to understand trends and patterns in fraudulent applications and obtain information to take appropriate measures.

[0875] The above are the processing steps of the system for carrying out this invention, and the specific operations and inputs / outputs are clearly stated for each step.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] [Third embodiment]

[0880] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0881] 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.

[0882] 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).

[0883] 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.

[0884] 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.

[0885] 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).

[0886] 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.

[0887] 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.

[0888] 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.

[0889] 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.

[0890] 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.

[0891] 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."

[0892] This invention relates to a system for effectively detecting fraudulent applications and quickly responding to them. This system is composed of functions including fraudulent application detection, real-time information transmission, visualization using a geographic information system (GIS), alert notification to nearby stores, and analysis of past data.

[0893] As a specific embodiment for implementing the present invention, a flow from detecting a fraudulent application to sharing information, issuing an alert, and analyzing the information will be described.

[0894] Detecting and recording fraudulent applications

[0895] 1. When a user (shop crew member) detects a fraudulent application, they use a dedicated interface to enter the suspicious contract application information into the system, including the application date and time, applicant information, and details of the suspicious behavior.

[0896] 2. The device receives the entered information, first stores it in a local database, and then validates it to ensure that required fields are filled in properly and that the data format is correct.

[0897] 3. The terminal sends the information that has passed validation to the server, where it is stored in a secure database.

[0898] Real-time processing and visualization of information

[0899] 1. The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS). Using GIS, the location of the store can be accurately displayed.

[0900] 2. In order to visually display information about fraudulent applications, the server obtains the latitude and longitude information of the store and displays the location of the fraudulent application on a map with a red icon or a specific color, making it clear where the fraudulent application occurred.

[0901] Alert notifications to nearby stores

[0902] 1. The server runs a database query to identify other stores located within 1 km of the store where the fraudulent claim was detected.

[0903] 2. The server automatically generates a warning message and sends an alert to the identified nearby stores. The alert includes the store where the fraudulent application occurred, the date and time, and points to note.

[0904] 3. The terminal receives the alert and displays it to the user (shop crew) as a pop-up notification, allowing them to immediately become alert to any suspicious applications.

[0905] Historical data analysis

[0906] 1. The server aggregates past fraudulent application data from the database and calculates the number of fraudulent applications within a specified period (for example, one year).

[0907] 2. The server performs statistical analysis based on the collected data to determine which stores are experiencing fraudulent applications and how frequently.

[0908] 3. The server generates and visually displays the analysis results as dashboards and reports, allowing administrators to understand trends and patterns in fraudulent applications and obtain information to take effective measures.

[0909] Specific examples

[0910] 1. A user (shop crew member) detects a suspicious contract application by a foreigner at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into a dedicated system.

[0911] 2. The device receives this input information, validates it, and then sends it to the server, which stores it in a database and displays it on a map using GIS.

[0912] 3. The server identifies five stores within 1 km of the store in question, generates an alert, and sends it. The device displays the received alert as a pop-up, and the user can confirm the notification.

[0913] 4. The server compiles application data from the past year and displays the analysis results on the dashboard, showing that 10 fraudulent applications occurred in October.

[0914] This series of processes enables fraudulent contracts to be detected quickly and dealt with effectively.

[0915] The processing flow will be explained below.

[0916] Step 1:

[0917] A user (shop crew member) detects a suspicious contract application and enters the suspicious contract application information into the system through a dedicated interface. The information entered includes the application date and time, applicant information, and details of the suspicious behavior.

[0918] Step 2:

[0919] The device receives the entered information and temporarily stores it in a local database, while simultaneously validating the information to ensure that required fields are filled in properly and that the data format is correct.

[0920] Step 3:

[0921] The terminal sends the information that has passed validation to the server, where it is stored in a secure database.

[0922] Step 4:

[0923] The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS). Here, the latitude and longitude information of the store is acquired, and by linking with the GIS API, the location of the fraudulent application is clearly displayed by showing it on the map with a red icon or a specific color.

[0924] Step 5:

[0925] The server uses a database query to identify other stores within 1 km of the store where the fraudulent claim was detected. The query returns a list of nearby stores.

[0926] Step 6:

[0927] The server automatically generates a warning message and sends an alert to the identified nearby stores, which includes the store where the fraudulent application occurred, the date and time, and points to note.

[0928] Step 7:

[0929] The terminal receives the alert and displays it to the user (shop crew) as a pop-up notification, allowing the user to immediately become alert to suspicious applications and take appropriate measures.

[0930] Step 8:

[0931] The server aggregates past fraudulent application data from the database and calculates the number of fraudulent applications within a specified period (e.g., one year). This is achieved by performing statistical data processing.

[0932] Step 9:

[0933] The server performs statistical analysis on the aggregated data to identify which stores are experiencing fraudulent applications and how frequently they occur, and generates the results as dashboards and reports.

[0934] Step 10:

[0935] The analysis results generated by the server are sent to the device and displayed visually on a dashboard, allowing users (administrators and shop crew) to understand trends and patterns in fraudulent applications and use this information to take future countermeasures.

[0936] Example 1

[0937] 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."

[0938] The problem to be solved by this invention is to provide a system for effectively detecting fraudulent applications and responding quickly. Specifically, the object is to provide a system that can efficiently and in real time detect fraudulent applications, share information, issue alerts, and analyze past data.

[0939] 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.

[0940] In this invention, the server includes: application means for detecting fraudulent applications; transmission means for transmitting detected fraudulent application information to the server in real time; storage means for saving the sent fraudulent application information in a database; visualization means for displaying the saved fraudulent application information on a map using a geographic information system; alert means for automatically sending alerts to other stores located around the store where the fraudulent application occurred; analysis means for compiling and analyzing past fraudulent application data and outputting it as a report; validation means for validating input data when fraudulent application information is entered and checking required fields and data format; warning generation means for generating and sending warning messages to multiple identified surrounding stores; and visualization means for acquiring latitude and longitude information of stores and displaying them on a map with specific colors and icons to visually display the fraudulent application status. This enables rapid detection of fraudulent applications, information sharing, and warnings to surrounding stores.

[0941] A "fraudulent application" is an application made using unauthorized or fraudulent information.

[0942] The "application means" is a means for detecting fraudulent applications, and includes an interface for users to input information.

[0943] The "transmission means" is a means for transmitting detected fraudulent application information to the server in real time.

[0944] The "storage means" is a means for storing the transmitted fraudulent application information in a database.

[0945] The "visualization means" is a means for displaying the stored fraudulent application information on a map using a geographic information system.

[0946] The "alert means" is a means for automatically sending an alert to other stores located around the store where the fraudulent application occurred.

[0947] "Analysis methods" are means for compiling and analyzing past fraudulent application data and outputting it as a report.

[0948] "Validation means" refers to a means for validating input data and checking required fields and data format when fraudulent application information is entered.

[0949] The "warning generation means" is a means for generating and transmitting a warning message to the identified surrounding stores.

[0950] The "visualization means" is a means for obtaining the latitude and longitude information of the store and showing it on a map with a specific color or icon in order to visually display the fraudulent application status.

[0951] This invention relates to a system for effectively detecting fraudulent applications and quickly responding to them. This system is composed of functions including fraudulent application detection, real-time information transmission, visualization using a geographic information system (GIS), alert notification to nearby stores, and analysis of past data.

[0952] Detecting and recording fraudulent applications

[0953] A user (shop crew member) uses a dedicated interface to enter information about suspicious contract applications into the system, including the date and time of the application, applicant information, and details of suspicious behavior.

[0954] The terminal receives information entered by the user and temporarily stores it in a local database. A lightweight database such as SQLite is used for the local database. The saved data is then validated to ensure the input format and required fields are entered correctly. Information that passes validation is sent to the server via secure communication using the HTTPS protocol. The server stores the received data in a secure database (for example, PostgreSQL).

[0955] Real-time processing and visualization of information

[0956] The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS). GIS tools include Google Maps API and ESRI ArcGIS. The server periodically runs a script to detect new data and obtains new fraudulent application information. Based on the obtained information, the GIS tool is called, the latitude and longitude information of the store is obtained, and a red marker is placed at a specific location on the map to visually indicate the location of the fraudulent application.

[0957] Alert notifications to nearby stores

[0958] The server executes a database query (SQL query) to identify other stores within 1 km of the store where the fraudulent application was detected. A warning message is generated and sent to the identified stores via email or a push notification system (e.g., Firebase Cloud Messaging). The warning message includes the store where the fraudulent application occurred, the date and time, and important points to note.

[0959] The terminal receives the alert and displays it to the user (shop crew) as a pop-up notification. The application running on the terminal receives notifications from the server on a specific port and displays the received message on the screen in a pop-up format.

[0960] Historical data analysis

[0961] The server aggregates data on fraudulent applications from the past database and calculates the number of fraudulent applications within a specified period (for example, one year). A calculation script is run periodically on the server to extract fraudulent application information from the database for the past year and count the number of cases within the period. A statistical analysis of the extracted data is performed using a data analysis library such as Pandas or NumPy to calculate how frequently fraudulent applications occur at each store. Based on the analysis results, a dashboard is created in the form of graphs and charts using a data visualization tool such as Tableau or Power BI. For example, it displays information such as "fluctuations in the number of fraudulent applications by month" and "frequency of fraudulent applications by store."

[0962] Specific examples

[0963] 1. A user (shop crew member) detects a suspicious contract application at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into a dedicated system.

[0964] 2. The device receives this input information, temporarily stores it, validates it, and then sends it to the server, which stores it in a database and displays it on a map using GIS.

[0965] 3. The server identifies five stores within 1 km of the store in question, generates an alert, and sends it. The device displays the received alert as a pop-up, and the user can confirm the notification.

[0966] 4. The server compiles application data from the past year and displays the analysis results on the dashboard, showing that 10 fraudulent applications occurred in October.

[0967] Prompt Sentence Examples

[0968] "At 1:45 PM on October 15th, a suspicious contract application by a foreigner was detected in the store. The applicant was behaving strangely. Please send alerts to surrounding stores as well."

[0969] This will enable the creation of a system that can quickly detect fraudulent applications, share information, and issue warnings to surrounding stores.

[0970] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0971] Step 1:

[0972] A user (shop crew member) enters suspicious contract application information into a dedicated interface.

[0973] Input: Application date and time, applicant information, details of suspicious behavior (e.g., "October 15th, 13:45", "Foreigner", "Suspicious behavior").

[0974] Specific actions: Enter the required information into the input screen of a web form or dedicated application and click the "Submit" button.

[0975] Step 2:

[0976] The terminal receives the information input by the user and temporarily stores it in a local database.

[0977] Input: Application information entered by the user.

[0978] Data processing: Validate the data format in a local database to ensure consistency and that required fields are entered correctly.

[0979] Output: Data that passes validation is temporarily saved.

[0980] What happens: The data is temporarily stored in a lightweight database such as SQLite and validation is performed.

[0981] Step 3:

[0982] The terminal sends the information that has passed the validation to the server.

[0983] Input: Application information that has passed validation.

[0984] Data processing: Secure communication using the HTTPS protocol.

[0985] Output: The server receives the data via secure communication.

[0986] What happens: If validation is successful, the data is sent to the server using HTTPS.

[0987] Step 4:

[0988] The server stores the received fraudulent application information in a database.

[0989] Input: Application information sent from the terminal.

[0990] Data processing: Store the received data in a secure database (e.g., PostgreSQL).

[0991] Output: The data is saved to a database.

[0992] Specific operation: Stores the received data in a secure database.

[0993] Step 5:

[0994] The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS).

[0995] Input: Fraudulent application information retrieved from the database.

[0996] Data processing: Call GIS tools (Google Maps API; ESRI ArcGIS) to obtain store latitude and longitude information and convert it into a display format.

[0997] Output: The locations of fraudulent claims are displayed on a map.

[0998] Specific operation: Using a GIS tool, place a red marker on the map based on the acquired latitude and longitude information.

[0999] Step 6:

[1000] The server runs a database query to identify other stores located within 1 km of the store where the fraudulent claim was detected.

[1001] Input: Latitude and longitude information of the store where the fraudulent application occurred, and data of surrounding stores.

[1002] Data processing: Search for stores within 1km using an SQL query.

[1003] Output: List of other stores within 1km radius.

[1004] Specific operation: The server periodically executes queries to identify nearby stores.

[1005] Step 7:

[1006] The server generates a warning message and sends an alert to the identified surrounding stores.

[1007] Input: List of surrounding stores, fraudulent application information.

[1008] Data processing: Generate a warning message (e.g., "A fraudulent application occurred on October 15th at 1:45 PM. Please be careful") and send it via a notification service (e.g., Firebase Cloud Messaging).

[1009] Output: A warning message is sent to each store.

[1010] Specific behavior: After generating a message, an alert will be sent via email or push notification.

[1011] Step 8:

[1012] The device receives the alert and displays it to the user (shop crew) as a pop-up notification.

[1013] Input: The warning message sent by the server.

[1014] Data processing: Process received messages into popup format.

[1015] Output: Show a popup notification on the device.

[1016] What it does: When a notification is received on a specific port, the application displays a pop-up notification on the screen.

[1017] Step 9:

[1018] The server aggregates fraudulent application data from past databases and calculates the number of fraudulent applications within a specified period (for example, one year).

[1019] Input: Past fraudulent application data.

[1020] Data processing: Run the data aggregation script and count the number of items within the specified period.

[1021] Output: Number of fraudulent applications within a specified period.

[1022] Specific operation: Executes the aggregation script periodically and aggregates the results.

[1023] Step 10:

[1024] The server performs statistical analysis based on the aggregated data.

[1025] Input: Aggregated fraudulent application data.

[1026] Data processing: Perform statistical analysis using data analysis libraries such as Pandas and NumPy.

[1027] Output: Results of the statistical analysis.

[1028] Specific actions: Runs analysis scripts and calculates statistical indicators.

[1029] Step 11:

[1030] The server generates and visually displays the analysis results as dashboards and reports.

[1031] Input: Results of the statistical analysis.

[1032] Data processing: Create graphs and charts using Tableau and Power BI.

[1033] Output: Display as a dashboard or report.

[1034] Specific action: Convert the data into a format that is easy to visualize using a data visualization tool.

[1035] The above are the specific processing steps of the program of this system.

[1036] (Application example 1)

[1037] 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."

[1038] Conventional fraudulent application detection systems lack the ability to quickly notify nearby stores of fraudulent application information, making it difficult to take immediate action to prevent the spread of fraud. Furthermore, because there is no mechanism for real-time notifications using smart devices, notifications can be overlooked or responses delayed. Furthermore, there is insufficient visualization of trends based on pattern analysis of past fraudulent application data, resulting in a lack of information to take effective countermeasures.

[1039] 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.

[1040] In this invention, the server includes detection means for detecting fraudulent applications, transmission means for transmitting detected fraudulent application information to the server in real time, storage means for saving the transmitted fraudulent application information in a database, visualization means for displaying the saved fraudulent application information on a map using a geographic information system, alert means for automatically sending alerts to other stores located around the store where the fraudulent application occurred, analysis means for compiling and analyzing past fraudulent application data and outputting it as a report, and reception means for other stores that have received the fraudulent application information to receive the same as a pop-up notification via their smartphones or head-mounted displays. This makes it possible to quickly and reliably notify nearby stores of fraudulent application information and encourage them to take immediate action, and furthermore, by analyzing fraudulent application patterns based on past data, it is possible to provide information for taking effective countermeasures.

[1041] "Fraudulent application" refers to an application made with fraudulent content that violates normal procedures and standards.

[1042] "Detection means" refers to a device or part of a system for detecting fraudulent applications.

[1043] "Transmission means" refers to a device or part of a system that has the function of transmitting detected fraudulent application information to a server in real time.

[1044] "Storage means" refers to a device or part of a system that has the function of storing transmitted fraudulent application information in a database.

[1045] "Visualization means" refers to a device or part of a system that has the function of displaying stored fraudulent application information on a map using a geographic information system.

[1046] "Alert means" refers to a device or part of a system that has the function of automatically sending an alert to other stores located around the store where the fraudulent application occurred.

[1047] "Analysis means" refers to a device or part of a system that has the function of compiling and analyzing past fraudulent application data and outputting it as a report.

[1048] "Receiving means" refers to a device or part of a system that has the function of allowing other stores that receive the fraudulent application information to receive it as a pop-up notification via their smartphones or head-mounted displays.

[1049] "Geographic information system" is a general term for software and hardware used to collect and analyze geographic data and display it on a map.

[1050] A "smartphone" is a mobile device that has the same functions as a computer, despite being a mobile phone.

[1051] A "head-mounted display" refers to a device that is worn on the user's head and displays visual information.

[1052] A "pop-up notification" refers to a short message displayed on an application to immediately notify the user of important information.

[1053] A "generative AI model" refers to a mathematical model generated by artificial intelligence technology for analysis and prediction.

[1054] A "prompt" refers to a textual instruction or question that is input into a generative AI model.

[1055] This invention relates to a system that uses a smartphone or head-mounted display (HMD) to quickly detect fraudulent applications and notify nearby stores in real time. It also includes the aggregation and analysis of past fraudulent application data, and the visualization and provision of the results.

[1056] 1. Program Generation

[1057] The system mainly consists of the following components:

[1058] Detection methods for detecting fraudulent applications

[1059] A means for transmitting detected fraudulent application information to a server.

[1060] A means of storing submitted information in a database

[1061] A visualization method for displaying stored information on a map using GIS

[1062] An alerting method that automatically sends alerts to nearby stores

[1063] The store that receives the fraudulent application information receives it on their smartphone or HMD.

[1064] Analysis tool that aggregates and analyzes past data and outputs the results

[1065] 2. Explain the program's processing in natural language

[1066] The server includes the following hardware and software:

[1067] Hardware: Cloud Server

[1068] Software: Python, Flask (backend), GIS software (e.g., Folium), data analysis library (Pandas)

[1069] A smartphone and HMD are installed on the terminal side and function as follows.

[1070] Detection Method

[1071] When a user detects a fraudulent application, they enter information about the fraudulent application using a dedicated interface, including the date and time of the application, information about the applicant, and details of any suspicious behavior.

[1072] Transmission and storage methods

[1073] The device receives this input information, validates it, and then sends it to the server, which then stores it in a secure database.

[1074] Visualization tools

[1075] The server uses GIS to display the saved fraudulent application information on a map. Specifically, it obtains the location information of the store where the fraudulent application occurred and displays it as a marker on the map.

[1076] Alert and Receipt Methods

[1077] When a fraudulent application is detected, the server automatically generates an alert to nearby stores and notifies them on smartphones or HMDs, allowing users to immediately take precautions.

[1078] analytical means

[1079] The server aggregates past fraudulent application data and performs statistical analysis, and the results of this analysis are displayed visually in the form of dashboards and reports.

[1080] 3. Adding concrete examples and prompts

[1081] Specific examples

[1082] Users can enter information such as "foreigner," "October 15th, 13:45," and "suspicious behavior" on their smartphones, and an alert is instantly sent to other stores within a 1km radius. At the same time, the server analyzes fraudulent application data from the past year and displays the results on a dashboard.

[1083] Prompt Sentence Examples

[1084] Based on the information below, please design a system that notifies other nearby stores in real time when a fraudulent application is detected and analyzes past fraudulent application data.

[1085] Date and time of fraudulent application: October 15th, 13:45

[1086] Applicant information: Foreigner

[1087] Fraudulent Activity Details: Suspicious Activity

[1088] This system, configured in this way, quickly detects fraudulent applications, notifies relevant parties in real time, and provides analytical information using past data to take effective countermeasures, thereby preventing the spread of fraudulent activity and accelerating response.

[1089] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1090] Step 1:

[1091] When a user detects a fraudulent application, they use a smartphone or head-mounted display to enter the application date and time, applicant information, and details of suspicious behavior into a dedicated interface. The entered information is saved in temporary memory on the device. Input data includes the application date and time, applicant information, and details of suspicious behavior. The application information saved in temporary memory is obtained as output data.

[1092] Step 2:

[1093] The terminal validates the entered information. Specifically, it checks whether all required fields in the input data are filled in and whether the data format is correct. For example, it checks the date format and the format of the applicant information. If validation is successful, it proceeds to the next step. The input data is data in temporary memory, and the output data is the result of validation.

[1094] Step 3:

[1095] The terminal sends the information that has passed validation to the server. The transmission is done using an HTTP request (POST method). The input data is the application information on the terminal side, and the output data is the application information saved on the server side.

[1096] Step 4:

[1097] The server stores the received information in a secure database. The database is an RDBMS (Relational Database Management System) and the information is inserted into tables. The input data is the application information received by the server and the output data are the records stored in the database.

[1098] Step 5:

[1099] The server obtains latitude and longitude information based on the fraudulent application information stored in the database. This information is then displayed on a map using a geographic information system (GIS). GIS software such as Folium is used. The input data is the latitude and longitude information in the database, and the output data is the location of the fraudulent application displayed on the map.

[1100] Step 6:

[1101] The server executes a database query to identify other stores located within a certain distance (e.g., 1 km) around the store where the fraudulent claim was detected. The query results in a list of identified stores. The input data is the location information of the fraudulent claim and the surrounding stores, and the output data is a list of identified surrounding stores.

[1102] Step 7:

[1103] The server generates a warning message for the identified stores and sends an alert. The warning message includes the name of the store where the fraudulent application occurred, the date and time, and important points to note. This is sent to the smartphone or HMD. The input data is a list of identified stores, and the output data is the sent warning message.

[1104] Step 8:

[1105] The terminal receives the alert and displays it to the user as a pop-up notification. The pop-up notification contains a warning message that the user can view and respond to immediately. The input data is the warning message sent from the server, and the output data is the pop-up notification displayed to the user.

[1106] Step 9:

[1107] The server aggregates past fraudulent application data from a database and calculates the number of fraudulent applications within a specified period. Libraries such as Pandas are used for data analysis. The input data is past application information, and the output data is aggregated statistical information.

[1108] Step 10:

[1109] The server performs statistical analysis based on the aggregated data. It uses a generative AI model to analyze patterns in fraudulent application data and displays the results as a dashboard. Specific software operations include data filtering, clustering, and trend analysis. The input data is the aggregated application information, and the output data is a dashboard of the analysis results.

[1110] Through the above steps, the system of the present invention can quickly detect fraudulent applications, immediately notify relevant parties, and provide information using past data to take effective measures.

[1111] 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.

[1112] This invention relates to a system for effectively detecting and quickly responding to fraudulent applications. This system enhances risk assessment of fraudulent applications by combining fraudulent application detection, real-time information transmission, visualization using a geographic information system (GIS), alert notifications to nearby stores, analysis of past data, and an emotion engine that recognizes user emotions.

[1113] As a specific embodiment for implementing the present invention, a flow from detecting a fraudulent application to sharing information, issuing an alert, and analyzing using an emotion engine will be described.

[1114] Detecting and recording fraudulent applications

[1115] 1. When a user (shop crew member) detects a suspicious contract application, they use a dedicated interface to enter the suspicious contract application information into the system. This includes the application date and time, applicant information, and details of the suspicious behavior. The emotion engine also analyzes the user's emotional state in real time and records this information.

[1116] 2. The device receives the entered information, first stores it in a local database, and then validates it to ensure that required fields are filled in properly and that the data format is correct.

[1117] 3. The terminal sends the information that has passed validation to the server, where it is stored in a secure database.

[1118] Real-time processing and visualization of information

[1119] 1. The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS). Here, the server obtains the latitude and longitude information of the store and, in conjunction with the GIS API, displays the location of the fraudulent application on the map with a red icon or a specific color, clearly showing the location of the fraudulent application.

[1120] 2. The emotion engine analyzes the user's emotional data when a fraudulent application is made, and integrates and displays the results in a visualization tool. This allows users to visually confirm the risk assessment of fraudulent applications.

[1121] Alert notifications to nearby stores

[1122] 1. The server uses a database query to identify other stores within 1 km of the store where the fraudulent claim was detected. The query returns a list of nearby stores.

[1123] 2. The server automatically generates a warning message and sends an alert to the identified nearby stores. The alert includes the store where the fraudulent application occurred, the date and time, and points to note.

[1124] 3. The terminal receives the alert and displays it to the user (shop crew) as a pop-up notification, allowing the user to immediately become alert to suspicious applications and take appropriate measures.

[1125] Historical data analysis

[1126] 1. The server aggregates past fraudulent application data from the database and calculates the number of fraudulent applications within a specified period (for example, one year). This is achieved by performing statistical data processing.

[1127] 2. The server performs statistical analysis on the aggregated data to identify which stores have experienced fraudulent applications and how frequently. The results are then generated as a dashboard or report.

[1128] 3. The emotion engine analyzes past application data and user emotional data to identify patterns of fraudulent applications, improving the accuracy of detecting subtle fraudulent behavior.

[1129] 4. The analysis results generated by the server are sent to the device and displayed visually on a dashboard, allowing users (administrators and shop crew) to understand trends and patterns in fraudulent applications and use this information to take future countermeasures.

[1130] Specific examples

[1131] 1. A user (shop crew member) detects a suspicious contract application from a foreigner at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into the dedicated system. At the same time, the emotion engine analyzes the user's facial expression and tone of voice, and records their emotional state, such as "tension" or "anxiety."

[1132] 2. The device receives this input information, validates it, and then sends it to the server, which stores it in a database and displays it on a map, integrating GIS and emotion data.

[1133] 3. The server identifies five stores within 1 km of the store in question, generates an alert, and sends it. The device displays the received alert as a pop-up, and the user can confirm the notification.

[1134] 4. The server aggregates application data and emotion data from the past year, and displays the analysis results on the dashboard, showing that 10 fraudulent applications occurred in October. The emotion engine also evaluates the risk of fraudulent applications based on the emotion data, and reflects this in the analysis results.

[1135] This series of processes, combined with emotional data, strengthens risk assessment of contract fraud, enabling swift and effective response.

[1136] The processing flow will be explained below.

[1137] Step 1:

[1138] A user (shop crew member) detects a suspicious contract application and enters the suspicious contract application information into the system through a dedicated interface. The information entered includes the date and time of the application, applicant information, and details of suspicious behavior. An emotion engine also analyzes the user's facial expressions and tone of voice in real time, and records emotional data such as "tension" and "anxiety."

[1139] Step 2:

[1140] The device receives this information, temporarily stores it in a local database, and then validates the information to ensure that required fields are filled in properly and that the data format is correct.

[1141] Step 3:

[1142] The terminal sends the information that has passed validation to the server, where it is stored in a secure database.

[1143] Step 4:

[1144] The server processes the fraudulent application information and emotion data stored in the database in real time and displays it on a map using a geographic information system (GIS). It obtains the latitude and longitude information of stores and, by linking with the GIS API, shows the locations of fraudulent applications visually by displaying them on the map with red icons or specific colors. At the same time, it performs a risk assessment using emotion data and visualizes the results.

[1145] Step 5:

[1146] The server uses a database query to identify other stores within 1 km of the store where the fraudulent claim was detected, and the stores listed by the query are then automatically targeted for alert notifications.

[1147] Step 6:

[1148] The server automatically generates a warning message and sends an alert to the identified surrounding stores. This alert includes the store where the fraudulent application occurred, the date and time, points to be careful about, and the risk assessment results based on the emotion engine.

[1149] Step 7:

[1150] The terminal receives the alert and displays it to the user (shop crew) as a pop-up notification, allowing the user to immediately become alert to suspicious applications and take appropriate measures.

[1151] Step 8:

[1152] The server aggregates past fraudulent application data and emotion data from the database and calculates the number of fraudulent applications and emotion trends within a specified period (e.g., one year). This is achieved by performing statistical data processing.

[1153] Step 9:

[1154] The server performs statistical analysis based on the aggregated data to determine which stores have experienced fraudulent applications and how frequently they have occurred, as well as the associated emotional data to determine risk assessment results. These results are then generated as dashboards and reports.

[1155] Step 10:

[1156] The analysis results generated by the server are sent to the terminal and displayed visually on a dashboard, allowing users (administrators and shop crew) to understand trends and patterns of fraudulent applications and user emotional tendencies, and use this information to help with future countermeasures.

[1157] Specific examples

[1158] 1. A user (shop crew member) detects a suspicious contract application from a foreigner at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into the dedicated system. At the same time, the emotion engine analyzes the user's facial expression and tone of voice, and records their emotional state, such as "tension" or "anxiety."

[1159] 2. The device receives this input information, validates it, and then sends it to the server, which stores it in a database and displays it on a map, integrating GIS and emotion data.

[1160] 3. The server identifies five stores within 1 km of the store in question, generates an alert, and sends it. The device displays the received alert as a pop-up, and the user can confirm the notification.

[1161] 4. The server aggregates application data and emotion data from the past year, and displays the analysis results on the dashboard, showing that 10 fraudulent applications occurred in October. The emotion engine also evaluates the risk of fraudulent applications based on the emotion data, and reflects this in the analysis results.

[1162] This series of processes, combined with emotional data, strengthens risk assessment of contract fraud, enabling swift and effective response.

[1163] Example 2

[1164] 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."

[1165] Conventional fraudulent application detection systems have had issues with delayed response after detecting fraudulent applications and providing only limited information. Furthermore, risk assessment is insufficient because the system does not take into account the user's emotional state. As a result, early detection of fraudulent applications and effective implementation of preventative measures are sometimes ineffective. Furthermore, there is a lack of a way to visually grasp the location of fraudulent applications and the surrounding situation.

[1166] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1167] In this invention, the server includes application means for detecting fraudulent applications, transmission means for transmitting detected fraudulent application information to the server in real time, storage means for saving the transmitted fraudulent application information in a database, visualization means for displaying the saved fraudulent application information on a map using a geographic information system, emotion analysis means for analyzing the emotional state of users at the location where the fraudulent application occurred and recording the information in real time, alert means for automatically sending alerts to other locations located in the vicinity of the location where the fraudulent application occurred, and analysis means for compiling and analyzing the information based on past fraudulent application information and the emotional state of users and outputting it as a report. This significantly improves risk assessment of fraudulent applications and enables quick and effective response.

[1168] "Fraudulent application" refers to an application or attempted contract made with fraudulent intent.

[1169] "Application method" refers to the interface or mechanism for detecting fraudulent applications.

[1170] "Transmission means" refers to the method or technology for transmitting detected fraudulent application information to a server in real time.

[1171] "Storage means" refers to a mechanism for safely storing submitted fraudulent application information in a database.

[1172] "Visualization means" refers to technology that displays stored fraudulent application information on a map using a geographic information system.

[1173] "Emotion analysis means" refers to technology that analyzes the emotional state of users at the location where fraudulent applications occur and records that information in real time.

[1174] "Alert method" refers to a mechanism that automatically sends a warning to other locations located in the vicinity of the location where the fraudulent application occurred.

[1175] "Analysis methods" refers to technology for compiling and analyzing information based on past fraudulent application information and the user's emotional state, and outputting it as a report.

[1176] A "geographic information system" refers to a system that handles geospatial information and visualizes data on a map.

[1177] "User" refers to an individual or person with a role who uses this system to detect, record, and address fraudulent applications.

[1178] "Server" refers to a computer device that manages the processing of the entire system and collects, stores, and processes fraudulent application information and emotion analysis data.

[1179] "Database" refers to an information management system for organizing and storing fraudulent application information and related data.

[1180] The present invention provides a system for effectively detecting and quickly responding to fraudulent claims, which enhances risk assessment of fraudulent claims by combining fraudulent claim detection, real-time information transmission, visualization using a geographic information system (GIS), alert notification to other locations in the vicinity, analysis of historical data, and user sentiment analysis.

[1181] Detecting and recording fraudulent applications

[1182] First, when a user (shop crew member) detects a suspicious contract application, they use a dedicated interface to enter the date and time of the application, applicant information, and details of the suspicious behavior into the system. As this information is entered, an emotion engine analyzes the user's emotional state (e.g., tension, anxiety) in real time, and this information is also recorded. This analysis uses technology that analyzes facial expressions and tone of voice using a camera and microphone.

[1183] The device then temporarily stores this information in a local database and performs validation, such as checking for missing required fields and checking the date format. If the information passes validation, it is sent from the device to the server, where it is stored in a secure database.

[1184] Real-time processing and visualization of information

[1185] The server processes the stored fraudulent application information in real time and displays it on a map using a geographic information system (GIS), such as Google Maps API, to clearly indicate the location of fraudulent applications using, for example, a red icon.

[1186] The emotion engine also integrates the analyzed emotion data into visualization tools and displays them on a map. Emotional states are displayed as appropriate icons (e.g., emoji faces), allowing users to visually assess the risk of fraudulent applications.

[1187] Alert notifications to nearby stores

[1188] The server uses a database query to identify other locations within 1 km of the location where the fraudulent claim was detected. It uses SQL queries to compile a list of nearby locations and then generates and sends out an alert. The alert includes the location, date, and time of the fraudulent claim, as well as any important points to note.

[1189] The terminal receives this alert and displays it to the user (shop crew) as a pop-up notification, allowing the user to immediately check the information and take necessary measures.

[1190] Historical data analysis

[1191] The server aggregates past fraudulent application data from the database and calculates the number of fraudulent applications within a specified period (e.g., the past year). This process involves extracting the data using SQL queries and performing statistical processing and visualization using Python tools such as Pandas and Matplotlib.

[1192] The emotion engine combines and analyzes past fraudulent application data with user emotion data to identify patterns of fraudulent applications. It uses a clustering algorithm to extract specific behavioral and emotional patterns. The server visually displays the results of this analysis on a dashboard, allowing users (administrators and shop crew) to understand trends and patterns in fraudulent applications and develop preventative measures.

[1193] Specific examples

[1194] For example, a user (shop crew member) detects a suspicious contract application made by a foreigner at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into the dedicated system. At the same time, the emotion engine analyzes the user's facial expressions and tone of voice, and records their emotional state, such as "tension" or "anxiety."

[1195] The device receives this information, validates it, and then sends it to the server, which stores it in a database and displays it on a map, integrating GIS and emotion data.

[1196] The server identifies five other locations within 1 km of the location and generates and sends an alert, which the device displays as a pop-up for the user to confirm.

[1197] The server aggregates application data and emotion data from the past year, and displays the analysis results on the dashboard, showing that 10 fraudulent applications occurred in October. The emotion engine also evaluates the risk of fraudulent applications based on the emotion data, and reflects this in the analysis results.

[1198] When using a generative AI model, you might use prompts like the following:

[1199] "At 13:45 on October 15th, a foreigner exhibited suspicious behavior. The user's emotional state was 'tension' and 'anxiety'."

[1200] The comprehensive operation of the system as described above will strengthen risk assessment of fraudulent applications and enable swift and effective responses.

[1201] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1202] Program processing steps

[1203] Detecting and recording fraudulent applications

[1204] Step 1:

[1205] A user (shop crew member) detects a suspicious contract application. Using a dedicated interface, the user enters the application date and time, applicant information, and details of suspicious behavior. The entered data is in text format and separated into specific fields. This input information is sent directly to the next processing step, while the emotion engine simultaneously analyzes the user's emotional state. This analysis uses a camera and microphone to evaluate facial expressions and tone of voice in real time.

[1206] Step 2:

[1207] The terminal receives the information entered by the user. The entered data is temporarily stored in a local database and validated. Specific validation details include whether all required fields (e.g., application date and time, applicant information) are filled in, whether the date format is correct, and whether the details of suspicious activity are 50 characters or more. Information that passes validation is sent to the next process as a new data structure.

[1208] Step 3:

[1209] The device sends the information that has passed validation to the server. The data is encrypted during transmission. The transmitted data includes the application date and time, applicant information, details of suspicious behavior, and emotion analysis results. The server receives this data and stores it in a secure database.

[1210] Real-time processing and visualization of information

[1211] Step 4:

[1212] The server retrieves the fraudulent application information stored in the database and begins processing it in real time. The input data here is detailed information about the fraudulent application and the results of sentiment analysis. The server retrieves the latitude and longitude information of the store from a GIS API (e.g., Google Maps API) and displays the location of the fraudulent application on a map with a red icon. This display data is generated in real time through requests to the GIS API.

[1213] Step 5:

[1214] The emotion engine takes the analyzed emotion data and integrates the results into a visualization method. Specifically, it adds icons (e.g., emoji faces) indicating the emotional state to the locations of fraudulent claims on a map. The input data includes the emotion analysis results, and the output data consists of the visual display information of the GIS.

[1215] Alert notifications to nearby stores

[1216] Step 6:

[1217] The server uses a database query to identify other locations within 1 km of the location where the fraudulent claim was detected. The input data for this process includes the latitude and longitude of the fraudulent claim, and uses an SQL query to list other nearby locations. The output data is a list of the identified nearby locations.

[1218] Step 7:

[1219] The server generates a warning message for the identified nearby locations and sends an alert. The alert contains the location, date, and time of the fraudulent application, as well as points to note, and this information is generated automatically. The input data is the list of identified nearby locations and the fraudulent application information, and the output data is the alert message and its transmission status.

[1220] Step 8:

[1221] The alert received by the terminal is displayed to the user (shop crew) as a pop-up notification. Specifically, the user is immediately notified of the warning through desktop or mobile notifications. The input data of this process is the alert message sent from the server, and the output data is the notification confirmation status sent to the user.

[1222] Historical data analysis

[1223] Step 9:

[1224] The server aggregates past fraudulent application data from the database. It uses an SQL query to extract data to calculate the number of fraudulent applications for a specified period (e.g., the past year). The input data is detailed information about fraudulent applications, and the output data is the number of fraudulent applications for the specified period.

[1225] Step 10:

[1226] The server performs statistical analysis based on the collected data. Python's Pandas and Matplotlib are used to generate graphs and heat maps to visualize the number and location of fraudulent applications. The input data is the number of fraudulent applications within a specified period, and the output data is visualized data of the analysis results.

[1227] Step 11:

[1228] The emotion engine combines and analyzes past fraudulent application data with user emotion data. It uses a clustering algorithm to extract specific behavioral and emotional patterns. The input data is fraudulent application information and emotion data, and the output data is the extracted behavioral and emotional patterns.

[1229] Step 12:

[1230] The analysis results generated by the server are sent to the terminal and displayed visually on a dashboard. This allows users (administrators and shop crew) to understand trends and patterns of fraudulent applications and use them to develop future countermeasures. The input data is the analysis results sent from the server, and the output data is the visual display information on the dashboard.

[1231] This series of processing steps significantly strengthens the risk assessment of fraudulent applications and enables a fast and effective response.

[1232] (Application example 2)

[1233] 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."

[1234] Conventional fraudulent application detection systems can detect fraudulent applications and issue warnings, but they ignore the user's emotional state and lack information to better understand fraudulent behavior. Furthermore, they lack the ability to visualize fraudulent application information or send alerts to nearby stores in real time, making it difficult to respond immediately. Furthermore, analysis of past fraudulent application data is insufficient, making it difficult to assess the risk of recurrence.

[1235] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1236] In this invention, the server includes application means for detecting fraudulent applications, transmission means for transmitting detected fraudulent application information to the server in real time, storage means for saving the transmitted fraudulent application information in a database, visualization means for displaying the saved fraudulent application information on a map using a geographic information system, alert means for automatically sending alerts to other stores located around the store where the fraudulent application occurred, analysis means for aggregating and analyzing past fraudulent application data and outputting it as a report, emotion analysis means for analyzing the user's emotional state from application data, and means for integrating the user's emotional state into the fraudulent application information and displaying it on the visualization means. This improves the accuracy of fraudulent application detection and enables quick and effective response.

[1237] "Fraudulent application" refers to an act of violating prescribed procedures and attempting to obtain unfair benefits.

[1238] "Application Method" means the method for detecting fraudulent applications and entering information into the system.

[1239] "Transmission means" refers to a means for transmitting detected fraudulent application information to a server in real time.

[1240] "Storage Means" refers to the means for storing submitted fraudulent application information in a database.

[1241] The "visualization means" is a means for displaying the stored fraudulent application information on a map using a geographic information system.

[1242] "Alert means" refers to a means for automatically issuing a warning to other stores located around the store where the fraudulent application occurred.

[1243] "Analysis methods" refers to the means for compiling and analyzing past fraudulent application data and outputting it as a report.

[1244] "Emotion analysis means" means means for analyzing the user's emotional state from application data.

[1245] "Integration means" refers to a means for integrating and displaying a user's emotional state with fraudulent application information.

[1246] The system for implementing this invention combines multiple means for effectively detecting fraudulent applications and quickly responding to them. The specific flow and the hardware and software used are described below.

[1247] Overall system overview

[1248] 1. Detecting fraudulent applications

[1249] When a user (store staff member) detects a fraudulent application, they enter the fraudulent application information into the system using a dedicated interface.

[1250] The emotion analysis means analyzes the user's emotional state at the time of input in real time and adds that information.

[1251] 2. Real-time processing and information transmission

[1252] The terminal receives the input information and first temporarily stores it in a local database.

[1253] Validate information to ensure required fields are filled in properly and that data is formatted correctly.

[1254] The terminal sends the information that has passed the validation to the server.

[1255] The server receives the information and stores it in a database.

[1256] 3. Visualization

[1257] The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS).

[1258] The locations of fraudulent applications are clearly displayed on a map, and emotional states are also integrated and visualized.

[1259] 4. Store-to-store alerts

[1260] The server automatically identifies other stores within a certain distance of the store where the fraudulent application was detected and sends an alert.

[1261] The terminal displays the received alert to the user in a pop-up notification.

[1262] 5. Historical Data Analysis

[1263] The server compiles and analyzes past fraudulent application data from the database and calculates the number of fraudulent applications for a specified period.

[1264] The analysis results are output as dashboards and reports so that users can view them.

[1265] Hardware and software used

[1266] EmotionEngine: A library for analyzing a user's emotional state. This library analyzes emotions from voice and facial expressions in real time.

[1267] GISMap: A library for displaying the locations of fraudulent applications on a map using a geographic information system.

[1268] NotificationManager: A library for generating cross-store alerts and notifying other stores.

[1269] DatabaseManager: A library for managing the storage and retrieval of fraudulent application data.

[1270] Specific examples

[1271] A user (store staff member) detects a suspicious contract application from a foreigner at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into a dedicated interface. At the same time, an emotion analysis tool analyzes the user's emotional state and records it as "tension" or "anxiety."

[1272] The device receives this input information, validates it, and then sends it to the server, which stores it in a database and displays it on a map, integrating GIS and emotion data.

[1273] The server identifies five stores within a certain distance of the store in question, generates an alert, and sends it out. The alert is received by the device and displayed as a pop-up, allowing the user to confirm the notification.

[1274] The server compiles application data and emotion data from the past year, and displays on the dashboard that 10 fraudulent applications occurred in October. In addition, the emotion analysis means evaluates the risk of fraudulent applications based on the emotion data, and reflects this in the analysis results.

[1275] Prompt Sentence Examples

[1276] Data for fraudulent application warning system

[1277] User Input: I'm nervous

[1278] Applicant information: Foreigners

[1279] Suspicious Activity: Suspicious activity

[1280] Location information: (35.6895, 139.6917)

[1281] In this way, a system embodying the present invention is constructed, which improves the accuracy of detecting fraudulent applications and enables prompt and effective responses.

[1282] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1283] Step 1:

[1284] When a user detects a fraudulent application, they use a dedicated interface to input information about the fraudulent application into the system. Based on the input, the date and time of the application, applicant information, details of suspicious behavior, and the user's emotional state are collected. Using an emotion analysis means, the user's emotional state is analyzed and recorded together with the application information.

[1285] Step 2:

[1286] The terminal receives the information entered by the user and temporarily stores it in a local database. At the same time, the terminal validates the input information to ensure that required fields are entered properly and that the data format is correct.

[1287] Step 3:

[1288] The terminal sends the information that has passed validation to the server. The input is the user's fraudulent application information and emotion data. After transmission, the server receives the information and stores it in a secure database. At this point, the server rechecks the integrity of the information.

[1289] Step 4:

[1290] The server processes the fraudulent application information stored in the database in real time. To display the locations of fraudulent applications on a map using a geographic information system (GIS), the location data of the fraudulent application information is sent to a GIS API, and the locations of the fraudulent applications are displayed on the map.

[1291] Step 5:

[1292] The server visualizes the emotional data obtained using emotion analysis techniques. In addition to the locations of fraudulent applications, the user's emotional state is also integrated and displayed on a map, allowing users to intuitively confirm risk assessment.

[1293] Step 6:

[1294] The server executes a query against the database to automatically identify other stores located within a certain distance of the store where the fraudulent application was detected. The input is the location data of the store where the fraudulent application occurred, and the output is a list of surrounding stores.

[1295] Step 7:

[1296] The server generates a warning message to the identified surrounding stores, which includes the store where the fraudulent application occurred, the date and time, and points to note, and is automatically sent by an alert means.

[1297] Step 8:

[1298] The device displays the received alert as a pop-up notification to the user, allowing the user to check the alert displayed on the screen and take immediate action.

[1299] Step 9:

[1300] The server aggregates and analyzes past fraudulent application data. The input is past fraudulent application data and sentiment data, and statistical data processing is performed to calculate the number of fraudulent applications within a period and a risk assessment. The aggregated results are output to a dashboard or report.

[1301] Step 10:

[1302] The server displays the aggregated results and risk assessments on a dashboard, which users can view to understand trends and patterns in fraudulent applications and obtain information to take appropriate measures.

[1303] The above are the processing steps of the system for carrying out this invention, and the specific operations and inputs / outputs are clearly stated for each step.

[1304] 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.

[1305] 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.

[1306] 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.

[1307] [Fourth embodiment]

[1308] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1309] 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.

[1310] 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).

[1311] 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.

[1312] 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.

[1313] 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).

[1314] 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.

[1315] 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.

[1316] 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.

[1317] 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.

[1318] 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.

[1319] 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.

[1320] 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."

[1321] This invention relates to a system for effectively detecting fraudulent applications and quickly responding to them. This system is composed of functions including fraudulent application detection, real-time information transmission, visualization using a geographic information system (GIS), alert notification to nearby stores, and analysis of past data.

[1322] As a specific embodiment for implementing the present invention, a flow from detecting a fraudulent application to sharing information, issuing an alert, and analyzing the information will be described.

[1323] Detecting and recording fraudulent applications

[1324] 1. When a user (shop crew member) detects a fraudulent application, they use a dedicated interface to enter the suspicious contract application information into the system, including the application date and time, applicant information, and details of the suspicious behavior.

[1325] 2. The device receives the entered information, first stores it in a local database, and then validates it to ensure that required fields are filled in properly and that the data format is correct.

[1326] 3. The terminal sends the information that has passed validation to the server, where it is stored in a secure database.

[1327] Real-time processing and visualization of information

[1328] 1. The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS). Using GIS, the location of the store can be accurately displayed.

[1329] 2. In order to visually display information about fraudulent applications, the server obtains the latitude and longitude information of the store and displays the location of the fraudulent application on a map with a red icon or a specific color, making it clear where the fraudulent application occurred.

[1330] Alert notifications to nearby stores

[1331] 1. The server runs a database query to identify other stores located within 1 km of the store where the fraudulent claim was detected.

[1332] 2. The server automatically generates a warning message and sends an alert to the identified nearby stores. The alert includes the store where the fraudulent application occurred, the date and time, and points to note.

[1333] 3. The terminal receives the alert and displays it to the user (shop crew) as a pop-up notification, allowing them to immediately become alert to any suspicious applications.

[1334] Historical data analysis

[1335] 1. The server aggregates past fraudulent application data from the database and calculates the number of fraudulent applications within a specified period (for example, one year).

[1336] 2. The server performs statistical analysis based on the collected data to determine which stores are experiencing fraudulent applications and how frequently.

[1337] 3. The server generates and visually displays the analysis results as dashboards and reports, allowing administrators to understand trends and patterns in fraudulent applications and obtain information to take effective measures.

[1338] Specific examples

[1339] 1. A user (shop crew member) detects a suspicious contract application by a foreigner at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into a dedicated system.

[1340] 2. The device receives this input information, validates it, and then sends it to the server, which stores it in a database and displays it on a map using GIS.

[1341] 3. The server identifies five stores within 1 km of the store in question, generates an alert, and sends it. The device displays the received alert as a pop-up, and the user can confirm the notification.

[1342] 4. The server compiles application data from the past year and displays the analysis results on the dashboard, showing that 10 fraudulent applications occurred in October.

[1343] This series of processes enables fraudulent contracts to be detected quickly and dealt with effectively.

[1344] The processing flow will be explained below.

[1345] Step 1:

[1346] A user (shop crew member) detects a suspicious contract application and enters the suspicious contract application information into the system through a dedicated interface. The information entered includes the application date and time, applicant information, and details of the suspicious behavior.

[1347] Step 2:

[1348] The device receives the entered information and temporarily stores it in a local database, while simultaneously validating the information to ensure that required fields are filled in properly and that the data format is correct.

[1349] Step 3:

[1350] The terminal sends the information that has passed validation to the server, where it is stored in a secure database.

[1351] Step 4:

[1352] The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS). Here, the latitude and longitude information of the store is acquired, and by linking with the GIS API, the location of the fraudulent application is clearly displayed by showing it on the map with a red icon or a specific color.

[1353] Step 5:

[1354] The server uses a database query to identify other stores within 1 km of the store where the fraudulent claim was detected. The query returns a list of nearby stores.

[1355] Step 6:

[1356] The server automatically generates a warning message and sends an alert to the identified nearby stores, which includes the store where the fraudulent application occurred, the date and time, and points to note.

[1357] Step 7:

[1358] The terminal receives the alert and displays it to the user (shop crew) as a pop-up notification, allowing the user to immediately become alert to suspicious applications and take appropriate measures.

[1359] Step 8:

[1360] The server aggregates past fraudulent application data from the database and calculates the number of fraudulent applications within a specified period (e.g., one year). This is achieved by performing statistical data processing.

[1361] Step 9:

[1362] The server performs statistical analysis on the aggregated data to identify which stores are experiencing fraudulent applications and how frequently they occur, and generates the results as dashboards and reports.

[1363] Step 10:

[1364] The analysis results generated by the server are sent to the device and displayed visually on a dashboard, allowing users (administrators and shop crew) to understand trends and patterns in fraudulent applications and use this information to take future countermeasures.

[1365] Example 1

[1366] 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."

[1367] The problem to be solved by this invention is to provide a system for effectively detecting fraudulent applications and responding quickly. Specifically, the object is to provide a system that can efficiently and in real time detect fraudulent applications, share information, issue alerts, and analyze past data.

[1368] 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.

[1369] In this invention, the server includes: application means for detecting fraudulent applications; transmission means for transmitting detected fraudulent application information to the server in real time; storage means for saving the sent fraudulent application information in a database; visualization means for displaying the saved fraudulent application information on a map using a geographic information system; alert means for automatically sending alerts to other stores located around the store where the fraudulent application occurred; analysis means for compiling and analyzing past fraudulent application data and outputting it as a report; validation means for validating input data when fraudulent application information is entered and checking required fields and data format; warning generation means for generating and sending warning messages to multiple identified surrounding stores; and visualization means for acquiring latitude and longitude information of stores and displaying them on a map with specific colors and icons to visually display the fraudulent application status. This enables rapid detection of fraudulent applications, information sharing, and warnings to surrounding stores.

[1370] A "fraudulent application" is an application made using unauthorized or fraudulent information.

[1371] The "application means" is a means for detecting fraudulent applications, and includes an interface for users to input information.

[1372] The "transmission means" is a means for transmitting detected fraudulent application information to the server in real time.

[1373] The "storage means" is a means for storing the transmitted fraudulent application information in a database.

[1374] The "visualization means" is a means for displaying the stored fraudulent application information on a map using a geographic information system.

[1375] The "alert means" is a means for automatically sending an alert to other stores located around the store where the fraudulent application occurred.

[1376] "Analysis methods" are means for compiling and analyzing past fraudulent application data and outputting it as a report.

[1377] "Validation means" refers to a means for validating input data and checking required fields and data format when fraudulent application information is entered.

[1378] The "warning generation means" is a means for generating and transmitting a warning message to the identified surrounding stores.

[1379] The "visualization means" is a means for obtaining the latitude and longitude information of the store and showing it on a map with a specific color or icon in order to visually display the fraudulent application status.

[1380] This invention relates to a system for effectively detecting fraudulent applications and quickly responding to them. This system is composed of functions including fraudulent application detection, real-time information transmission, visualization using a geographic information system (GIS), alert notification to nearby stores, and analysis of past data.

[1381] Detecting and recording fraudulent applications

[1382] A user (shop crew member) uses a dedicated interface to enter information about suspicious contract applications into the system, including the date and time of the application, applicant information, and details of suspicious behavior.

[1383] The terminal receives information entered by the user and temporarily stores it in a local database. A lightweight database such as SQLite is used for the local database. The saved data is then validated to ensure the input format and required fields are entered correctly. Information that passes validation is sent to the server via secure communication using the HTTPS protocol. The server stores the received data in a secure database (for example, PostgreSQL).

[1384] Real-time processing and visualization of information

[1385] The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS). GIS tools include Google Maps API and ESRI ArcGIS. The server periodically runs a script to detect new data and obtains new fraudulent application information. Based on the obtained information, the GIS tool is called, the latitude and longitude information of the store is obtained, and a red marker is placed at a specific location on the map to visually indicate the location of the fraudulent application.

[1386] Alert notifications to nearby stores

[1387] The server executes a database query (SQL query) to identify other stores within 1 km of the store where the fraudulent application was detected. A warning message is generated and sent to the identified stores via email or a push notification system (e.g., Firebase Cloud Messaging). The warning message includes the store where the fraudulent application occurred, the date and time, and important points to note.

[1388] The terminal receives the alert and displays it to the user (shop crew) as a pop-up notification. The application running on the terminal receives notifications from the server on a specific port and displays the received message on the screen in a pop-up format.

[1389] Historical data analysis

[1390] The server aggregates data on fraudulent applications from the past database and calculates the number of fraudulent applications within a specified period (for example, one year). A calculation script is run periodically on the server to extract fraudulent application information from the database for the past year and count the number of cases within the period. A statistical analysis of the extracted data is performed using a data analysis library such as Pandas or NumPy to calculate how frequently fraudulent applications occur at each store. Based on the analysis results, a dashboard is created in the form of graphs and charts using a data visualization tool such as Tableau or Power BI. For example, it displays information such as "fluctuations in the number of fraudulent applications by month" and "frequency of fraudulent applications by store."

[1391] Specific examples

[1392] 1. A user (shop crew member) detects a suspicious contract application at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into a dedicated system.

[1393] 2. The device receives this input information, temporarily stores it, validates it, and then sends it to the server, which stores it in a database and displays it on a map using GIS.

[1394] 3. The server identifies five stores within 1 km of the store in question, generates an alert, and sends it. The device displays the received alert as a pop-up, and the user can confirm the notification.

[1395] 4. The server compiles application data from the past year and displays the analysis results on the dashboard, showing that 10 fraudulent applications occurred in October.

[1396] Prompt Sentence Examples

[1397] "At 1:45 PM on October 15th, a suspicious contract application by a foreigner was detected in the store. The applicant was behaving strangely. Please send alerts to surrounding stores as well."

[1398] This will enable the creation of a system that can quickly detect fraudulent applications, share information, and issue warnings to surrounding stores.

[1399] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1400] Step 1:

[1401] A user (shop crew member) enters suspicious contract application information into a dedicated interface.

[1402] Input: Application date and time, applicant information, details of suspicious behavior (e.g., "October 15th, 13:45", "Foreigner", "Suspicious behavior").

[1403] Specific actions: Enter the required information into the input screen of a web form or dedicated application and click the "Submit" button.

[1404] Step 2:

[1405] The terminal receives the information input by the user and temporarily stores it in a local database.

[1406] Input: Application information entered by the user.

[1407] Data processing: Validate the data format in a local database to ensure consistency and that required fields are entered correctly.

[1408] Output: Data that passes validation is temporarily saved.

[1409] What happens: The data is temporarily stored in a lightweight database such as SQLite and validation is performed.

[1410] Step 3:

[1411] The terminal sends the information that has passed the validation to the server.

[1412] Input: Application information that has passed validation.

[1413] Data processing: Secure communication using the HTTPS protocol.

[1414] Output: The server receives the data via secure communication.

[1415] What happens: If validation is successful, the data is sent to the server using HTTPS.

[1416] Step 4:

[1417] The server stores the received fraudulent application information in a database.

[1418] Input: Application information sent from the terminal.

[1419] Data processing: Store the received data in a secure database (e.g., PostgreSQL).

[1420] Output: The data is saved to a database.

[1421] Specific operation: Stores the received data in a secure database.

[1422] Step 5:

[1423] The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS).

[1424] Input: Fraudulent application information retrieved from the database.

[1425] Data processing: Call GIS tools (Google Maps API; ESRI ArcGIS) to obtain store latitude and longitude information and convert it into a display format.

[1426] Output: The locations of fraudulent claims are displayed on a map.

[1427] Specific operation: Using a GIS tool, place a red marker on the map based on the acquired latitude and longitude information.

[1428] Step 6:

[1429] The server runs a database query to identify other stores located within 1 km of the store where the fraudulent claim was detected.

[1430] Input: Latitude and longitude information of the store where the fraudulent application occurred, and data of surrounding stores.

[1431] Data processing: Search for stores within 1km using an SQL query.

[1432] Output: List of other stores within 1km radius.

[1433] Specific operation: The server periodically executes queries to identify nearby stores.

[1434] Step 7:

[1435] The server generates a warning message and sends an alert to the identified surrounding stores.

[1436] Input: List of surrounding stores, fraudulent application information.

[1437] Data processing: Generate a warning message (e.g., "A fraudulent application occurred on October 15th at 1:45 PM. Please be careful") and send it via a notification service (e.g., Firebase Cloud Messaging).

[1438] Output: A warning message is sent to each store.

[1439] Specific behavior: After generating a message, an alert will be sent via email or push notification.

[1440] Step 8:

[1441] The device receives the alert and displays it to the user (shop crew) as a pop-up notification.

[1442] Input: The warning message sent by the server.

[1443] Data processing: Process received messages into popup format.

[1444] Output: Show a popup notification on the device.

[1445] What it does: When a notification is received on a specific port, the application displays a pop-up notification on the screen.

[1446] Step 9:

[1447] The server aggregates fraudulent application data from past databases and calculates the number of fraudulent applications within a specified period (for example, one year).

[1448] Input: Past fraudulent application data.

[1449] Data processing: Run the data aggregation script and count the number of items within the specified period.

[1450] Output: Number of fraudulent applications within a specified period.

[1451] Specific operation: Executes the aggregation script periodically and aggregates the results.

[1452] Step 10:

[1453] The server performs statistical analysis based on the aggregated data.

[1454] Input: Aggregated fraudulent application data.

[1455] Data processing: Perform statistical analysis using data analysis libraries such as Pandas and NumPy.

[1456] Output: Results of the statistical analysis.

[1457] Specific actions: Runs analysis scripts and calculates statistical indicators.

[1458] Step 11:

[1459] The server generates and visually displays the analysis results as dashboards and reports.

[1460] Input: Results of the statistical analysis.

[1461] Data processing: Create graphs and charts using Tableau and Power BI.

[1462] Output: Display as a dashboard or report.

[1463] Specific action: Convert the data into a format that is easy to visualize using a data visualization tool.

[1464] The above are the specific processing steps of the program of this system.

[1465] (Application example 1)

[1466] 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."

[1467] Conventional fraudulent application detection systems lack the ability to quickly notify nearby stores of fraudulent application information, making it difficult to take immediate action to prevent the spread of fraud. Furthermore, because there is no mechanism for real-time notifications using smart devices, notifications can be overlooked or responses delayed. Furthermore, there is insufficient visualization of trends based on pattern analysis of past fraudulent application data, resulting in a lack of information to take effective countermeasures.

[1468] 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.

[1469] In this invention, the server includes detection means for detecting fraudulent applications, transmission means for transmitting detected fraudulent application information to the server in real time, storage means for saving the transmitted fraudulent application information in a database, visualization means for displaying the saved fraudulent application information on a map using a geographic information system, alert means for automatically sending alerts to other stores located around the store where the fraudulent application occurred, analysis means for compiling and analyzing past fraudulent application data and outputting it as a report, and reception means for other stores that have received the fraudulent application information to receive the same as a pop-up notification via their smartphones or head-mounted displays. This makes it possible to quickly and reliably notify nearby stores of fraudulent application information and encourage them to take immediate action, and furthermore, by analyzing fraudulent application patterns based on past data, it is possible to provide information for taking effective countermeasures.

[1470] "Fraudulent application" refers to an application made with fraudulent content that violates normal procedures and standards.

[1471] "Detection means" refers to a device or part of a system for detecting fraudulent applications.

[1472] "Transmission means" refers to a device or part of a system that has the function of transmitting detected fraudulent application information to a server in real time.

[1473] "Storage means" refers to a device or part of a system that has the function of storing transmitted fraudulent application information in a database.

[1474] "Visualization means" refers to a device or part of a system that has the function of displaying stored fraudulent application information on a map using a geographic information system.

[1475] "Alert means" refers to a device or part of a system that has the function of automatically sending an alert to other stores located around the store where the fraudulent application occurred.

[1476] "Analysis means" refers to a device or part of a system that has the function of compiling and analyzing past fraudulent application data and outputting it as a report.

[1477] "Receiving means" refers to a device or part of a system that has the function of allowing other stores that receive the fraudulent application information to receive it as a pop-up notification via their smartphones or head-mounted displays.

[1478] "Geographic information system" is a general term for software and hardware used to collect and analyze geographic data and display it on a map.

[1479] A "smartphone" is a mobile device that has the same functions as a computer, despite being a mobile phone.

[1480] A "head-mounted display" refers to a device that is worn on the user's head and displays visual information.

[1481] A "pop-up notification" refers to a short message displayed on an application to immediately notify the user of important information.

[1482] A "generative AI model" refers to a mathematical model generated by artificial intelligence technology for analysis and prediction.

[1483] A "prompt" refers to a textual instruction or question that is input into a generative AI model.

[1484] This invention relates to a system that uses a smartphone or head-mounted display (HMD) to quickly detect fraudulent applications and notify nearby stores in real time. It also includes the aggregation and analysis of past fraudulent application data, and the visualization and provision of the results.

[1485] 1. Program Generation

[1486] The system mainly consists of the following components:

[1487] Detection methods for detecting fraudulent applications

[1488] A means for transmitting detected fraudulent application information to a server.

[1489] A means of storing submitted information in a database

[1490] A visualization method for displaying stored information on a map using GIS

[1491] An alerting method that automatically sends alerts to nearby stores

[1492] The store that receives the fraudulent application information receives it on their smartphone or HMD.

[1493] Analysis tool that aggregates and analyzes past data and outputs the results

[1494] 2. Explain the program's processing in natural language

[1495] The server includes the following hardware and software:

[1496] Hardware: Cloud Server

[1497] Software: Python, Flask (backend), GIS software (e.g., Folium), data analysis library (Pandas)

[1498] A smartphone and HMD are installed on the terminal side and function as follows.

[1499] Detection Method

[1500] When a user detects a fraudulent application, they enter information about the fraudulent application using a dedicated interface, including the date and time of the application, information about the applicant, and details of any suspicious behavior.

[1501] Transmission and storage methods

[1502] The device receives this input information, validates it, and then sends it to the server, which then stores it in a secure database.

[1503] Visualization tools

[1504] The server uses GIS to display the saved fraudulent application information on a map. Specifically, it obtains the location information of the store where the fraudulent application occurred and displays it as a marker on the map.

[1505] Alert and Receipt Methods

[1506] When a fraudulent application is detected, the server automatically generates an alert to nearby stores and notifies them on smartphones or HMDs, allowing users to immediately take precautions.

[1507] analytical means

[1508] The server aggregates past fraudulent application data and performs statistical analysis, and the results of this analysis are displayed visually in the form of dashboards and reports.

[1509] 3. Adding concrete examples and prompts

[1510] Specific examples

[1511] Users can enter information such as "foreigner," "October 15th, 13:45," and "suspicious behavior" on their smartphones, and an alert is instantly sent to other stores within a 1km radius. At the same time, the server analyzes fraudulent application data from the past year and displays the results on a dashboard.

[1512] Prompt Sentence Examples

[1513] Based on the information below, please design a system that notifies other nearby stores in real time when a fraudulent application is detected and analyzes past fraudulent application data.

[1514] Date and time of fraudulent application: October 15th, 13:45

[1515] Applicant information: Foreigner

[1516] Fraudulent Activity Details: Suspicious Activity

[1517] This system, configured in this way, quickly detects fraudulent applications, notifies relevant parties in real time, and provides analytical information using past data to take effective countermeasures, thereby preventing the spread of fraudulent activity and accelerating response.

[1518] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1519] Step 1:

[1520] When a user detects a fraudulent application, they use a smartphone or head-mounted display to enter the application date and time, applicant information, and details of suspicious behavior into a dedicated interface. The entered information is saved in temporary memory on the device. Input data includes the application date and time, applicant information, and details of suspicious behavior. The application information saved in temporary memory is obtained as output data.

[1521] Step 2:

[1522] The terminal validates the entered information. Specifically, it checks whether all required fields in the input data are filled in and whether the data format is correct. For example, it checks the date format and the format of the applicant information. If validation is successful, it proceeds to the next step. The input data is data in temporary memory, and the output data is the result of validation.

[1523] Step 3:

[1524] The terminal sends the information that has passed validation to the server. The transmission is done using an HTTP request (POST method). The input data is the application information on the terminal side, and the output data is the application information saved on the server side.

[1525] Step 4:

[1526] The server stores the received information in a secure database. The database is an RDBMS (Relational Database Management System) and the information is inserted into tables. The input data is the application information received by the server and the output data are the records stored in the database.

[1527] Step 5:

[1528] The server obtains latitude and longitude information based on the fraudulent application information stored in the database. This information is then displayed on a map using a geographic information system (GIS). GIS software such as Folium is used. The input data is the latitude and longitude information in the database, and the output data is the location of the fraudulent application displayed on the map.

[1529] Step 6:

[1530] The server executes a database query to identify other stores located within a certain distance (e.g., 1 km) around the store where the fraudulent claim was detected. The query results in a list of identified stores. The input data is the location information of the fraudulent claim and the surrounding stores, and the output data is a list of identified surrounding stores.

[1531] Step 7:

[1532] The server generates a warning message for the identified stores and sends an alert. The warning message includes the name of the store where the fraudulent application occurred, the date and time, and important points to note. This is sent to the smartphone or HMD. The input data is a list of identified stores, and the output data is the sent warning message.

[1533] Step 8:

[1534] The terminal receives the alert and displays it to the user as a pop-up notification. The pop-up notification contains a warning message that the user can view and respond to immediately. The input data is the warning message sent from the server, and the output data is the pop-up notification displayed to the user.

[1535] Step 9:

[1536] The server aggregates past fraudulent application data from a database and calculates the number of fraudulent applications within a specified period. Libraries such as Pandas are used for data analysis. The input data is past application information, and the output data is aggregated statistical information.

[1537] Step 10:

[1538] The server performs statistical analysis based on the aggregated data. It uses a generative AI model to analyze patterns in fraudulent application data and displays the results as a dashboard. Specific software operations include data filtering, clustering, and trend analysis. The input data is the aggregated application information, and the output data is a dashboard of the analysis results.

[1539] Through the above steps, the system of the present invention can quickly detect fraudulent applications, immediately notify relevant parties, and provide information using past data to take effective measures.

[1540] 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.

[1541] This invention relates to a system for effectively detecting and quickly responding to fraudulent applications. This system enhances risk assessment of fraudulent applications by combining fraudulent application detection, real-time information transmission, visualization using a geographic information system (GIS), alert notifications to nearby stores, analysis of past data, and an emotion engine that recognizes user emotions.

[1542] As a specific embodiment for implementing the present invention, a flow from detecting a fraudulent application to sharing information, issuing an alert, and analyzing using an emotion engine will be described.

[1543] Detecting and recording fraudulent applications

[1544] 1. When a user (shop crew member) detects a suspicious contract application, they use a dedicated interface to enter the suspicious contract application information into the system. This includes the application date and time, applicant information, and details of the suspicious behavior. The emotion engine also analyzes the user's emotional state in real time and records this information.

[1545] 2. The device receives the entered information, first stores it in a local database, and then validates it to ensure that required fields are filled in properly and that the data format is correct.

[1546] 3. The terminal sends the information that has passed validation to the server, where it is stored in a secure database.

[1547] Real-time processing and visualization of information

[1548] 1. The server processes the fraudulent application information stored in the database in real time and displays it on a map using a geographic information system (GIS). Here, the server obtains the latitude and longitude information of the store and, in conjunction with the GIS API, displays the location of the fraudulent application on the map with a red icon or a specific color, clearly showing the location of the fraudulent application.

[1549] 2. The emotion engine analyzes the user's emotional data when a fraudulent application is made, and integrates and displays the results in a visualization tool. This allows users to visually confirm the risk assessment of fraudulent applications.

[1550] Alert notifications to nearby stores

[1551] 1. The server uses a database query to identify other stores within 1 km of the store where the fraudulent claim was detected. The query returns a list of nearby stores.

[1552] 2. The server automatically generates a warning message and sends an alert to the identified nearby stores. The alert includes the store where the fraudulent application occurred, the date and time, and points to note.

[1553] 3. The terminal receives the alert and displays it to the user (shop crew) as a pop-up notification, allowing the user to immediately become alert to suspicious applications and take appropriate measures.

[1554] Historical data analysis

[1555] 1. The server aggregates past fraudulent application data from the database and calculates the number of fraudulent applications within a specified period (for example, one year). This is achieved by performing statistical data processing.

[1556] 2. The server performs statistical analysis on the aggregated data to identify which stores have experienced fraudulent applications and how frequently. The results are then generated as a dashboard or report.

[1557] 3. The emotion engine analyzes past application data and user emotional data to identify patterns of fraudulent applications, improving the accuracy of detecting subtle fraudulent behavior.

[1558] 4. The analysis results generated by the server are sent to the device and displayed visually on a dashboard, allowing users (administrators and shop crew) to understand trends and patterns in fraudulent applications and use this information to take future countermeasures.

[1559] Specific examples

[1560] 1. A user (shop crew member) detects a suspicious contract application from a foreigner at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into the dedicated system. At the same time, the emotion engine analyzes the user's facial expression and tone of voice, and records their emotional state, such as "tension" or "anxiety."

[1561] 2. The device receives this input information, validates it, and then sends it to the server, which stores it in a database and displays it on a map, integrating GIS and emotion data.

[1562] 3. The server identifies five stores within 1 km of the store in question, generates an alert, and sends it. The device displays the received alert as a pop-up, and the user can confirm the notification.

[1563] 4. The server aggregates application data and emotion data from the past year, and displays the analysis results on the dashboard, showing that 10 fraudulent applications occurred in October. The emotion engine also evaluates the risk of fraudulent applications based on the emotion data, and reflects this in the analysis results.

[1564] This series of processes, combined with emotional data, strengthens risk assessment of contract fraud, enabling swift and effective response.

[1565] The processing flow will be explained below.

[1566] Step 1:

[1567] A user (shop crew member) detects a suspicious contract application and enters the suspicious contract application information into the system through a dedicated interface. The information entered includes the date and time of the application, applicant information, and details of suspicious behavior. An emotion engine also analyzes the user's facial expressions and tone of voice in real time, and records emotional data such as "tension" and "anxiety."

[1568] Step 2:

[1569] The device receives this information, temporarily stores it in a local database, and then validates the information to ensure that required fields are filled in properly and that the data format is correct.

[1570] Step 3:

[1571] The terminal sends the information that has passed validation to the server, where it is stored in a secure database.

[1572] Step 4:

[1573] The server processes the fraudulent application information and emotion data stored in the database in real time and displays it on a map using a geographic information system (GIS). It obtains the latitude and longitude information of stores and, by linking with the GIS API, shows the locations of fraudulent applications visually by displaying them on the map with red icons or specific colors. At the same time, it performs a risk assessment using emotion data and visualizes the results.

[1574] Step 5:

[1575] The server uses a database query to identify other stores within 1 km of the store where the fraudulent claim was detected, and the stores listed by the query are then automatically targeted for alert notifications.

[1576] Step 6:

[1577] The server automatically generates a warning message and sends an alert to the identified surrounding stores. This alert includes the store where the fraudulent application occurred, the date and time, points to be careful about, and the risk assessment results based on the emotion engine.

[1578] Step 7:

[1579] The terminal receives the alert and displays it to the user (shop crew) as a pop-up notification, allowing the user to immediately become alert to suspicious applications and take appropriate measures.

[1580] Step 8:

[1581] The server aggregates past fraudulent application data and emotion data from the database and calculates the number of fraudulent applications and emotion trends within a specified period (e.g., one year). This is achieved by performing statistical data processing.

[1582] Step 9:

[1583] The server performs statistical analysis based on the aggregated data to determine which stores have experienced fraudulent applications and how frequently they have occurred, as well as the associated emotional data to determine risk assessment results. These results are then generated as dashboards and reports.

[1584] Step 10:

[1585] The analysis results generated by the server are sent to the terminal and displayed visually on a dashboard, allowing users (administrators and shop crew) to understand trends and patterns of fraudulent applications and user emotional tendencies, and use this information to help with future countermeasures.

[1586] Specific examples

[1587] 1. A user (shop crew member) detects a suspicious contract application from a foreigner at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into the dedicated system. At the same time, the emotion engine analyzes the user's facial expression and tone of voice, and records their emotional state, such as "tension" or "anxiety."

[1588] 2. The device receives this input information, validates it, and then sends it to the server, which stores it in a database and displays it on a map, integrating GIS and emotion data.

[1589] 3. The server identifies five stores within 1 km of the store in question, generates an alert, and sends it. The device displays the received alert as a pop-up, and the user can confirm the notification.

[1590] 4. The server aggregates application data and emotion data from the past year, and displays the analysis results on the dashboard, showing that 10 fraudulent applications occurred in October. The emotion engine also evaluates the risk of fraudulent applications based on the emotion data, and reflects this in the analysis results.

[1591] This series of processes, combined with emotional data, strengthens risk assessment of contract fraud, enabling swift and effective response.

[1592] Example 2

[1593] 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."

[1594] Conventional fraudulent application detection systems have had issues with delayed response after detecting fraudulent applications and providing only limited information. Furthermore, risk assessment is insufficient because the system does not take into account the user's emotional state. As a result, early detection of fraudulent applications and effective implementation of preventative measures are sometimes ineffective. Furthermore, there is a lack of a way to visually grasp the location of fraudulent applications and the surrounding situation.

[1595] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1596] In this invention, the server includes application means for detecting fraudulent applications, transmission means for transmitting detected fraudulent application information to the server in real time, storage means for saving the transmitted fraudulent application information in a database, visualization means for displaying the saved fraudulent application information on a map using a geographic information system, emotion analysis means for analyzing the emotional state of users at the location where the fraudulent application occurred and recording the information in real time, alert means for automatically sending alerts to other locations located in the vicinity of the location where the fraudulent application occurred, and analysis means for compiling and analyzing the information based on past fraudulent application information and the emotional state of users and outputting it as a report. This significantly improves risk assessment of fraudulent applications and enables quick and effective response.

[1597] "Fraudulent application" refers to an application or attempted contract made with fraudulent intent.

[1598] "Application method" refers to the interface or mechanism for detecting fraudulent applications.

[1599] "Transmission means" refers to the method or technology for transmitting detected fraudulent application information to a server in real time.

[1600] "Storage means" refers to a mechanism for safely storing submitted fraudulent application information in a database.

[1601] "Visualization means" refers to technology that displays stored fraudulent application information on a map using a geographic information system.

[1602] "Emotion analysis means" refers to technology that analyzes the emotional state of users at the location where fraudulent applications occur and records that information in real time.

[1603] "Alert method" refers to a mechanism that automatically sends a warning to other locations located in the vicinity of the location where the fraudulent application occurred.

[1604] "Analysis methods" refers to technology for compiling and analyzing information based on past fraudulent application information and the user's emotional state, and outputting it as a report.

[1605] A "geographic information system" refers to a system that handles geospatial information and visualizes data on a map.

[1606] "User" refers to an individual or person with a role who uses this system to detect, record, and address fraudulent applications.

[1607] "Server" refers to a computer device that manages the processing of the entire system and collects, stores, and processes fraudulent application information and emotion analysis data.

[1608] "Database" refers to an information management system for organizing and storing fraudulent application information and related data.

[1609] The present invention provides a system for effectively detecting and quickly responding to fraudulent claims, which enhances risk assessment of fraudulent claims by combining fraudulent claim detection, real-time information transmission, visualization using a geographic information system (GIS), alert notification to other locations in the vicinity, analysis of historical data, and user sentiment analysis.

[1610] Detecting and recording fraudulent applications

[1611] First, when a user (shop crew member) detects a suspicious contract application, they use a dedicated interface to enter the date and time of the application, applicant information, and details of the suspicious behavior into the system. As this information is entered, an emotion engine analyzes the user's emotional state (e.g., tension, anxiety) in real time, and this information is also recorded. This analysis uses technology that analyzes facial expressions and tone of voice using a camera and microphone.

[1612] The device then temporarily stores this information in a local database and performs validation, such as checking for missing required fields and checking the date format. If the information passes validation, it is sent from the device to the server, where it is stored in a secure database.

[1613] Real-time processing and visualization of information

[1614] The server processes the stored fraudulent application information in real time and displays it on a map using a geographic information system (GIS), such as Google Maps API, to clearly indicate the location of fraudulent applications using, for example, a red icon.

[1615] The emotion engine also integrates the analyzed emotion data into visualization tools and displays them on a map. Emotional states are displayed as appropriate icons (e.g., emoji faces), allowing users to visually assess the risk of fraudulent applications.

[1616] Alert notifications to nearby stores

[1617] The server uses a database query to identify other locations within 1 km of the location where the fraudulent claim was detected. It uses SQL queries to compile a list of nearby locations and then generates and sends out an alert. The alert includes the location, date, and time of the fraudulent claim, as well as any important points to note.

[1618] The terminal receives this alert and displays it to the user (shop crew) as a pop-up notification, allowing the user to immediately check the information and take necessary measures.

[1619] Historical data analysis

[1620] The server aggregates past fraudulent application data from the database and calculates the number of fraudulent applications within a specified period (e.g., the past year). This process involves extracting the data using SQL queries and performing statistical processing and visualization using Python tools such as Pandas and Matplotlib.

[1621] The emotion engine combines and analyzes past fraudulent application data with user emotion data to identify patterns of fraudulent applications. It uses a clustering algorithm to extract specific behavioral and emotional patterns. The server visually displays the results of this analysis on a dashboard, allowing users (administrators and shop crew) to understand trends and patterns in fraudulent applications and develop preventative measures.

[1622] Specific examples

[1623] For example, a user (shop crew member) detects a suspicious contract application made by a foreigner at 1:45 PM on October 15th and enters information such as "October 15th, 1:45 PM," "foreigner," and "suspicious behavior" into the dedicated system. At the same time, the emotion engine analyzes the user's facial expressions and tone of voice, and records their emotional state, such as "tension" or "anxiety."

[1624] The device receives this information, validates it, and then sends it to the server, which stores it in a database and displays it on a map, integrating GIS and emotion data.

[1625] The server identifies five other locations within 1 km of the location and generates and sends an alert, which the device displays as a pop-up for the user to confirm.

[1626] The server aggregates application data and emotion data from the past year, and displays the analysis results on the dashboard, showing that 10 fraudulent applications occurred in October. The emotion engine also evaluates the risk of fraudulent applications based on the emotion data, and reflects this in the analysis results.

[1627] When using a generative AI model, you might use prompts like the following:

[1628] "At 13:45 on October 15th, a foreigner exhibited suspicious behavior. The user's emotional state was 'tension' and 'anxiety'."

[1629] The comprehensive operation of the system as described above will strengthen risk assessment of fraudulent applications and enable swift and effective responses.

[1630] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1631] Program processing steps

[1632] Detecting and recording fraudulent applications

[1633] Step 1:

[1634] A user (shop crew member) detects a suspicious contract application. Using a dedicated interface, the user enters the application date and time, applicant information, and details of suspicious behavior. The entered data is in text format and separated into specific fields. This input information is sent directly to the next processing step, while the emotion engine simultaneously analyzes the user's emotional state. This analysis uses a camera and microphone to evaluate facial expressions and tone of voice in real time.

[1635] Step 2:

[1636] The terminal receives the information entered by the user. The entered data is temporarily stored in a local database and validated. Specific validation details include whether all required fields (e.g., application date and time, applicant information) are filled in, whether the date format is correct, and whether the details of suspicious activity are 50 characters or more. Information that passes validation is sent to the next process as a new data structure.

[1637] Step 3:

[1638] The device sends the information that has passed validation to the server. The data is encrypted during transmission. The transmitted data includes the application date and time, applicant information, details of suspicious behavior, and emotion analysis results. The server receives this data and stores it in a secure database.

[1639] Real-time processing and visualization of information

[1640] Step 4:

[1641] The server retrieves the fraudulent application information stored in the database and begins processing it in real time. The input data here is detailed information about the fraudulent application and the results of sentiment analysis. The server retrieves the latitude and longitude information of the store from a GIS API (e.g., Google Maps API) and displays the location of the fraudulent application on a map with a red icon. This display data is generated in real time through requests to the GIS API.

[1642] Step 5:

[1643] The emotion engine takes the analyzed emotion data and integrates the results into a visualization method. Specifically, it adds icons (e.g., emoji faces) indicating the emotional state to the locations of fraudulent claims on a map. The input data includes the emotion analysis results, and the output data consists of the visual display information of the GIS.

[1644] Alert notifications to nearby stores

[1645] Step 6:

[1646] The server uses a database query to identify other locations within 1 km of the location where the fraudulent claim was detected. The input data for this process includes the latitude and longitude of the fraudulent claim, and uses an SQL query to list other nearby locations. The output data is a list of the identified nearby locations.

[1647] Step 7:

[1648] The server generates a warning message for the identified nearby locations and sends an alert. The alert contains the location, date, and time of the fraudulent application, as well as points to note, and this information is generated automatically. The input data is the list of identified nearby locations and the fraudulent application information, and the output data is the alert message and its transmission status.

[1649] Step 8:

[1650] The alert received by the terminal is displayed to the user (shop crew) as a pop-up notification. Specifically, the user is immediately notified of the warning through desktop or mobile notifications. The input data of this process is the alert message sent from the server, and the output data is the notification confirmation status sent to the user.

[1651] Historical data analysis

[1652] Step 9:

[1653] The server aggregates past fraudulent application data from the database. It uses an SQL query to extract data to calculate the number of fraudulent applications for a specified period (e.g., the past year). The input data is detailed information about fraudulent applications, and the output data is the number of fraudulent applications for the specified period.

[1654] Step 10:

[1655] The server performs statistical analysis based on the collected data. Python's Pandas and Matplotlib are used to generate graphs and heat maps to visualize the number and location of fraudulent applications. The input data is the number of fraudulent applications within a specified period, and the output data is visualized data of the analysis results.

[1656] Step 11:

[1657] The emotion engine combines and analyzes past fraudulent application data with user emotion data. It uses a clustering algorithm to extract specific behavioral and emotional patterns. The input data is fraudulent application information and emotion data, and the output data is the extracted behavioral and emotional patterns.

[1658] Step 12:

[1659] The analysis results generated by the server are sent to the terminal and displayed visually on a dashboard. This allows users (administrators and shop crew) to understand trends and patterns of fraudulent applications and use them to develop future countermeasures. The input data is the analysis results sent from the server, and the output data is the visual display information on the dashboard.

[1660] This series of processing steps significantly strengthens the risk assessment of fraudulent applications and enables a fast and effective response.

[1661] (Application example 2)

[1662] 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."

[1663] Conventional fraudulent application detection systems can detect fraudulent applications and issue warnings, but they ignore the user's emotional state and lack information to better understand fraudulent behavior. Furthermore, they lack the ability to visualize fraudulent application information or send alerts to nearby stores in real time, making it difficult to respond immediately. Furthermore, analysis of past fraudulent application data is insufficient, making it difficult to assess the risk of recurrence. ...

Claims

1. an application means for detecting fraudulent applications; a transmitting means for transmitting the detected fraudulent application information to a server in real time; a storage means for storing the submitted fraudulent application information in a database; A visualization means for displaying the stored fraudulent application information on a map using a geographic information system; An alerting means for automatically sending an alert to other stores located around the store where the fraudulent application occurred; An analytical method to compile and analyze past fraudulent application data and output it as a report, A system including:

2. 2. The system according to claim 1, wherein the alert means is means for simultaneously issuing an alert to a plurality of stores within a certain distance therearound.

3. 2. The system according to claim 1, wherein the visualization means utilizes a geographic information system to display the store where the fraudulent application occurred and its surrounding stores in different colors.

Images